List of papers accepted for ICPR 2026

Hstc-Moseg: A Hierarchical Spatially Adaptive And Temporally Consistent Network For Radar Point Cloud Moving Object Segmentation

Luo, Zhengjie; Zhang, Jinlai; Deng, Qinrui; Yan, Ruyu; Gao, Kai; Chao, Ong Zhi

Visual Instruction-Finetuned Language Model For Versatile Brain Mr Image Tasks

Kim, Jonghun; Ra, Sinyoung; Park, Hyunjin

Deep Kernel Video Approximation For Unsupervised Action Segmentation

Pintea, Silvia; Dijkstra, Jouke

Skeleton-Snippet Contrastive Learning With Multiscale Feature Fusion For Action Localization

Cheng, Qiushuo; Liu, Jingjing; Morgan, Catherine; Whone, Alan; Mirmehdi, Majid

A Study In Dataset Distillation For Image Super-Resolution

Dietz, Tobias; Moser, Brian ; Nauen, Tobias; Raue, Federico; Frolov, Stanislav; Dengel, Andreas

A Low-Resolution Image Is Worth 1X1 Words: Enabling Fine Image Super-Resolution With Transformers And Taylorshift

Nagaraju, Sanath; Moser, Brian ; Nauen, Tobias; Frolov, Stanislav; Raue, Federico; Dengel, Andreas

Retinexdual: Retinex-Based Dual Nature Approach For Generalized Ultra-High-Definition Image Restoration

Kishawy, Mohab; Hussein, Ali Abdellatif; Chen, Jun

Dinolight: Robust Ambient Light Normalization With Self-Supervised Visual Prior Integration

Oh, Youngjin; Kwon, Junhyeong; Cho, Nam Ik

Prompt Injection Attacks On Llm Generated Reviews Of Scientific Publications

Keuper, Janis

Cure: Controllable Unified Image Restoration For Complex Degradations

Kim, Boseong; Cho, Donghyeon

Visual Model Checking: Graph-Based Inference Of Visual Routines For Image Retrieval

Molina Rodríguez, Adrià; Ramos Terrades, Oriol; Lladós Canet, Josep

Np-Desire-Gs: Neighborhood Planarity-Enhanced Gaussian Splatting For Robust Static-Dynamic Object Separation And Surface Alignment In Urban Driving Scenes

Verma, sachin; Wintel, Florian ; Lindseth, Frank; Kiss, Gabriel

Metamoa: Top-Down Dynamic Guidance For Parameter-Efficient Domain Generalization

Soliman, Mahmoud; Radwan, Ahmed; Abdelaziz, Omar; S. Shehata, Mohamed

$M^2$Pose: Robust 6D Object Pose Estimation Via Multi-Frequency Surface Encoding And Multi-Reference Voting

Park, Jaewoo; Kim, Jaeguk; Cho, Nam Ik

Hypercore: Coreset Selection Under Noise Via Hypersphere Models

Moser, Brian ; Shanbhag, Arundhati; Nauen, Tobias; Frolov, Stanislav; Raue, Federico; Folz, Joachim; Dengel, Andreas

Lfg: Local Controllable 3D Generation Using Latent Flexible Grid Representation

Zhang, Kaiyi; Han, Tian; Quan, Long

Automated Visualization Code Synthesis Via Multi-Path Reasoning And Feedback-Driven Optimizations

Seo, Wonduk; Kang, Daye; An, Hyunjin; Kim, Taehan; Cho, Soohyuk; Yu, Minhyeong; Lee, Seungyong; Park, Jian; Bu, Yi; Lee, Seunghyun

Dualsight: Learning To Disentangle Artifact And Semantic Features For Detection Of Diffusion-Generated Images

Abdullah, Ahmed; Ebert, Nikolas; Wasenmüller, Oliver

Autoreframe: Context-Aware Horizontal-To-Vertical Video Transformation With Temporal Smoothness

Shen, Minmin; Li, Ce; Feng, Yarong; Zhang, Yixiao; Jin, Haiyun; Chamarahalli Arunkumar, Ganesh Samarth; Lin, Shih-Yao; Tabarestani, Solale; Chen, Caren

Efficient Post-Hoc Calibration In Object Detection Without Held-Out Data

Ebert, Nikolas; Stricker, Didier; Wasenmüller, Oliver

A Framework For Low-Effort Training Data Generation For Urban Semantic Segmentation

Kalšan, Damjan; Zavadski, Denis; Küchler, Tim; Lee, Haebom; Roth, Stefan; Rother, Carsten

Ac^2-Fuse: Syntax-Preserving Canonicalization And Cross-Model Curvature For Detecting Llm-Generated Code

Yang, Yuchen; Huang, Enhao; Xia, Chunshu; Yang, Bingrun; Pan, Tongtong; Zhang, Zhiyu; Dong, Dong; Qin, Zhan

Smoothed-Modernbert: Co-Attentional Synergy Of Probabilistic Topic Models And Modernbert Through Dynamic Fusion

Ojo, Akinlolu; Bouguila, Nizar

Feddg-Moe-Nf: Prototypical Normalizing Flow Networks For Federated Domain Generalization

Abdelaziz, Omar Abdelaziz Morgan; Osama, Mahmoud; Radwan, Ahmed; ElGazwy, Ahmed; Shehata, Mohamed S.

Physics-Guided 3D Convolutional Learning For Accurate Springback Error Prediction In Single Point Incremental Forming

Chen, Du; Coenen, Frans; Nguyen, Anh; Penalva Oscoz, Mariluz; Martin Rebe, Ander; Hai, Yang

Immunotrace: A Meta-Agent For Immune History Tracking

Ma, Jiahao; Li, Hongzong; Hu, Yefan; Huang, Jian-dong

Occlusion-Ordered Semantic Instance Segmentation

Baselizadeh, Soroosh; Yu, Cheuk-To; Veksler, Olga; Boykov, Yuri

An Ai Agent For Immune Receptor Fingerprint‑Based Diagnosis Of Infection Of Unknown Origin

Ma, Jiahao; Li, Hongzong; Hu, Yefan; Huang, Jian-dong

Univariate Channel Fusion For Multivariate Time Series Classification

Moro, Fernando; Souza, Vinicius

Bem: Training-Free Background Embedding Memory For False-Positive Suppression In Real-Time Fixed-Background Camera

Park, Junwoo; Lee, Jangho; Lim, Sunho

Image Thresholding: Understanding Bias Of Evaluation Metrics Towards Specific Evaluation Functions

Hegazy, Eslam; Gabr, Mohamed

Psformer: Parameter-Efficient Transformer With Segment Shared Attention For Time Series Forecasting

wang, yanlong; Xu, Jian; Ma, Fei; Zhang, Hongkang; Huang, Shao-Lun; Sun, Danny Dongning; Zhang, Xiao-Ping

Towards Time Series Generation Conditioned On Unstructured Natural Language

Woo, Jaeyun; Lee, Jiseok; Iwana, Brian Kenji

Lisu: Composable Layer-Wise Selective Unlearning For Large Language Models

Hendricks, Arne

A Prototypical Signature Approach For Writer-Independent Offline Signature Verification

Moura, Kecia; Sabourin, Robert; Cruz, Rafael

Deca-Net: A Dual-Encoder Network Leveraging Pre/Post-Contrast Comparison For Coronary Artery Segmentation

庆鑫, 倪; 朝路, 冯; 睦卿, 张; 金柱, 杨

Training Free Zero-Shot Image Anomaly Localisation Via Diffusion Inversion

Hicsonmez, Samet; Shabayek, Abd El Rahman; AOUADA,  Djamila

Towards Safer Mobile Agents: Scalable Generation And Evaluation Of Diverse Scenarios For Vlms

Taniguchi, Takara; Saito, Kuniaki; Hashimoto, Atsushi

Cg-Clip: Seeing Beyond Objects To Improve Ood Corruption Detection

Jain, Darshita; Ali, Asmat; Majumder, Anima

Corkhsi: Hyperspectral Anomaly Detection In Corks Using An Autoencoder With A Novel Spectral–Spatial Loss Optimization

Dini, Afshin; Delirie, Farnaz; Rahtu, Esa

Panosamic: Panoramic Image Segmentation From Sam Feature Encoding And Dual View Fusion

Chamseddine, Mahdi; Stricker, Didier; Rambach, Jason

Revisiting Point Cloud Representations Across Heterogeneous Sensors

Reichardt, Laurenz; Speckert, Mario; Musiat, Alexander; Wasenmüller, Oliver

Enhancing Micrograph Denoising Via Semantic-Aware Knowledge Learning

Cao, Chengzhi; Xu, Min

Yolov8-Cbam For Wtb Defect Segmentation

Mendes Ramon, Stevan Henrique

Visg Av-Hubert: Viseme-Guided Av-Hubert

Papadopoulos, Aristeidis; Jain, Rishabh; Harte, Naomi

A Large Language Model Framework For Predicting Judicial Outcomes In Civil Law Systems

A. Araujo, Alan; O. Santin, Altair; Viegas, Eduardo

Sra-Seg: Synthetic To Real Alignment For Semi-Supervised Medical Image Segmentation

Aranya, OFM Riaz Rahman; Desai, Kevin

Collidenet: Hierarchical Multi-Scale Video Representation Learning With Disentanglement For Time-To-Collision Forecasting

Desai, Nishq; Etemad, Ali; Greenspan, Michael

All-In-One Conditioning For Text-To-Image Synthesis

Jayasekara, Hirunima; Huynh, Chuong; Ren, Yixuan; Acquaye, Christabel; Shrivastava, Abhinav

State Of Charging Attack Detection Using Multi-Scale Feature Extraction And Attention Mechanism

Su, Yan; Zhang, Jinlai; Yang, Yuanhao; Qi, Pengfei; Wang, Yuting

Whitecon: Semi-Supervised Domain Adaptation Regression Through Whitening Transform And Dual Consistency

Sim, Sejin; Kim, SeoungBum

Uncovering Logit Suppression Vulnerabilities In Llm Safety Alignment

li, yuxi; Liu, Yi; Li, Yuekang; Shi, Ling; Deng, Gelei; Chen, Shengquan; Wang, Kailong

Complementary Attention Parameter-Efficient Fine-Tuning

Zhang, Chushan; Lu, Ruihan ; Tong, Jinguang; Li, Xuesong ; Li, Hongdong

Benchmarking Document Parsers On Mathematical Formula Extraction From Pdfs

Horn, Pius; Keuper, Janis

Semalign: Language Guided Semi-Supervised Domain Generalization

Fernando, Muditha; Kailainathan, Kajhanan; Nagaratnam, Krishnakanth; Senavirathne, Isuranga; Rodrigo, Ranga

Revnet: Rotation-Equivariant Point Cloud Completion Via Vector Neuron Anchor Transformer

Ni, Zhifan; Steinbach, Eckehard

Compositional Novelty Metrics For Graph-Structured Data

Joshi, Rucha Bhalchandra; Mishra, Subhankar

Adafocus: Instruction-Aware Dynamic Visual Token Compression For Efficient Multi-Modal Understanding

ye, zihang; liu, xianzhong

Tas-Gnn: A Status-Aware Signed Graph Neural Network For Anomaly Detection In Bitcoin Trust Systems

Xue, Chang; Liu, Fang; Wang, Jiaye; Xing, Jinming; Yang, Chen

Tunemia: Membership Inference Attack On Latent Diffusion Models

Azulay, Noam; Habler, Idan; Shabtai, Asaf; Elovici, Yuval

Bridging The Semantic Gap For Categorical Data Clustering Via Large Language Models

Yang, Zihua; Liao, Xin; Zhang, Yiqun; Cheung, Yiu-ming

Markovian Reeb Graphs For Simulating Spatiotemporal Patterns Of Life

Subrahmanya, Anantajit; Gudavalli, Chandrakanth; Levenson, Connor; Manjunath, B.S.

Flexible Knowledge Distillation For Class-Incremental Learning Via Structural Knowledge Transfer

Seungmo, Seo; Youn, Jongsu; Bae, Jaehyung; Choi, Jongwon

Diabetic Complication Progression Prediction Based On Hierarchical Reinforcement Path Reasoning

Dai, Jin; Yuan, Meng; Zhang, Zhen; Zhang, Ziwen

Beyond Consistency: Explicit Boundary Learning For Semi-Supervised Ovarian Tumor Segmentation

Vu, Minh-Khoa; Bui, Hoang-Son; Le, Thi-Lan

Seeing Red, Thinking Bad: Color Bias In Vision Language Models

Ide, Kohsuke; Yamada, Ryousuke; Fukuhara, Yoshihiro; Kataoka, Hirokatsu; Satoh, Yutaka

Drivingworld: Constructing World Model For Autonomous Driving Via Video Gpt

Hu, Xiaotao; Jia, Mingkai; Guo, Xiaoyang; Zhang, Qian; Long, Xiaoxiao; Yin, Wei

Hypdomain: Bridging Domain Gaps In Clip With Few-Shot Hypernetwork Residuals

Ghosh, Souvik; Jawahar, C. V.; Namboodiri, Vinay

Most: Momentum Online Subspace Training

Souza, Lincon; Kobayashi, Takumi; Batalo, Bojan

Stpose: Unseen Object Pose Estimation With A Single Template Via Query-Aware 3D Reconstruction

Kim, Jaeguk; Cho, Nam Ik

Normalized Matching Transformer

Pourhadi, Abtin; Swoboda, Paul

Watching Ice Through The Crowd: Computer Vision On Social Media Images For Glacier Monitoring

Paradise Vit, Abigail

Approximate Nearest Neighbor Using Hierarchical K-Means For Seed Classification

Cecotti, Hubert; Gonzales, Ivan

Telerank: Pairwise Ranking Of Temporal Driver Performance Using Telemetry

Röscher, Anton; van der Haar, Dustin

Lunar-G2R: Geometry-To-Reflectance Learning For High-Fidelity Lunar Brdf Estimation

Grethen, Clémentine; Menga, Nicolas; Brochard, Roland; Morin, Géraldine; Gasparini, Simone; Lebreton, Jérémy ; Gestido, Manuel Sanchez

Cascadeformer: A Family Of Two-Stage Cascading Transformers For Skeleton-Based Human Action Recognition

Peng, Yusen; Yilmaz, Alper

More Interpretable Decision Trees: Pruning Via Node Descent And The Delta Penalty

Carreira-Perpinan, Miguel; Hada, Suryabhan Singh

Representation Learning With Semantic-Aware Instance And Sparse Token Alignments

Bui, Phuoc-Nguyen; Nguyen, Toan Duc; Bum, Junghyun; Le, Duc-Tai; Choo, Hyunseung

Diversity-Aware Multi-Prompt Learning For Compositional Zero-Shot Learning

Chen, Ziyi; Zhao, Xinru; Lang, Congyan

P4: Place With Purpose -- Pose And Prompt-Guided Human Synthesis In Real Scenes

KHAN, DADAN; Zohaib, Mohammad; Timofte, Radu; Odone, Francesca

Llm-Based Poi Recommendation Incorporating Explicit Behavior Pattern

Yao, Xin; Luo, Xiangfeng; Chen, Xue; Zhu, Jinhui

Investigating Permutation-Invariant Discrete Representation Learning For Spatially Aligned Images

Stirling, Jamie; Al-Moubayed, Noura; Shum, Hubert

Refinerag: Word-Level Poisoning Attacks Via Retriever-Guided Text Refinement

Wang, Ziye; Wang, Guanyu; Wang, Kailong

Weeddiffusion: A Dual-Branch Synthetic Augmentation Framework For Weed Mapping

De Marinis, Pasquale; Iammarino, Antonio; Vessio, Gennaro; Castellano, Giovanna

Nvs-Ho: A Benchmark For Novel View Synthesis Of Handheld Objects

Ali, Musawar; Carranza-García, Manuel; Fioraio, Nicola; Salti, Samuele ; Di Stefano, Luigi

When Safe Models Merge Into Danger: Exploiting Latent Vulnerabilities In Llm Fusion

Li, Jiaqing; Zhang, Zhibo; Zhou, Shide; Li, Yuxi; Yu, Tianlong; Wang, Kailong

Trusted But Tainted: Enrolment Perturbations That Undermine Morphing Attack Detection And Face Recognition

Kamble, Dhammadip; Patwardhan, Sushrut; Sao, Anil; Sharma, Arvind; Ramachandra, Raghavendra

Training-Free Photo-Realistic Point Cloud Rendering Via Geometry-Aware Densification And Multi-View Refinement

Sato, Shogo; Murasaki, Kazuhiko; Tanida, Ryuichi

Higher-Order Adversarial Patches For Real-Time Object Detectors

Bayer, Jens; Münch, David; Becker, Stefan; Arens, Michael; Beyerer, Jürgen

Kinetic Mining In Context: Few-Shot Action Synthesis Via Text-To-Motion Distillation

Cazzola, Luca; Alboody, Ahed

Cxmarena: Unified Dataset To Benchmark Performance In Realistic Cxm Scenarios

Gupta, Karan; Garg, Raghav; Sharma, Kapil

Mgd-Depth: Disentangling Scene Dynamics Via Multi-Granularity Representation Learning

Yue, Siting; Ren, Yawei; Li, Jun; Peng, Kebin; He, Sen

Implicit Neural Representations For Efficient Medical Image Segmentation

He, Chong; Zhang, Zhicheng; Luan, Jiuhong; Wei, Zhonglian; Shen, Yuncheng; Yin, Yingyong; Hu, Junjie; Zhang, Yan

Efficient Score Pre-Computation For Diffusion Models Via Cross-Matrix Krylov Projection

Lau, Kai Kwan; Na, Andrew S.; Wan, Justin WL

Gnc-Pose: Geometry-Aware Gnc-Pnp For Monocular 6D Pose Estimation

Liu, Xiujin

Kraft: Kalman Residual Diffusion With Formation Awareness For Uav Swarm Tracking

Rahman, Md. Hasibur; Madria, Sanjay

Wavelet-Driven Spatial And Frequency Domain Representation Learning For Medical Image Segmentation

Wang, Lanping; Li, Mingyong; Ding, Shuaipeng

Hifi-Fg: High-Fidelity Image Inpainting With Frequency Attention And Gated Fusion

Yang, Shaohan; Yang, Fang; Shi, Qingxuan

Learning Cognitive-Aware Representations For Imaging-Based Diagnosis Of Alzheimer’S Disease

Yu, Huan ; Zhang, Yanteng; Wei, Yuxiang; Fu, Yibing; Mei, Siyuan ; Liu, Qiang; Calhoun, Vince

Multiview Pedestrian Detection With Multi Pedestrian Consistency Loss

Kim, Myeongjun

Serum Tumor Marker-Guided Lesion Features Enhancement Network For Lung Cancer Detection

Jiang, Dongxun; Zhang, Dongdong; Li, Wei

Towards Unified Music Emotion Recognition Across Dimensional And Categorical Models

Kang, Jaeyong; Herremans, Dorien

Operational Readiness For Object Detection

Becker, Stefan; Bayer, Jens; Hübner, Wolfgang; Arens, Michael

Planar-Sfm: Camera Pose Estimation Via Homography Graph Embeddings

Pragier, Gabi; Karklinsky, Matan; Ungarish, David; Ben-Cohen, Avi

Dynamic Classifier Ensemble Selection For Data Stream Mining Based On Loca-Global Dominance And Adaptive Online Sampling

Santos, Fernando; Enembreck, Fabricio

Local Autoregression With Finite-Support Random Variables For Image Generation

zhao, chenqiu; Basu, Anup

Diffuflicker: Diffusion-Based Led Traffic Light Flicker Removal In Dashcam Videos

Kim, Sujin; Lee, Juwon; Park, In Kyu

Rarr: Real-Time Attention-Driven Rain Removal With Hierarchical Scale-Aware Efficient Network

eum, seungho; Cho, Ihjjoon; kim, jeonghyeon; choe, junsuk; park, unsang

Hypermil: Hypergraph-Based Channel Reasoning For Multiple Instance Learning On Multivariate Time Series

Del Gaudio, Livia; Cuculo, Vittorio; Cucchiara, Rita

Dual The Reasoning, Double The Insight With Tambi: A Self-Supervised Framework For Skeleton Action Representation

ALI, Mahmoud; Majhi, Snehashis; Yang, Di; Kong, Quan; Francesca, Gianpiero; Bremond, Francois

Snappose3D: Diffusion-Based Single-Frame 2D-To-3D Lifting Of Human Poses

Simoni, Alessandro; Catalini, RIccardo; Di Nucci, Davide; Borghi, Guido; Davoli, Davide; Garattoni, Lorenzo; Francesca, Gianpiero; Kawana, Yuki; Vezzani, Roberto

Fixationformer: Direct Utilization Of Expert Gaze Trajectories For Chest X-Ray Classification

Beckmann, Daniel; Risse, Benjamin

Layergs: Decomposition And Inpainting Of Layered 3D Human Avatars Via 2D Gaussian Splatting

Xu, Yinghan; Dingliana, John

Visually Grounded Language Models Forvisual-Contextual Text Classification.

Raphaëlle, Lemaire; Pantin, Jeremie; Lechervy, Alexis; Kaibaldiyev, Azamat; Maurel, Fabrice; Dias, Gaël; Chahir, Youssef

Adp-Dit: Text-Guided Diffusion Transformer For Brain Image Generation In Alzheimer’S Disease Progression

Lee, Juneyong; Baek, Geonwoo; Jang, Ikbeom

Aster: Latent Pseudo-Anomaly Generation For Unsupervised Time-Series Anomaly Detection

Hermary, Romain; Hicsonmez, Samet; Pineau, Dan; Shabayek, Abd El Rahman; Aouada, Djamila

Unsupervised Learning Of Density Estimates With Topological Optimization

Tanweer, Sunia; Khasawneh, Firas A.

Mamvi: 3D Test-Time Adaptation Via Masked Multi-View Point Clouds

Kong, Inseok; Jung, Geunyoung; Jung,  Jiyoung

Improving Llm First-Token Predictions In Multiple-Choice Question Answering Via Output Prefilling

Cappelletti, Silvia; Poppi, Tobia; Poppi, Samuele; Yong, Zheng Xin; Garcia-Olano, Diego; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita

Pixel-To-4D: Camera-Controlled Image-To-Video Generation With Dynamic 3D Gaussians

de Almeida, Melonie; Ivanova, Daniela; Shi, Tong; Williamson, John; Henderson, Paul

Vamae: Vessel-Aware Masked Autoencoders For Oct-Angiography

Abolade, Ilerioluwakiiye; Mireku, Prince; Chibundu, Kelechi; Ododo, Peace; Idoko, Emmanuel; Omoigui, Promise; Odelola, Solomon

Abmamba: Multimodal Large Language Model With Aligned Hierarchical Bidirectional Scan For Efficient Video Captioning

Yashima, Daichi; Kurita, Shuhei; Oda, Yusuke; Suzuki, Shuntaro; Otsuki, Seitaro; Sugiura, Komei

Growing Your Data: A Data Synthesis Approach For Irregular Time Series Forecasting

Wang, Tong; Chen, Xuxi; Wang, Zhangyang; Ding, Ying

Sportsgpt: An Llm-Driven Framework For Interpretable Sports Motion Assessment And Training Guidance

TIAN, wenbo; LIN, ruting; ZHENG, hongxian; YANG, yaodong; WU, geng; ZHANG, zihao; ZHANG, zhang

Sem-Neus: Semantically-Guided High-Fidelity Neural Surface Reconstruction Via Geometry Distillation

amrani, abderraouf; laga, hamid

Chardiff-Lp: A Diffusion Model With Character-Level Guidance For License Plate Image Restoration

Na, Kihyun; Park, Gyuhwan; Kim, Injung

Hct-Net: A Hybrid Cnn-Transformer Network For Robust Oracle Bone Script Recognition

Wang, Yibo; Zuo, Yanni; Jiang, Lanxin; Qian, Chong; Ubul, Kurban

Reverse-Calibrated Prototype-Guided Few-Shot Semantic Segmentation Network

Feng, Yi; Chen, Hao

Enhancing Mlops Efficiency Through Distributionally Invariant Models

Gulati, Aman; Das, Sambit; Dewani, Sanyog; Aggarwal, Purav

A Trainable Connected Filter Preprocessing Layer Based On Component Trees

Luz Alves, Wonder; Santos, Lucas; Hashimoto, Ronaldo; Passat, Nicolas; Souza, Anderson; Silva, Dennis; Kenmochi, Yukiko

Hac: Parameter-Efficient Hyperbolic Adaptation Of Clip For Zero-Shot Vqa

Dibitonto, Francesco; Beyan, Cigdem; Murino, Vittorio

Comparison Of Real-Time Multi Object Tracking With Limited Hardware Resources

Bernhart, Costin; Strohmayer, Julian; Kampel, Martin; Peer, Marco; Kleber, Florian

Token Reduction In Vision Transformers Via Discrete Wavelet Decomposition

Buratti, Christopher; Marchetti, Michele; Parlapiano, Federica; Traini, Davide; Ursino, Domenico; Virgili, Luca

An End-To-End Framework For Centimetric 3D Change Detection On Multi-Temporal High-Resolution Railway Mls

TIFOURA, Sid Ali; ABABSA, Fakhreddine; REBILLAT, Marc; hascoet, nicolas; elmeouche, rani; Viguier, Flavien; Salavati, Bahar

Three-Step Hierarchical Transformer For Multi-Pedestrian Trajectory Prediction

Delécluse, Raphaël; Wannous, Hazem; Grisoni, Laurent; Guimas, Laurent

Rethinking Hierarchical Supervision: Revisiting Simplicity In The Era Of Strong Visual Backbones

Thelen, Philipp; Wolf, Stefan; Beyerer, Jürgen

Adapting Temporal Tensor Decomposition For Spatiotemporal Pattern Extraction In Functional Neuroimaging

Sebia, Hana; Guyet, Thomas; Berry, Hugues; Vidal, Benjamin

Stay On Topic: Reducing Hallucinations In Large Language Models With Lda

Chikhaoui, Belkacem

Mmaf: Multimodal Attention Fusion For Molecular Toxicity Prediction

Rehman, Faiz Ur; Rahman, Muhammad Rameez Ur; Vascon, Sebastiano; Pelillo, Marcello

Multimodal Feature Fusion With Illumination Adaptation For Robust Household Waste Detection

Hu, Ziliang; Wu, Xiguang; Zhou, Jiuren; Liu, Yan; Han, Genquan

Rotation-Free Online Handwritten Character Recognition Using Linear Recurrent Units

Yang, Danyu

Data Scaling Laws For Block-Sparse Training

liu, zeyu; zhang, zhenfeng; zhang, yunquan; cheng, daning

Semi-Supervised Domain Adaptation With Entropy-Guided Curriculum And Contrastive Learning

Hwang, Sunhyeok; Kim, Seoung Bum

Consplat: 3D Segmentation From Dual Consistency Via 2D-3D Gradient And 3D-2D Projection

Lyu, Hongchang; Yang, Minghao; Pan, Hang; Liu, Chang; Jiao, Yingjie; Chen, Jinlong; Zhao, Yongjia; Zhan, Yongsong

Savaf: Sparse Audio-Visual Rendering With Multihead Acoustic Field Attention Network

Hasssan, Ahmed; Meng, Jian; Park, Sungjin; Seo, Jae-sun

Fieldworkarena: Agentic Ai Benchmark For Real Field Work Tasks

Takahashi, Jun; Moteki, Atsunori; Uchida, Akiyoshi; Masui, Shoichi; Yang, Fan; Uchino, Kanji; Song, Yueqi; Bisk, Yonatan; Neubig, Graham; Kusajima, Ikuo; Watanabe, Yasuto; Ishida, Hiroyuki; Nakagawa, Koki; Jiang, Shan

Dynamic Context Adapters: Efficiently Infusing History Into Vision-And-Language Models

Song, Yuhang; Lin, Bor-Jiun; Liu, Jiaxu; Chiu, Te-Chuan; Nguyen, Anh; Lee, Chun-Yi

A Novel Prototype-Based Neural Patch Network For Explainable Tumour Classification Under Noisy Labels

Sarpong, Kwabena; Awrangjeb, Mohammad ; Islam, Md. Saiful

Smt-Net: Terrain-Guided Hybrid Neural Network For Meteorological Data Super-Resolution Reconstruction

Pan, Zhigeng; Zhang, Lifeng; Lin, Xianxuan; Wu, Xi; Meng, Fan; Wu, Timing

Cafe-Gs: Compactness-Aware Frequency-Guided Densification For 3D Gaussian Splatting

HUAR, Léo-Paul; Sandri, Gustavo; Sabater, Neus; Guillemot, Christine; Hellier, Pierre

Sharc: Reference Point Driven Spherical Harmonic Representation For Complex Shapes

Sapoutzoglou , Panagiotis; Terzakis, George; Pateraki, Maria

A Modular Deep Learning Framework For Breast Tumor Detection From Microwave Imaging Data

Tchatchoua, Philip; Trin, Ulysse

Robust Explanations Through Uncertainty Decomposition: A Path To Trustworthier Ai

Zhu, Chenrui; Bounia, Louenas; Nguyen, Vu‑Linh; Destercke, Sébastien; Hoarau, Arthur

Elevation-Separated Crf Post-Processing Of Remote Sensing Imagery For Self-Supervised Image Segmentation

Weindel, Joshua; Qiu, Kevin; Bulatov, Dimitri

Implicit-Explicit Segmentation Synergy: A Dual-Guided Fusion Network For Joint Lesion Localization And Disease Classification

Li, Jing; Wu, Yixuan; Zheng, Xiaorou; Dong, Shoubin

Benchmarking Transformers On Spatio-Temporal River Water Temperature Modeling

Jia, Linlin; Fankhauser, Benjamin; Bigler, Vidushi; Riesen, Kaspar

Dentab: A Dataset For Table Recognition And Visual Qa On Real-World Dental Estimates

Hamdi, Laziz; Paquet, Thierry; Tamasna, Amine

As-Ects: Adaptive Shapelet Learning For Early Classification Of Streaming Time Series

Li, Wei; Meng, Xiaofeng

Stegano-Obf: Privacy-Preserving Obfuscation For Action Recognition Datasets Via Semantic Embedding

Nakabayashi, Takuya; Babazaki, Yasunori; Shibata, Takashi; Takahashi, Toru

Fine-Grained Alignment In Vision-And-Language Navigation Through Bayesian Optimization

Song, Yuhang; Gianni, Mario; Yang, Chenguang; Lin, Kunyang ; Chiu, Te-Chuan ; Nguyen, Anh ; Lee, Chun-Yi

What Matters In Virtual Try-Off? Dual-Unet Diffusion Models For Garment Reconstruction

Truong, Phat; Madadi, Meysam; Escalera, Sergio

Rethinking The Pointer Loss In Table Structure Recognition: Geometry-Aware Pointer Loss For Spatial Locality

Choi, Hong-Jun; Lee, Jongho; Kim, Jaeyoung

G-Drift Mia: Membership Inference Via Gradient-Induced Feature Drift In Llms

Kumar, Ravi; Grover, Utkarsh; Lin, Xiaomin; Polyzou, Agoritsa

Multimodal Contrastive Enhancement Network For Cross-Ethnic Analysis Of Degenerative Brain Regions In Alzheimer'S Disease

Zhu, Haoran; Yu, Tong; Hua, Zhen; Ge, Ling; Wang, Jianjia

Time-Domain Quantum Diffusion Graph Networks For Fmri In Alzheimer'S Disease Diagnosis

Zhu, Haoran; Yu, Tong; Wang, Chaoqun; Wang, Jianjia

Litefusion-Detr: Lightweight Dual-Branch Detr For Efficient Multi-Modal Uav Detection

Ren, Jinshuai; Zhang, Zongyu; Shi, Zhiguo; Zhu, Huijie; Wang, Yong; Wang, Wei; Qian, Yekui

Interactive Gadolinium-Free Mri Synthesis: A Transformer With Localization Prompts

Su, Changhui

Anatomical Codebook: Learning Volumetric Context For 2D Medical Image Segmentation

lee, hyunji; Lee, Yu Rim; Park, Soo Young; Tak, Won Young; Jung, Soon Ki

Multi-Camera Multi-Object Tracking Based On Epipolar Distance And Appearance Similarity

Oka, Masamune; Tanaka, Masayuki; Shibata, Takashi; Okutomi, Masatoshi

A Baseline Study And Benchmark For Few-Shot Open-Set Action Recognition With Feature Residual Discrimination

Berti, Stefano; Paquale, Giulia; Natale, Lorenzo

Difficulty-Aware Interleaved Distillation For Robust Cross-Surface Writer Identification

Priya, Kumari ; Adak, Chandranath; Dey, Aritra; Chattopadhyay, Soumi; Chanda, Sukalpa

Explainability-Guided Deepfake Detection For High-Fidelity Facial Edits

Das, Bibek; Chattopadhyay, Soumi; Adak, Chandranath; Pandey, Astitva; Parihar, Ashutosh ; Akhtar, Zahid; Dutta, Soumya; Hadid, Abdenour

Diffusion-Latent Invisible Watermarking For Proactive Deepfake Provenance Verification

Das, Bibek; Deo, Anurag; Adak, Chandranath; Chattopadhyay, Soumi; Akhtar, Zahid; Dutta, Soumya; Hadid, Abdenour

Tf-Dc: A Time–Frequency Deep Classification Framework For Rf-Based Uav Identification

chunxu, luo; yuntian, hu; zhiyan, dong; lihua, zhang

How To Evaluate And Refine Your Cam

Domeniconi, Luca; Stramiglio, Alessandra; Lombardi, Michele; Salti, Samuele

Modern Summarization Methods For Diplomatic Documents: Current State And Limitations

Streilein, Merlin; Steiner, Tobias; Riesen, Kaspar; Fischer, Andreas

Rs-Ovc: Open-Vocabulary Counting For Remote-Sensing Data

Shor, Tamir; Leifman, George; Beryozkin, Genady

A Multi-Modal Blip-2 Approach For Video Captioning

Brimont, Antoine; Zaharia, Titus; Tapu, Ruxandra

Improving Proactive Risk-Awareness Of Autonomous Driving Via Trajectory Monitoring

Zhao, Xue; Li, Xianfei; Peng, Pai; Ye, Nanyang

Jailbreaking Llms Without Gradients Or Priors: Effective And Transferable Attacks

Nurlanov, Zhakshylyk; Schmidt, Frank R.; Bernard, Florian

Prism: A Unified Framework For Photorealistic Reconstruction And Intrinsic Scene Modeling

Dirik, Alara; Wang, Tuanfeng; Ceylan, Duygu; Zafeiriou, Stefanos; Frühstück, Anna

Rq-Pad: Reconstruction Quality For Robust Face Presentation Attack Detection

Bouzid, Hamza; Lézoray, Olivier; Rosenberger, Christophe

Nearest-Neighbor Density Estimation For Dependency Suppression

Anderson, Kathleen; Martinetz, Thomas

Forging The Unknown: Open-Set Deepfake Attribution Via Adaptive Fingerprint Learning

Fang, Yizhi; Han, Boxuan; Wang, Jingwen; Luo, Xiandang; Peng, Siyu; Chen, Xiarun; Wen, Weiping; Cheng, Sai

Tubelite: Lightweight Multi-Actor Spatio-Temporal Action Detection

Soltaninezhad, Ali; Cote, Melissa; Rico Espinosa, Alejandro; Porto Marques, Tunai; Branzan Albu, Alexandra

Fake3Dgs: A Benchmark For 3D Manipulation Detection In Neural Rendering

Di Nucci, Davide; Catalini, Riccardo; Borghi, Guido; Vezzani, Roberto

Quilting-Based Image Pre-Processing For Commercial Ground Hook And Line Fishing Imagery Classification

Rico Espinosa, Alejandro; Cote, Melissa; Soltaninezhad, Ali; Porto Marques, Tunai; Branzan Albu, Alexandra; Diaz Gimeno, Vanesa; Lower, Jacob W.; Prussin, Robin

Revisiting Human-In-The-Loop Object Retrieval With Pre-Trained Vision Transformers

Zaher, Kawtar; Buisson, Olivier; Joly, Alexis

When Not To Answer: Evaluating Prompts On Reasoning Models For Effective Abstention In Unanswerable Math Word Problems

Saadat, Asir; Sogir, Tasmia Binte ;  Chowdhury, Md Taukir Azam; Aziz, Syem

Mamba-Vos: Efficient Video Object Segmentation With Selective State Space Models

Jang, Cheolhun; Kim, Wontae; Ji, Daehyun; Cho, Nam Ik

Metapath-Driven Embeddings For Zero-Shot Object State Classification

Gouidis, Filippos; Papoutsakis, Konstantinos; Patkos, Theodore; Argyros, Antonis; Plexousakis, Dimitris

Evostruggle: A Dataset Capturing The Evolution Of Struggle Across Activities And Skill Levels

Feng, Shijia; Wray, Michael; Mayol-Cuevas, Walterio

Eva Optimizer: Escaping Low-Curvature Traps In Deep Learning

Metta, Carlo; Di Cecco, Antonio; Papini, Andrea; Fantozzi, Marco; Galfré, Silvia Giulia; Vegliò, Michelangelo; Bianchi, Luigi Amedeo; Parton, Maurizio; Morandin, Francesco

Dgi: Time Series Anomaly Detection By Injection Of Anomaly Prior

Xiong, Xudong; Zhou, Xiaohui; Wang, Yijie

Few-Shot Adaptive Open-Set Object Detection With Personalized Scene Generation

Nakamura, Yuzuru; Ishii, Yasunori; Yamashita, Takayoshi

Liteaugnet: A Lightweight Semantic-Guided Augmentation Network For Efficient Edge-Level Image Classification

Rahman, Mohammad Shahedur; Bari, Mohammad Tahmid; Adnan, Md. Nasim ; Parvez, Arshad

Emasam: A Computationally Efficient Sharpness-Aware Minimization \\Via Ema-Guided Perturbations

Ratchatorn, Tanapat; Tanaka, Masayuki

Mfanet: A Lightweight Network Combining Cnn And Mamba For Medical Image Segmentation

Zhang, Haozhuo; Zhang, Bob; Zeng, Pinxian

Is Visual Realism Enough? Evaluating Gait Biometric Fidelity In Generative Ai Human Animation

DeAndres-Tame, Ivan; Ye, Chengwei; Tolosana, Ruben; Vera-Rodriguez, Ruben; Yu, Shiqi

Bughunter: An Automated Game Test Framework With Marl-Based Data Collection And Fdm-Based Bug Detection

Kim, Jung In; Lee, Jungmin; Kim, Jaehoon ; Heo, Jongkook; Jeong, Jinyong; Kim, Seoung Bum

Cliptbp: Clip-Pair Based Temporal Boundary Prediction With Boundary-Aware Learning For Moment Retrieval

Kim, Ji-Hyeon; Kim, Ho-Joong; Lee, Seong-Whan

Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding In Gaussian Splatting

Nguyen, Long; Nguyen, Kien; Sridharan, Sridha; Fookes, Clinton; Moghadam, Peyman

What Matters For Grocery Product Retrieval With Open Source Vision Language Models

Maminta, Emmanuel; Atienza, Rowel

Reco-Mil: Rare-Enhanced Contextual Multiple Instance Learning

Zhou, Shicheng; Wang, Zefeng; Yu, Jikai; Wu, Boyuan; Zhu, Jiayun

Nlos-Mt: A Hybrid Mamba And Windowed Attention Transformer For Non-Line-Of-Sight Imaging

Jin, Shaohui; Ye, Xiu; Liu, Mengge; Wang, Huimin; Lu, Yang; Liu, Hao; Xu, Mingliang

Following The Teacher'S Footsteps: Scheduled Checkpoint Distillation For Domain-Specific Llms

Feng, Cheng; Zhong, Chaoliang; Sun, Jun; Oishi, Yusuke

Returnratenet: Neural Network-Based Estimation Of Size-Related Return Rates In Fashion E-Commerce

Szabo, Attila; Nestler, Andrea; Späth, Matthias; Weffer, Rodrigo; Shirvany, Reza

Fusedpt: Multi-Scale And Multi-Projection Model For Learning Depth In 360 Degree

Paula, Matheus; Imamoglu, Nevrez; Caron, Guillaume; André, Antoine

Dotgreedx: Combining Scoring-Based Technique And Greedy Search For Gnn Explainability

Brito Azevedo, Mariana; Brun, Luc; Héroux, Pierre; Lamotte, Jean-Luc

Cross-Modal Learning For Plankton Recognition

Kareinen, Joona; Immonen, Veikka; Eerola, Tuomas; Haraguchi, Lumi; Lensu, Lasse; Kraft, Kaisa; Suikkanen, Sanna; Kälviäinen, Heikki

Risk-Field Constrained Reinforcement Learning For Safe Autonomous Driving

Wang, Xuanqi; Zhang, Zhang

Mmfuser: Multimodal Multi-Layer Feature Fuser For Fine-Grained Vision-Language Understanding

Cao, Yue; Huang, Yong; Zhu, Wei; Liu, Yangzhou; Chen, Zhe; Shi, Guangchen; Fa, Yong; Yang, Yujie; Mei, Song; Lu, Tong

Llm-Guided Exploration For Sample-Efficient Uav Navigation

Xie, Xianan; Li, Junbao; Sheng, Yuanyuan; Liu, Huanyu

Unique Step Refinement For Transformer-Based Generative Models

Grimal, Paul; Le Borgne, Herve; Ferret, Olivier

Selfxtface: Attention Based Feature Pyramid Network In Face Detection

Kasım, Furkan; Kirchdorfer, Carlos; Mohammad, Salman; Günther, Manuel

Dk-Msp: Integrating Domain Knowledge Into Multi-Stage Prompting Engineerinng For Aspect-Level Multimodal Sentiment Analysis

Feng, Haiwei; Zhang, Qi; Yang, Shuo; Li, Yutong; Xie, Ziye; Xiao, Zhiqun

Graphexplainer: Explaining Nodes, Edges And Attributes Of Graph Neural Network Predictions

Segura-Alabart, Natàlia; Serratosa, Francesc; Lemoine, Jean Philippe

Mocodiff: Modality-Aware Conditional Diffusion Model For 3D Brain Tumor Segmentation

Guo, Sijie; Liu, Yandong; Dong, Jing; Yi, Pengfei; Liu, Rui; Wei, Xiaopeng

Llm-Umls-Pico: A Large Language Model-Based Pico Extraction Method With Umls Semantic Validation

Qiao, Chungeng; Zhang, Meiqi; Huang, Hongfa; Yin, Yipeng; Xiao, Wei

Semantically Stable Image Composition Analysis Via Saliency And Gradient Vector Flow Fusion

Dadras, Armin; Sablatnig, Robert ; Proksa, Franziska; Seidl, Markus

Yesnt: Are Diffusion Relighting Models Ready For Capture Stage Compositing? A Hybrid Alternative To Bridge The Gap

Jüttner, Elisabeth; Pfeifer, Janelle; Krath, Leona; Korfhage, Stefan; Dröge, Hannah; Hullin, Matthias; Plack, Markus

Tag-Head: Time-Aligned Graph Head For Plug-And-Play Fine-Grained Action Recognition

Ul Hassan, Imtiaz; Bessis, Nik ; Behera, Ardhendu

Gradient Consistency Focal Dice Loss And Multi-Scale Attention For Accurate Segmentation Of Mortar Joints In Stone Masonry

Lucho, Stuardo; Desquesnes, Xavier; Leconge, Remy; Treuillet, Sylvie

There Is  More To Attention: Statistical Filtering Enhances Explanations In Vision Transformers

Ayyar, Meghna P; Benois-Pineau, Jenny; Zemmari, Akka

Unifying Runtime Monitoring Approaches For Safety-Critical Machine Learning: Application To Vision-Based Landing

Dario, Mathieu; Chenevier, Florent; Delmas, Kevin; Guerin, Joris; Guiochet, Jérémie

Towards Label-Free Single-Cell Phenotyping Using Multi-Task Learning

Nazir, Saqib; Behera, Ardhendu

U-Cfr: Uncertainty-Guided Cascade Forward Refinement For Interactive Segmentation

Danquah Darko, Elijah; Xian, Min; Soule, Terence; Yao, Tiankai; William Anderson, Matthew

Lindeps: A Fine-Tuning Free Post-Pruning Method To Remove Layer-Wise Linear Dependencies

Henry, Maxim; Deliège, Adrien; Cioppa, Anthony; Van Droogenbroeck, Marc

Llava-Mr: Large Language-And-Vision Assistant For Video Moment Retrieval

Lu, Weiheng; Yu, An; Li, Jian; Chang, Ming-Ching

Seeing Inside Deep Treatment Effect Models: A Representation-Level Evaluation

Khan, Ahmad Saeed; Schaffernicht, Erik; Stork, Johannes Andreas

Automatic Segmentation For 3D Morphometric Analysis Of The Mouse Brain

Zayim, Beyza

Stylistic-Storm: Self-Supervised Spectral Disentanglement Using Adversarial Learning And Jepa For Weather Analysis

Ouattara, Hamed; Duthon, Pierre ; Salmane, Pascal Houssam ; Bernardin, Frédéric; Aider, Omar Ait

Anomaly Detection By Effectively Leveraging Synthetic Images

Kang, Sungho; Park, Hyunkyu; Lee, Yeonho; Lee, Hanbyul; Jeong, Mijoo; Park, YeongHyeon; Lee, Injae; Yi, Juneho

Machine Unlearning In The Era Of Quantum Machine Learning: An Empirical Study

Crivoi, Carla; Ionescu, Radu Tudor

Person Re-Identification Via Generalized Class Prototypes

Al Muzaddid, Md Ahmed; Beksi, William

Simple Hierarchical Prompting With Induced-Parent Consistency For Hierarchical Image Classification

Barna, Nasid Habib; Dey, Noyon; Bhandarkar, Suchendra M

Fusion2Print: Deep Flash-Non-Flash Fusion For Contactless Fingerprint Matching

Sahoo, Roja; Namboodiri, Anoop

Lightweight Model Augmented By Expert Knowledge In Realistic Clinical Decision-Making On Colorectal Cancer Treatment

D'CRUZ, Célia; Precioso, Frédéric; Bereder, Jean-Marc; Riveill, Michel

Learning Rate Informed Priors For Neural Network Calibration

FALL, MOUHAMADOU MAKHTAR; AINOUZ, SAMIA; Lapray, Pierre Jean; Tarel, Jean-Philippe

Model-Agnostic Style Protection By Disrupting Optimized Style Image

Park, Hyunkyu; Kang, Sungho; Lee, Yeonho; Lee, Injae; Yi, Juneho

Diagnosing Llm Benchmark: A Psychometric Analysis Of Difficulty And Discrimination

Qin, Jiacheng; Zhang, Xu; Feng, Dawei; Ding, Bo; Zhai, Yuanzhao

Neuro-Symbolic Instruction Tuning For Explainable Mahjong Agents Via Two-Stage Dual-Lora

Fang, Zhaohao; Xu, Junhuai; Yu, Jiawei; Li, Hanjie; Chen, Shuotian; Li, Jiyi; Yoshioka, Masaharu

Nestedsleepnet: Physiology-Guided Multi-Scale Learning With Hierarchical Temporal Memory For Eeg Sleep Stage Classification

Rai, Rakesh;  Parui, Sricheta; Singh, Dushyant Kumar; Singh, Rupal Hukampal

Rethinking Open Vocabulary Video Anomaly Detection - Normality Matters

Deng, Yunhui; Wang, Hongxing

Cafi: Copula-Based Adversarial Feature Index For Adversarial Robustness Analysis

Feng, Huaxing; Liu, Lin; Hu, Cong

Bridging The Standalone-Vlm Gap For Chest X-Ray Findings: An Empirical Study On Bit Depth, Projectors, And Training Recipes

Bolkonskiy, Yuri; Bokov, Aleksei

Enhancing Rl Generalizability In Robotics Through Shap Analysis Of Algorithms And Hyperparameters

Kong, Lingxiao; Yang, Cong; Beyan, Oya; Boukhers, Zeyd

Stableskip: Stability-Guided Dynamic Token Skipping For Efficient Large Language Model Inference

Wu, Daokuan

Exploiting Open-Set Noise With Adaptive Entropy Enhancement For Learning With Open-World Noisy Data

Luo, Qian; Geng, Chuanxing

Progressive Multi-Level Distillation For Domain Adaptive Object Detection

Yan, Mengfan; Huang, Maochen; Chen, Wenjie

Two-Stage Vision Transformers And Hard Masking Offer Robust Object Representations

Aniraj, Ananthu; F. Dantas, Cassio; Ienco, Dino; Marcos, Diego

Embedding Arithmetic: A Lightweight, Tuning-Free Framework For Post-Hoc Bias Mitigation In Text-To-Image Models

Thirugnana Sambandham, Venkatesh; Schön, Torsten

Tridar-Net: Tri-Domain Decomposition And Adaptive Routing Network For Low-Light Enhancement

Yu, Hantian

Ray Augmented Supervision For 3D Object Detection

Duong, Huy-Hoang; Allibert, Guillaume; Voicila, Adrian

Hybrid Classical-Quantum Architecture For Vectorised Image Classification Of Hand-Written Sketches

Cordero Carrasco, Yeray; Biswas, Sanket; Vilariño, Fernando; Bilkis, Matias

Himes: Hippocampus-Inspired Memory System For Personalized Ai Assistants

Li, Hailong; Li, Feifei; Que, Wenhui; Fan, Xingyu

Lwd: A Lightweight Decoder Leveraging Gated Attention And Cross-Group Convolution For Medical Image Segmentation

Xi, Runkai; Law, K. L. Eddie

Skinpolyformer: Polygon-Driven Differentiable Segmentation With Mask Supervision For Skin Lesions

Tong, Tong; Huang, Wenhui

Transwavenet: Multi-Scale Transformer-Wavelet Encoding For Efficient Colorectal Polyp Segmentation.

Shakya, Amit; Yadav, Akanksha ; Phutke, Shruti; Kumar, Rupesh; Sharma, Lalit

Cloud-Edge Hybrid Reasoning: Decoupling Symbolic Correction From Large-Scale Generation

WANG, RUI

Plotgraph: Graph-First Screenplay Generation With Structural Consistency

Liu, Wenhui; Guo, Kan; Wei, Jia; Luo, Hong; Lu, Haijun; Shao, Yan; Ren, Jiaqian; Feng, Daquan

Sift-Vton: Geometric Correspondence Supervision On Cross-Attention For Virtual Try-On

Takemoto, Kosuke; Koshinaka, Takafumi

Understanding Human-Centric Dynamics Through Need-Driven Interaction Modeling

Zhai, Zimo; Xu, Manjie; Liang, Wei

Esplora: Enhanced Spatial Precision With Low-Rank Adaption In Text-To-Image Diffusion Models For High-Definition Synthesis

Rigo, Andrea; Stornaiuolo, Luca; Martino, Mauro; Lepri, Bruno; Sebe, Niculae

Dynamic Personality Adaptation In Large Language Models Via State Machines

Pielage, Leon; Hätscher, Ole; Back, Mitja; Marschall, Bernhard; Risse, Benjamin

Loss Landscape Topology Reveals Why Simple Baselines Are Competitive At 3D Point Cloud Segmentation Under Class Imbalance

Savva, Antonis; Kyrkou, Christos; Theocharides, Theocharis

3D Sparse Gan-Based Moe For Object Generation And Completion

Hamdi, Yahia; Andrialovanirina, Nicolas; Mahé, Kélig ; Poisson Caillault, Emilie

Blind Multi-Coil Mri Reconstruction Through Joint Optimization With The Diffusion Model

Zhao, Guangxin; Luo, Xinzhe; Akoda, Mary-Brenda; Sedlacik, Jan; Qin, Chen

Energy-Based Open-Set Active Learning For Object Classification

Lyu, Zongyao; Beksi, William

Diagnosis-Aware Medical Radiology Report Generation With Retrieval-Augmented Multimodal Knowledge Injection

Wang, Borong; Ye, Jian; Zhao, Ze

Cryptoscope: Utilizing Large Language Models For Automated Cryptographic Logic Vulnerability Detection

Li, Zhihao; Ji, Zimo; Zheng, Tao; Ren, Hao; Lan, Xiao

Resolving The Inherent Contextual Insufficiency In Referring Image Segmentation With Global Semantic Priors

Yi, Chong; Chen, Jialei; Ito, Seigo; Murase, Hiroshi; Deguchi, Daisuke

Text Conditioned Implicit Visual Chain-Of-Reasoning For Unsupervised 3D Medical Image Registration

Iqbal, Muhammad Zafar; UlHaq, Anwar ; Grandhi, Srimannarayana

Npcl: Negative-Preserving Contrastive Learning Under Noisy Correspondence

Li, Bing; Xue, Jiaqi; Sun, Hongji

Legendre-Kan : High Accuracy Ka Network Based On Legendre Polynomials

Chen, Wei; Liu, Yanyi; Xia, Qingfeng

Unsolvable Problem Detection And Trustworthy Reasoning In 3D-Llms

Elgin, Michael; Sheshappanavar, Shivanand

Idpad: Implicit And Dynamic Preference Alignment During Decoding

cai, xiangjun

Zayan: Disentangled Contrastive Transformer For Tabular Remote Sensing Data

Habib, Al Zadid Sultan Bin; Tasnim, Tanpia; Islam, Md. Ekramul; Tabasum, Muntasir

Parameter Efficient American Sign Language Recognition Via Mediapipe Landmarks

Varanasi, Abhishek; sinha, manjira; Dasgupta, Tirthankar

Period-Aware And Prior-Constrained Adaptive Orthogonal Model For Eeg Emotion Recognition

Wu, Jianing; Hao, Yanrong; Zhang, Chenchen; Bian, Jing; Wen, Xin; Zhou, Mengni; Cao, Rui

The Detector Teaches Itself: Lightweight Self-Supervised Adaptation For Open-Vocabulary Object Detection

Wan, Yazhe; Oh, Changjae

When To Prune? The Importance Of Timing In Data Efficiency Training

Fukase, Vinicius; Gama, Heitor; Bueno, Bárbara; Libanio, Lucas; Costa, Anna; Jordao, Artur

Geometry-Based Approach To Find The Egg-Shape Parameters

Gabdulkhakova, Aysylu; Kropatsch, Walter G.

Beyond Standard Benchmarks: A Systematic Audit Of Vision-Language Model'S Robustness To Natural Semantic Variation Across Diverse Tasks

Chengyu, Jia; MaungMaung, AprilPyone; H. Nguyen, Huy; Chen, Jinyin; Echizen, Isao

Checkmate: Interpretable And Explainable Rsvqa Is The Endgame

Tosato, Lucrezia;  Tartini-Chappuis, Christel; Montariol, Syrielle; Weissgerber, Flora; Lobry, Sylvain; Tuia, Devis

Ragdnet: A Region-Adjacency Graph For Semantic Segmentation Of Mechanical Drawings Using Graph Neural Networks

MONNIER WEIL, Alexandre; HILI, Nicolas; LEDRU, YVES

Few-Shot Supervised Contrastive Learning For Image/Video Distortion Classification

Fadillah, Riestiya Zain; Amirshahi, Seyed Ali; Pedersen, Marius; Beghdadi, Azeddine

Crashchat: A Multimodal Large Language Model For Multitask Traffic Crash Video Analysis

Liang, Kaidi; Li, Ke; Hu, Xianbiao; Qin, Ruwen

Beyond Texture: Advanced Facial Privacy Protection Via Hierarchical Diffusion Autoencoder

Lu, Ting-Yi; Lin, Che-Tsung; Zach, Christopher; Lai, Shang-Hong

Bi-Mcq: Reformulating Vision–Language Alignment For Negation Understanding

Kim, Tae Hun; Lee, Hyun Gyu

Ic-Eo: Interpretable Code-Based Assistant For Earth Observation

Lahouel, Lamia; Lopata, Laurynas; Gruening, Simon; Meoni, Gabriele; Petit, Gaetan; Lobry, Sylvain

Adgr: Adaptive Density-Guided Graph Re-Ranking For Person Re-Identification

Kashimoto, Yushiro; Yamaguchi, Osamu

Prism: Position-Guided Region-Based Image Separation Into Multi-Layers

Shuai, Pan; Xu, Zhang; Jiayin, Chen; Wei, Zhang

Interpretable Image Recognition With Variable Number Of Prototypes

Benali, Katia; Vieru, Bianca; Ferecatu, Marin; Le Borgne, Hervé

Visibility-Aware Diffusion-Based Face Anonymization For Real-World Deployment

LAHGAZI, Mohamed Jaouad; Tarel, Jean-Philippe

Knowledge-Integrated Reasoning: A Novel Approach For External Knowledge Based Visual Question Answering

Satama, Pyry; Radman, Abduljalil; Laaksonen, Jorma

Dsflm: Dynamic Split Fusion Learning Model For Multimodal Aspect-Based Sentiment Analysis

Luan, Minghua; Lu, Jun; Xu, Xuelin

Rata-Tool: Retrieval-Based Tool Selection With Multimodal Large Language Models

Mattioli, Gabriele; Turri, Evelyn; Sarto, Sara; Baraldi, Lorenzo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita

Gramsr: Visual Feature Conditioning For Diffusion-Based Super-Resolution

D'Oronzio, Fabio; Putamorsi, Federico; Zini, Leonardo; Cornia, Marcella; Baraldi, Lorenzo

Opfsembler: An Optimum-Path Forest-Based Framework For Ensemble Pruning

Jodas, Danilo; Passos, Leandro; Rodrigues, Douglas; Costa, Kelton; Papa, João

Depthpolyp: Pseudo-Depth Guided Lightweight Segmentation For Real-Time Colonoscopy

Wu, Zhuoyu; Ou, Wenhui; Zhang, Lexi; Tan, Pei-Sze; Wu, Dongjun; Zhao, Junhe; Fang, Wenqi; Phan, Raphael C.-W.

Reinforced Multi-Expert Ensemble Strategy For Weakly Supervised Video Anomaly Detection

Yang, Hongyu; Xu, Wanru; Miao, Zhenjiang; Tian, Yi; Guo, Ping; Yao, Ruiying

Imagenet-Lc: A Benchmark For Object-Centric Robustness Under Localized Corruptions

Gupta, Sanchit; Swain, Subrat; Taneja, Mayank; Singh, Muskan; Gupta, Nishtha; Aggarwal, Nikunj; Kumar, Vireshwar

Knowledge Distillation Through Low-Frequency Logits

Kobayashi, Takumi

Pbdn-Net: Probabilistic Boundary Disentanglement Network For Prostate Mri Segmentation

Lei, Xin; Li, Yunhao; Huang, Jiahui; Yan, Pang; Wang, Qiong

Demystifying 3D Spatial Awareness Via Llm  Router

Tao, He; Zhang, Lidong; Chen, Luyuan; Lin, Tesi; Qin, Hao; Zhang, Jinjian; Kong, Ming; Zhu, Qiang; Zhang, Feng

Enhance The After-Discharge Mortality Rate Prediction Via Learning From The Medical Notes

YANG, ZIJIANG

Speaker-Invariant Emotion Representations With Gradient Reversal

Jayathunge, Kavisha; Yang, Xiaosong

Fesa-Clip: Frequency-Enhanced Semantic-Agnostic Decoupling For Generalizable Ai-Generated Image Detection

He, Bo; Yang, Huanglei;  Lian, Zhichao

Mfs-Munet: Multi-Scale Frequency Spatial Mamba U-Net For Medical Image Segmentation

Li, Feng; Sun, Chen; Wang, Bing; Xie, Zongyu

Inherently Interpretable Graph Neural Networks Via B-Cos Alignment

Pandey, Shruti ; Mishra, Subhankar

Plug-In Adapter And Upsampler For Arbitrary-Angle Light Field Reconstruction

Liu, Gaosheng; Hu, Zhuhua; Zhou, Qi

Scalable Two-Sample Real-Time Evaluation Across Modalities For Generative Models

Simmons, Colin; Wang, Haifeng

Channel-Aware Probing For Multi-Channel Imaging

Marikkar, Umar; Husain, Sameed; Awais, Muhammad; Atito, Sara

Tgln-Cascade: A Knowledge Graph Completion Framework Fusing Tanh-Gated Transformer And Cascade Rerankers

程, 果; 朱, 月琪; 孙, 可俽; 张, 永康; 高, 明霞

Fine-Tuning Llms With Extracted Rationales For Attributed Text Generation

Cao, Zelin; Zhao, Boxiang; Wang, Yi; Cheng, Peng; Lin, Bo

Hybridformer: Bridging Convolutional And Transformer Architectures For Enhanced Multi-Scale Visual Recognition

Zeng, Xiangfei; Guo, Qingbei; Duan, Hongbing

Merge-Bench: Resolve Merge Conflicts With Large Language Models

Schesch, Benedikt; Ernst, Michael

A Comparative Study Of Adaptation Strategies For Time Series Foundation Models In Anomaly Detection

Park, Miseon; Yoon, Kijung

Aggregation Of Ensemble Of Classifiers With Fuzzy Learning: Application For Land Cover Classification On Sar Images

Gallet, Matthieu; Atto, Abdourrahmane; Karbou, Fatima; Trouvé, Emmanuel

Towards Personalized Multimodal Efficient Detection Of Human Circadian States

Das, Kapotaksha; Burzo, Mihai; Abouelenien, Mohamed

Topolora-Sam: Topology-Aware Parameter-Efficient Adaptation Of Foundation Segmenters For Thin-Structure And Cross-Domain Binary Semantic Segmentation

Khazem, Salim

Sonar-Fert: An Accurate Detector Based On Rt-Detr For Underwater Sonar Imagery

Sun, Yumeng; Lian, Zhichao

Discriminator-Guided Adaptive Diffusion For Source-Free Test-Time Adaptation Under Image Corruptions

Olivato, Francesco; Beyan, Cigdem; Murino, Vittorio

Bridging The Arithmetic Gap: The Cognitive Complexity Benchmark And Financial-Pot For Robust Financial Reasoning

Zhao, Boxiang; Li, Qince; Wang, Zhonghao; Wang, Yi; Cheng, Peng; Lin, Bo

Degradation-Aware Blur-Segmentation Of Brain Tumor

Wang, Yuchun; Li, Xiaosong; Liang, Gefei; Liu, Yang

Decoding-Time Fusion Of Ocr And Large Language Models For Traditional Chinese Historical Document Recognition

Lin, Zih-Ci; Liao, Wen-Hung

Fpaco: Queue-Free Contrastive Learning With Asymmetric Vlm Distillation For Long-Tailed Medical Recognition

Xiao, Yuxin; Valiyev, Riad; Zhu, Xukun; Meng, Quanlin; Li, Ruirui

Dsi-Yolo: A Physics-Aware Framework For Citrus Detection In Unstructured Orchard Environments

Luo, Zhengjie; Shen, Bo; Gan, Zhangze; Yan, Ruyu; Kong, Leyun; Wu, Qiyu; Deng, Qinrui

Eopd-Sr:Entity-Ontology And Path-Dependency Subgraph Retrieval For Knowledge Graph–Augmented Reasoning

Xue, Jiawen; Tang, Yu; Mao, Yingchi; Wang, Zicheng; Pan, Zhenxiang; Nie, Bingbing; Qi, Rongzhi

Skeletonmamba: A Lightweight Mamba-Based Architecture For Action Recognition

Abdrakhim, Sanzhar; Rossi, Luca

Cbct-To-Ios Mesh Super-Resolution Via Implicit Grid-Enhanced Offset Refinement Network

kim, sujeong; han, jiyong; kim, dahee; yang, su; Yi, Won-Jin

Leveraging Gaze And Set-Of-Mark In Vllms For Human-Object Interaction Anticipation From Egocentric Videos

Materia, Daniele; Ragusa, Francesco; Farinella, Giovanni

Apstraffic: Adaptive Expert Decomposition And Pattern Aggregation For Spatio-Temporal Traffic Forecasting

Yan, Ruyu; Zhang, Jinlai; Luo, Zhengjie; Deng, Qinrui; Wang, Xinghua; Liu, Xiao

Tunable Magmax: Preference-Aware Model Merging For Continual Learning

Hiroshima, Kei; Uchida, Kento; Shirakawa, Shinichi

An Empirical Study Of Self-Supervised Pretraining In X-Ray Security Screening

Akbari, Nilofar; Wang, Yang; Zuo, Xinxin

Controllable Diffusion-Based Data Augmentation For X-Ray Object Detection

Kingi, Jacob; Wang, Yang; Zuo, Xinxin

Grasp: Gradient-Aligned Sequential Parameter Transfer For Memory-Efficient Multi-Source Learning

Wisell, Mary Isabelle; Jacobs, Nicholas; Manandhar, Aayush; Yasaei Sekeh, Salimeh

Efficient Korean Voice-Phishing Detection Using Qlora-Tuned Small Language Models

Lee, Jehyuk; Ku, Junhoe; Park, Eunwoo

Disentangling Cognition And Affect: A Caps-Inspired Multimodal Framework For Interpretable Personality Prediction

Li, Qilin; Wang, Weiqiang; Liu, Xiaoqian; Zhu, Tingshao

Uavdb: Point-Guided Masks For Uav Detection And Segmentation

Chen, Yu-Hsi

Mm-Des: Enhancing Multimodal Clinical Prediction With Joint Contrastive Embeddings And Dynamic Ensembles

Juraev, Firuz; Soubih, Abdenour; ABUHMED, Tamer

Unsupervised Latent Context Representation Of Electroencephalography For Label-Efficient Sleep Apnea Screening

Kang, Yoonkyeong; Park, Chanmi; Kim, Yeonji; Ko, Wonjun

Emoxformer: Human-Cognition-Inspired Multimodal Emotion Recognition From Disjoint Modality Datasets

Aisha, Qurat Ul Ain; Choi, Ji-Hoon; Choi, Se-In; Roy, Partha Pratim ; Kim, Byung-Gyu

Fm-Ad: Feature Density Modeling For Unsupervised Anomaly Detection With Continuous Normalizing Flows

Bøss, Jonathan; Wilm, Jakob

Adaptive Confidence-Weighted Expansion For Trustworthy Multi-Omics Multimodal Fusion

Raahemi, Mohammad; Sekhavati, Ali; Maleki, Alireza; Nasiri, Hamid

Multi-Source Pseudo-Label Generation For Weakly Supervised Salient Object Detection

Zhang, Handan; Liu, Tie; Shang, Yuanyuan; Ding, Hui; Shao, Zhuhong

Medroi: Codec-Agnostic Region Of Interest-Centric Compression For Medical Images

jiwon, kim; Jang, Ikbeom

Layer-Wise Lora Fine-Tuning: A Similarity Metric Approach

Ogawa, Keith; Yamamoto, Bruno Lopes; de Alcantara, Lucas Lauton; Pellicer, Lucas; Costa, Rosimeire Pereira; Bollis, Edson; Costa, Anna Helena Reali; Jordão, Artur

Leveraging Rgb Images For Pre-Training Of Event-Based Hand Pose Estimation

Liu, Ruicong; Ohkawa, Takehiko; Tse, Tze Ho Elden; Zhang, Mingfang; Yao, Angela; Sato, Yoichi

What Do Students Learn? A Feature-Level Analysis Of Dark Knowledge

Kang, Seungu; Kim, Songkuk

Corevad: A Contextual Reasoning Framework For Training-Free Video Anomaly Detection

Lim, Hyeongmuk; Hur, Youngbum

Hypdeformnet: Edge-Deployable Deep Architecture With Jacobian-Stable Hyperbolic Deformation And Lipschitz Distillation For Immunotherapy Response Prediction

Rundo, Francesco; Spata, Massimo; Banna, Giuseppe Luigi; Battiato, Sebastiano

Cgff: Video Style Transfer With Confidence-Guided Frame Fusion

Kwon, Jumyeong; Lee, Seungkyu

Pointnet++ Against Point Transformer V3 To 3D Semantic Segmentation Of Sulcus Acusticus

Andrialovanirina, Nicolas; Poisson Caillault, Emilie; Mahé, Kélig

Frets: Frequency-Enhanced Residual Transformer System For Spo2 Estimation

Mukherjee, Surajit; Ahmad, Shahzad; Padhy, Ram Prasad ; Chanda, Sukalpa ; Pal, Umapada

Too Simple Or Too Complex? Using Linguistic Signatures For Ai-Generated Text Detection

Schäfer, Karla; Bassenge, Mareike

Federated Medical Image Classification Under Class And Domain Imbalance Exploiting Synthetic Sample Generation

Pavan, Martina; Caligiuri, Matteo; Barbato, Francesco; Zanuttigh, Pietro

Denoise Then Train: Improving The Performance Of Unsupervised Anomaly Detection Models Under Label-Level Noise

KACAIVA BOMBARDELLI, Rogerio; Rameau, Julien; Al Chanti, Dawood; Solinas, Miguel ; LE PAPE-GARDEUX, Claude ; Dalla Mura, Mauro

From Datagloves To Deep Networks: A Survey Of Sign Language Recognition And Multimodal Approach

Khan, Usman; Ma, Zeyang ; Mansoor, Atif

Mtcurv: Deep Learning For Direct Microtubule Curvature Mapping In Noisy Fluorescence Microscopy Images

Ait Laydi, Achraf; Sid’El Moctar, Sidi Mohamed; El Mourabit, Yousef; Bouvrais, Hélène

Calad: Channel-Aware Contrastive Learning For Multivariate Time Series Anomaly Detection

Hong, Jaehyeop; Hur, Youngbum

Stereographic Projection Voting: An Efficient And Robust Planar Point Set Registration Framework

Wang, Wei; Liu, Yinlong

Crome: Cross-Domain Image Colorization Using An Optimal Mixture Of Heterogeneous Experts

Chang, Zheng; Zhang, Jingzhe; Li, Si

A Misclassification-Aware Framework For Image Classification Evaluation

Kim, Gyewan; Hyun, Yoonsuk

Hoi-R1: Exploring The Potential Of Multimodal Large Language Models For Human-Object Interaction Detection

Chen, Junwen; Xiong, Peilin; Yanai, Keiji

Istructtab: Structured Feature Sequencing For Multimodal Learning Of Image And Tabular Data

Habib, Al Zadid Sultan Bin; Ahamed, Md Younus; Gyawali, Prashnna; Doretto, Gianfranco; Adjeroh, Donald A.

Basil-Rppg: Basis Learning With Predictive Rppg Reconstruction For Heart Rate Estimation From Ultra-Short Facial Videos

Jhao, Jhih-Wei; Chen, Wen-Pin;  Chen, Jun-Ren; Chou,  Yen-Chun; Yang, Shih-Yu; Huang, Pei-Kai; Hsu, Chiou-Ting

Faster Neural Net Inference Via Forests Of Sparse Oblique Decision Trees

Idelbayev, Yerlan; Zharmagambetov, Arman; Gabidolla, Magzhan; Carreira-Perpinan, Miguel

Sign-To-Speech Prosody Transfer Via Sign Reconstruction-Based Gan

Manabe, Toranosuke; Shibata, Yuto; Takamichi, Shinnosuke; Aoki, Yoshimitsu

Qmc-Net: Data-Aware Quantum Representations For Remote Sensing Image Classification

Hossain, Md Aminur; V. Patel, Ayush; Banerjee, Biplab

Rényi Attention Entropy For Patch Pruning

Aizawa, Hiroaki; Igaue, Yuki

Physical-Semantic Co-Learning For Hypersepctral Image Cross-Scene Classification

Pan, Erting; Zhang, Nicai; Liu, Chengyin; Li, Zhang; Liu, Xiaolin; Yu, Qifeng

Pact: Motif Discovery In Time Series Via Adaptive Segmentation, Symbolization, And Suffix Tree

FODIL, Nour El Houda; OLIVIER, Damien; Tranouez, Pierrick

Egohang: Graph-Enhanced Horizon Aware Egocentric Action Anticipation

Vishwakarma, Pawanesh Kumar ; Chowdhury, Ananda S.; SAHU, ABHIMANYU

3D Wavelet-Based Structural Priors For Controlled Diffusion In Whole-Body Low-Dose Pet Denoising

Jing, Peiyuan; Yang, Yue; Cheng, Chun-Wun; Zhang, Zhenxuan; Yang, Liutao; Lima, Thiago; Strobel, Klaus; Leimgruber, Antoine; Aviles-Rivero, Angelica; Yang, Guang; Montoya, Javier

Cross-Lingual Vulnerabilities Of Text-To-Image Models: Evaluating Data Poisoning Attacks Across Ten Languages

Kakebayashi, Ryohei; Mori, Tatsuya

Rolling Feature Pattern Recognition For Adaptive Pairs Trading

Kolapwar, Pranjala

Local Anchor Embedding For Robust Face Recognition Via Progressive Global-Local Fusion

Ud Din, Nizam; Siddiqui, Shahid; Ahmed, Fawad; Aldahlawi, Abdullah

Secmair-Crack: An Industrial Dataset For Fine Crack Segmentation For Preventive Road Maintenance

KAGHAMBEGA, Harouna; LE BERRE, Matthieu; CLERGUE, Manuel; PREVOST, Lionel; SALINESI, Camille

H-Spam: Hierarchical Superpixel Anything Model

Walther, Julien; Giraud, Rémi; Clément, Michaël

Cmffusion: A Layout-Aware Text-To-Image Diffusion Model Via Multi-Object Cross-Attention For Cross-Modal Feature Fusion

Qi, Kai; Zhang, Qifei; Li, Wenjuan; Lu, Minfeng; Sheng, Lei

Delve Into Visual Contrastive Decoding For Hallucination Mitigation Of Large Vision-Language Models

Lee, Yi-Lun; Tsai, Ti-Hsuan; Chiu, Wei-Chen

Silhouette-Based Meta-Training For Geometric Relations

Bodnár, Attila; Gulyás, László; Kárász, Zoltán

Fusion For Vision’S Sake: Learning Controllable Subspace Decompositions For Visible–Infrared Fusion

KAJO , Ibrahim; ruichek, yassine

Urbane: Urban Reasoning And Block Adjustment Via Natural-Language Editing

Waltz, Tanner; Vera, Julio; Aliaga, Daniel

Ps-Tts: Phonetic Synchronization In Text-To-Speech For Achieving Natural Automated Dubbing

hong, changi; song, yoonah; park, hwayoung; bang, chaewoon; ku, dayeon; lee, dohyun; kim, hongkook

Variance-Normalized Latent Distillation (Vld) For Domain-Specific Learned Image Compression Under Jpeg Ai Constraints

EL MENNAOUI, Abdellah; Meehan, Joseph; Hemrit, Ghalia; DUGELAY, Jean-Luc

Probabilistic Ranking For Transfer Learning Bayesian Optimization

Wagner, Philipp; Namagerdi , Hayk; Roth, Marco; Huber, Marco

Approximate Natural Neighbors For Hyperspectral Images

MOULAY OMAR, IMENE; Vozel, Benoit; Le Moan, Steven

Complexity-Guided Ensemble Learning For Imbalanced Data Classification

Moresco, Matheus; Monteiro Jr, Marcos; Sabourin, Robert; Darmiton da Cunha Cavalcanti, George; Souza Britto Jr, Alceu

Chroma: Detecting Ai-Generated Images Through Inter-Channel Color-Space Correlations

Sotelo, Juan; Gardella, Marina; Musé, Pablo

Learning Quantifiable Visual Explanations Without Ground-Truth

Singh, Amritpal; Barsky, Andrey; Souibgui, Mohamed Ali; Valveny, Ernest; Karatzas, Dimosthenis

Mamer-Clip: Micro-Expression Recognition Based On Motion-Aware Contrastive Language-Image Pretraining Model*

Xie, Zhihua; Lv, Qingqing; Tu, Chenyu

Entanglenet: An Entanglement-Based Preprocessing Framework For Robust Defense Against Adversarial Attacks

Al-Fawa'reh, Mohammad; Kelly, Luke; Masek, Martin; Abu-Khalaf, Jumana

A Low-Light Image Enhancement Framework With Adaptability Of Frozen Experts

Zhang, Naixin; Wang, Ziheng; Cao, Rundong; Yu, Jiazhong; Shi, Linsu;  Liu, Ziwei; Cao, Sheng; Bai, Yuxuan; Lin, Tong

Kernel-Prototype Guided Background Adaptation For Class-Incremental Semantic Segmentation

Tran Ngoc, Viet-Anh; Loi, Dinh-Nhat; Dang, Thanh-Hai; Pham, Trang

Scpainter: A Unified Framework For Realistic 3D Asset Insertion And Novel View Synthesis

Dobre, Paul; Cooper, Jackson; Wang, Xin; Yang, Hongzhou

When Smaller Wins: Dual-Stage Distillation And Pareto-Guided Compression Of Liquid Neural Networks For Edge Battery Prognostics

Kannan, Dhivya Dharshini; Li, Wei; Zhang, Wei; Wang, Jianbiao; Seh, Zhi Wei; Ng, Man-Fai

Structure-Aware Phase-Based Dual Alignment For Robust Uav Object Detection

Baek, Minju; Oh, Hyeongseok; Yoon, Jaehong; Lee, Eunseon; Kim, Bogyeong; Paik, Joonki

Joint 2D-3D Segmentation And Association In Street-Level Imaging

Melnikov, Amir; Tanaka, Masayuki; Monno, Yusuke; Okutomi, Masatoshi

Delta-Nerf: Incremental Refinement Of Neural Radiance Fields Through Residual Control And Knowledge Transfer

Ghosh, Kriti; Chakraborty, Devjyoti; Ramaswamy, Lakshmish; Bhandarkar, Suchendra M.; Kim, In Kee; O'Hare, Nancy; Mishra, Deepak

Offline Stochastic Optimization Of Black-Box Objective Functions

dong, juncheng; wu, zihao; Jafarkhani, Hamid; Pezeshki, Ali; Tarokh, Vahid

Eliminating Object Hallucination In Mllms Via Convex Potential Flow Intervention

Shi, Ziqiang; Liu, Rujie; Yu, Shanshan; Shirahata, Koichi

Visual Information Facilitation Scene Text Retrieval

Ibrayim, Mayire ; Luo, Hailong ; Li, Pengyang

Scg-Ssc: Semantic Scene Completion Via Self-And-Cross Gated Fusion Of Depth Maps And Semantic Priors

Feng, Cheng; Zhang, Congxuan; Chen, Zhen; Hu, Weiming; Lu, Ke; Ge, Liyue

Faceml-Moe:Face Multi-Task Learning Via Attribute-Specific Expert Routing

Wang, Lu-Yan; Lai, Shang-Hong

Spot-Face: Forensic Face Identification Using Attention Guided Optimal Transport

PRASAD, RAVI; Singh, Dinesh

A Ct-Based Non-Invasive Diagnostic Model For The Grading Of Esophageal Precancerous Lesions And Early Cancer

Sun, Jingxuan; Li, Yuxuan; Jia, Yibin; Gao, Rui; Qiao, Xu; Wang, Jianbo

Sparse 3D Object Detection Via Local Geometric Refinement And Dynamic Context Perception

Li, Qian; Chen, Bingxi; Wu, Guowei; Li, Xuemeng; Guo, Mi; Jiu, Mingyuan; Li, Shupan; Xu, Mingliang

Ama-Vit: Acoustic-Mechanism-Aware Vision Transformer For Underwater Target Recognition

Cai, Zhangjie; Sun, Ruiting; Liao, Zhenhong; Zhang, Guanwen; Zhou, Wei

Consistent Scene Understanding In 3D Gaussian Splatting Via Multi-Cue Mask Refinement

Park, Hyunjoon; Cho, Donghyeon

Automated Smart Data Curation Via Embedding-Based Scenario Retrieval

Magyar, Dávid; Lányi, Zsombor; Tóth, Tekla

From Image Hashing To Scene Change Detection

Duong, Anh Kiet; Iatrides, Marie-Claire; Gomez-Krämer, Petra; Carozza, Jean-Michel

Feature-Level Fusion Of Source, System, And Fractal Features For Classification Of Infant Cries

Chaudhari, Hiya; Rana, Satyam; Patil, Hemant

Learning And Recognizing Latent Innovation Maturity Indicator Patterns In Texts

Caillard, Mélusine; Lejeune, Gaël; Fayemi, Pierre-Emmanuel; Aoussat, Améziane

Fundus To Cardiovascular Risk Factors With Anthropometric Guidance

Lee, Hyeonmin; Ko, Seonghyeon; Bum, Junghyun; Le, Duc-Tai; Son, Chang-Hwan; Choo, Hyunseung

Ifagenet: Identity-Aware Face Aging Via Feature Inversion And Age-Conditioned Adaptive Latent Shifts

Pyeon, Su Jang; Kim, Seong-Heon; Nam, Woo-Jeoung

Diffusion-Modeled Reinforcement Learning For Carbon And Risk-Aware Microgrid Optimization

Zhao, Yunyi; Zhang, Wei; Xiang , Cheng; Du, Hongyang; Niyato, Dusit; Gao, Shuhua

Gld: Gabor Convolutional Network For 2D Line Descriptors

Wan, ShiYi; Kato, Zoltan

Trajkd: Distilling Knowledge Via Adaptive Trajectory Curriculum And Dynamic Weighting

Jiu, Mingyuan; Guo, Mi; Ziyi Wu, Ziyi; Li, Jiahao; Li, Qian; Zhao, Hongru; Xu, Mingliang

Signmae: Segmentation-Driven Self-Supervised Learning For Sign Language Recognition

Xie, Kunyuan; Cai, Zhixi; Stefanov, Kalin

Graph Based Learning For Visual Prompt Guided Few Shot Object Part Segmentation

Mohan, Anant; Devarmani, Shashank; Gopalakrishnan, Viswanath

The Pragmatic Persona: Discovering Llm Persona Through Bridging Inference

Ryu, Jongwon; Yang, Jisoo; Ma, Minuk; Pham, Trung X.; Kim, Junyeong

Hgdl: Holistic Graph Distribution Learner For High-Fidelity Small Graph Generation

Wang, Haoyu; Wang, Zheng; Yan, Xinyu; Sun, Meijun

Prism: Color-Stratified Point Cloud Sampling

Lim, Hansol; Im, Minhyeok; Choi, Jongseong

H3D-Marnet: Wavelet-Guided Dual-Path Learning For Metal Artifact Suppression And Ct Modality Transformation For Radiotherapy Workflows

Rehman, Mubashara; Martinel, Niki ; Avanzo, Michele; Spizzo, Riccardo ; Micheloni, Christian

See All, Reach All: Spherical Vision-Based Servoing For Full-Surround Mobile Manipulation

Beaujard, Traian; Crombez, Nathan; Ruichek, Yassine

Pairwise Alignment And Compatibility For Arbitrary Irregular And Eroded Image Fragments

Shahar, Ofir; Elkin, Gur; Ben-Shahar, Ohad

Dynamic Neuro-Symbolic Adapter For Efficient Fine-Grained Visual Recognition

Chen, Guanyu; Liu, Tie; Shang, Yuanyuan; Ding, Hui; Shao, Zhuhong

A Lightweight Model-Based Method For Adversarial Purification In Autonomous Driving Segmentation

KAPSALI, IOULIA; GKILLAS, ALEXANDROS; LALOS, ARIS

Global–Local Feature Decoding With Adapter-Guided Samv2 For Salient Object Detection

Moradi, Morteza; Moradi, Mohammad; Palazzo, Simone; Borji, Ali; Spampinato, Concetto

Spatio-Temporal Pattern Spectra For Analysis Of Satellite Image Time Series

Raimond, Emilio; Merciol, François; Belmouhcine, Abdelbadie; Lefèvre, Sebastien

Semi-Supervised Soft Clustering With Flexible Cardinality

Vallejo-Huanga, Diego; Montenegro, Mateo; Simbaña, Brenda; Ferri, Cesar; Martinez-Plumed, Fernando

A Saliency-Driven Graph-Based Metric For Fmri-Based Visual Brain Decoding Evaluation

Moradi, Mohammad; Moradi, Morteza; Grassia, Marco;  Mangioni ,  Giuseppe

Masked-Controlnet: Counterfactual Mri Generation Of Brain Metastasis Evolution For Shared Decision Making Support

Minami, Masaki; Chen, Jinhui; Ding, Nan

Multi: Disentangling Camera Lens, Sensor, View, And Domain For Novel Image Generation

Godavarthy, Sonali; Neuwirth-Trapp, Matthias; Faasch, Tim-Felix; Bieshaar, Maarten; Möller, Michael; Paudel, Danda

Uniform Llm-Based Framework For Explainable Recommender Systems

LAKTAOUI, Hajar; LECHIAKH, Mohamed ; BASMADJIAN, Robert ; AZIZI, Lamiae

Rsd-Bev: Residual Self-Distillation Framework For Efficient Bev Representation Learning

Park, Sungjin; Song, Jaeha; Hwang, Soonmin

Attribute-Driven Weakly Supervised Text-Based Pedestrian Search

Liu, Naixi; Huang, Yan

Ace-Grasp: Aleatoric Ambiguity Modeling Via Consistency And Exploration For Grasping

Li, Yiming; xie, xianghua

Kadr: Multi-Charge Legal Judgment Prediction Via Knowledge-Augmented Dialectical Reasoning

Hu, LiangGeng; Li, YanLing; Ge, FengPei

Efficient Sample Synthesis And Decoupled Distillation For Black-Box Attack

Shen, Ke; kong, longteng; Zhou, Wanting

Mile: Mixture Of Incremental Lora Experts For Continual Semantic Segmentation Across Domains And Modalities

Muralidhara, Shishir; Stricker, Didier; Schuster, René

Oscar: Optical-Aware Semantic Control For Aleatoric Refinement In Sar-To-Optical Translation

Lee, Hyunseo; Kim, Sang Min; Shin, Ho Kyung; Kim, Taeheon; Nam, Woo-Jeoung

Ca-Unetr: Transformer-Based Cross-Attention Unet For 3D Medical Segmentation

Yadav, Agnesh Chandra; Kolekar, Maheshkumar H.

Hyperun: Controlling Uncertainty In Hyperbolic Space For Machine Unlearning

Jung, Inseo; Seo, Dabin; Baek, Sukyung; Jung, Jaeheun; Lee, Donghun; Kim, Jinkyu

Latent Rigidity Regularization For Conditional Vaes In Anomaly Detection

Åström, Oskar; Sopasakis, Alexandros

From Videos To Conversations: Egocentric Instructions For Task Assistance

Aggarwal, Lavisha; Bahirwani, Vikas; Colaco, Andrea

Self-Adaptive Low-Rank Adaptation For Class-Incremental Learning

Song, Yiming; Duan, Qiqi; Sun, Lijun; Shen, Yang; Zhou, Guochen; Shi, Yuhui

Privacy-Preserving Image Annotation By Large Multimodal Models

Wakai, Yuki; Atarashi, Kyohei; Takeuchi, Koh; Kashima, Hisashi

Does Your Definition Matter? Llms Comparison Between Prompt Sensitivity And Internal Behavior For Social Media Analysis

Azais, Marc-Alexis; Guillaume, Jean-Loup; Coustaty, Mickaël

Eyetheia: A Lightweight And Accessible Eye-Tracking Toolbox

Pather, Stevenson; Martignène, Niels; Bugnet, Arnaud; Boutaleb, Fouad; D'Hondt, Fabien; Santana Maia, Deise

Peak Wave Period And Direction Estimation Using 3D Fft On Monoscopic Videos

Paris, Nicolas; Marchand, Sylvain; Gomez-Krämer, Petra

Cross-Domain Human Action Recognition From Multiview Motion And Textual Descriptions

Porto, Yannick; Martins, Renato; Chalumeau, Thomas; Demonceaux, Cédric

Generalizable Deepfake Detection Via Simplicity-Bias-Aware Clip Adaptation

yahchouchi, charbel; Roggero, Noemi; Saroul, Laurent; Dantcheva, Antitza

Mfnet: A Multimodal Fingerprint–Vein  Recognition Network With Frequency-Domain  Enhancement And Cross-Modal Fusion

Wang, Jiachang; Xian, Tingting; Xu, Haibo; Aysa, Alimjan; Ubul, Kurban

Eg-Spxnet: Edge-Gated Superpixel Graph Neural Networks For Interpretable Retinal Disease Grading

Elsharkawy, Mohamed; Sakib, Sadman; El-melegy, Moumen; Ali, Asem; Mahmoud, Ali; Ghazal, Mohammed ; Khalil, Ashraf ; Wang, Wei; El-Baz, Ayman

Src-Conv: Statistical Recalibration Convolution For Amorphous Fire And Smoke Detection

Nan, Ding; Haozheng, Sun; Wenyu, Luo; Masaki, Minami; Jinhui, Chen

A General Framework For Adapting Foundation Models To Specialized Domains: A Case Study In Sewer Defect Classification

Babé, Aloïs; Cuingnet, Remi; Scuturici, Mihaela; Miguet, Serge

Trtf: A Two-Stage Robust Training Framework For Visual Question Answering

Li, Yu; Xu, Jinan

Scene-Aware Emotion Recognition In Comics With Llms

Mushtaq, Umer; Burie, Jean-Christophe; Doucet, Antoine; Rigaud, Christophe

Lidar-Driven Morphological Feature Spaces For Interactive Scene Analysis

Guiotte, Florent; Lefèvre, Sébastien; Corpetti, Thomas

Multimodal Abstractive Summarization Of Instructional Videos With Vision-Language Models

Nazir, Maham; Aqeel, Muhammad; Zhang, Richong; Setti, Francesco

Improving N1-Sleep Stage Detection Using Constant-Q Transform And Lightweight Cnn/Lstm Model

Poisson Caillault, Emilie; Louali, Hiba; Skamate, Salma; Hébert, Pierre-Alexandre

Gaze-Guided Multimodal Llms For Social Scene Understanding

Nasiriboukani, Shayan; Awais, Muhammad; Atito, Sara

Mmla-Yolo11N: Neck Slimming With Dynamic Upsampling And Lightweight Attention For Steel Surface Defect Detection

梁, 培钧

Multi-View Projection For Unsupervised Domain Adaptation In 3D Semantic Segmentation

Caunes, Andrew; Chateau, Thierry; Fremont, Vincent

Improving Temporal Action Segmentation Via Constraint-Aware Decoding

Ee, Yeo Keat; Debaditya, Roy; Li, Chen; Zhang, Hao; Fernando, Basura

Mc-Depth: Modular And Compute-Efficient Monocular Depth Estimation For Outdoor On-Board Vehicle Perception Systems

IATRIDES, Marie-Claire; Gomez-Krämer, Petra; Ben Ahmed, Olfa; Marchand, Sylvain

Fedopf: A Framework For Federated Learning Based On Optimum-Path Forest

Ribeiro Manesco, João Renato; Jodas, Danilo Samuel; Pontara Costa, Kelton Augusto; Papa, João Paulo

Federated Class-Incremental Object Detection

Pijarowski, Matthias; Rapp, Matthias; Wolpert, Alexander; Heckmann, Martin

Reading In The Dark: Low-Light Scene Text Recognition

Fu, Xuanshuo; Kang, Lei; Valveny, Ernest; Karatzas, Dimosthenis; Vazquez-Corral, Javier

Quantum Hamiltonian Descent For Rigid Image Registration

Voigts, Johannes; Kuete-Meli, Natacha; Lellmann, Jan

Hfvideoswin: High-Frequency Spatio-Temporal Features For More Generalizable Deepfake Video Detection

Atamna, Mehdi; Tkachenko, Iuliia; Miguet, Serge

A Constrained Feature Subset Selection Based On Binary Particle Swarm Optimization

Salmi, Abderezak; Hammouche, Kamal; Macaire, Ludovic

Adapt-Peft: Adaptive Parameter Efficient Fine Tuning For Underwater Image Enhancement

Malik, Sameer; Martinel, Niki

Occface: Unified Occlusion-Aware Facial Landmark Detection With Per-Point Visibility

Xiang, Xinhao; Li, Shin; Dhakad, Saurav; Bancroft, Theo; Zhang , Jiawei; Li, Weiyang

Randomized Algebraic Reconstruction For Modelling Genetic Sequences

Jablonskaitė, Kamilija; Landauskas, Mantas

Uncertainty-Aware Granger Causality From Irregular Time Series

Francis, Deena

Demographic Bias Evaluation In Omnimodal Language Models

Elobaid, Alaa

Teleportation With Null Space Gradient Projection For Optimization Acceleration

wu, zihao; dong, juncheng; aloui, ahmed; tarokh, vahid

Beyond Zoh: Advanced Discretization Strategies For Vision Mamba

Ibrahim, Fady; Wang, Guanghui; Liu, Guangjun

Multimodal Diabetic Retinopathy Classification From Oct Via Supergraph Edge-Type Graph Attention

Sakib, Sadman; Elsharkawy, Mohamed ; El-Melegy, Moumen; Ali, Asem; Mahmoud, Ali; Sewelam, Ashraf; Ghazal, Mohammed; El-Baz, Ayman

Cpa-Gnn: Contextual-Based Pattern-Aware Graph-Neural Network For Text Spotting

Sinha, Anant ; Palaiahnakote, Shivakumara ; Pal , Umapada ; Saraee, Mo

Mstis: Multi-Views Scene Text Image Sequencing To Enhance Text Detection Performance

Das Gupta, Debayan Das ; Roy, Jayasmita; Palaiahnakote, Shivakumara ; Pal, Umapada

Sketch-Clip: Efficient Clip Adaptation For Few-Shot Sketch Classification

Xu, Yunqi; Suen, Ching Yee

Paconet: Deep Data Extraction For Parallel Coordinates

Poonam, Poonam; Kniesel, Hannah; Vázquez, Pere-Pau; Ropinski, Timo

Spiking Transformer Framework For Event-Based Object Detection

Ullah, Wasi; Ambellouis, Sébastien ; Tatkeu, Charles

Sigmoid Supervised Contrastive Learning With Memory Bank For Feature Disentanglement

Wang, Bin; Dornaika, Fadi

Gcd: Geometry–Constrained Contact-Aware Diffusion For Text–Driven 3D Hand–Object Motion Synthesis

ADOSSEHOUN, Kossi Josué; Wannous, Hazem

Spare: A Fast And Accurate Approach Based On Handcrafted Features And Lightweight Fusion For 3D Anomaly Detection

Lhoste, Remi; Delhay, Damien; Baou, Zakaria; Lhoste, Remi

Mmg-Slam: Multimodal Visual Slam With Mambavision Loops And Gaussian Splatting

Bandyopadhyay, Ashok; Gupta, Adarsh; Sur, Arijit; UP, Rajeev

Cutclean: Neural Network Pruning For Privacy-Preserving Inference

Magliolo, Leonardo; Pastore, Vito Paolo; Valenzise, Giuseppe; Tartaglione, Enzo

Wheatformer3D: Segmentation And Phenotyping Of Wheat Heads With Transformers

Singh, Ashutosh; Hoppe, Sarah; Emilie-Budde, Lina; Pircher, Maximilian; Stefan Oehmcke, Stefan

Occ-Fas: A New Benchmark And Feature-Disentangled Mixture-Of-Experts Framework For Occlusion-Aware Face Anti-Spoofing

Chen, Jun-Ren ; Su, Cheng-Hsiang ; Ou, Yi-Chen ; Lin, Yi-Ting ; Chien, Kai-Heng; Huang, Pei-Kai; Hsu, Chiou-Ting

Assessing The Visual Enumeration Abilities Of Specialized Counting Architectures And Vision-Language Models

hou, kuinan; mi, jing; zorzi, marco; ballan, lamberto; testolin, alberto

Sequential Enumeration In Large Language Models

hou, kuinan; zorzi, marco; testolin, alberto

Depth-Guided Semantic Mapping Of 3D Endoscopic Reconstructions

Gyawali, Dipesh; Rogers, Jude; Green, Duncan; Karras, Elena; O'Malley, Quinn; Mundy, Thomas; Conley,  Ashley ; Marin, Valentina Vargas; Wong, James; Fujiwara, Akio; Barbalata, Corina; McCoul, Edward D.; Bidwell, Jonathan

Navclip: Learning-Based Uav Localization With Satellite Image Feature Matching

Lin, Huei-Yung

Recursive Prototyping For Computational Behavior Analysis From Egocentric Videos

Perochon, Sam; Oudre, Laurent

Dat3: Dual-Teacher Topology Adversarial Training For Defending Against Adversarial Attacks

Feng, Huaxing; Li, Yuanbo; Yin, Hefeng; Hu, Cong; Atito Ali Ahmed, Sara; Awais, Muhammad

Ego4Ood: Rethinking Egocentric Video Domain Generalization Via Covariate Shift Scoring

Vaseqi, Zahra; Clark, James

Physically-Guided Retinex Feature Enhancement For Low-Light Object Detection

Cheng, Qiyu; Su, Si; Yu, Qingchun

Sdunet: Shape-Depth Aware Hybrid Unet For Improved Kidney Segmentation In Diffusion-Weighted Mri

Abdelhalim, Ibrahim; Abou El-Ghar, Mohamed ; El-Melegy, Moumen; Ali, Asem; Ghazal, Mohammed; Mahmoud, Ali; Contractor, Sohail; El-Baz, Ayman

Diff-Stygs: 3D Gaussian Splatting Stylization Via Tuning-Free Multi-View Sparse Diffusion

Li, Yize; Lu, Lei; Kong, Zhenglun; Wang, Yanzhi; Zhao, Pu; Lin, Xue

Said: Spatial And Interaction-Aware Directed Heterogeneous Graph Neural Network For Gene Mutation Prediction From Histopathology Whole Slide Images

Wang, Yifei; Shi, Jun; Wu, Shihao; Li, Jiyang; Jiang, Zhiguo; Zheng, Yushan

Compact Recurrent Transformer With Persistent Memory

Mucllari, Edison; Daniels, Zachary; Zhang, David; Ye, Qiang

Zera: Zero-Reindex Multimodal Rag Via Heterogeneous Embedding Alignment For Lightweight Query Encoding

Kim, SungJin; Ahn, Dasom; Kim, HyeRim; Kim, Sangwon ; Kim, Kwang-Ju; Ko, Byoung Chul

Graph Contrastive Learning For Tag-Aware Influence Maximization

Dam, Arpan; Pathak, Sayan; Mitra, Bivas

Plankformer: Robust Plankton Instance Segmentation Via Mae-Pretrained Vision Transformers And Pseudo Community Image Generation

Miyazaki, Masaharu; Otake, Yurie; Ito, Koichi; Makino, Wataru; Urabe, Jotaro; Aoki, Takafumi

Enhancing Interactive Gaze Behavior Recognition Via Co-Training With Temporal Gaze Segmentation

Xu, Tianchen; Liu, Weimin; Jin, Xi; Yang, Yang; Li, Hui

Enabling 8B Bitwise Autoregressive Image Generation On Edge Gpus

Vezzali, Enrico; Bolelli, Federico; Grana, Costantino; Benini, Luca; Li, Yawei

The Good, The Bad, And The Template: Contrastive Anomaly Detection In 3D

Tarvo, Alexander; Chen, Xu; Acton, Colin; Wan, Yusen

Pecker: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning In Diffusion Models

Ma, Zhiyong; Deng, Zhitao; Tang, Huan; Chen, Jialin; Zheng, Zhijun; Li, Zhengping; Chuai, Qingyuan

Paired Uniform Cubic B-Splines Are Strong Approximation To Represent Skeleton Activity

Rosman, Muhammad Amirul Raziq; Malik, Owais Ahmed; Lai, Daphne Teck Ching; Ong, Wee Hong

Hffdet: Real-Time Point Cloud Object Detector Based On Hierarchical Feature Fusion

Li, Yuan; Song, Mengdie; Xie, Qihu; Meng, Yulong; Chen, Song; Kang, Yi

Explicit Analytical Reconstruction And  Global Geometric Constraints For Micron-Level Telecentric 3D Metrology

Liu, Zhenhua; Ye, Yuping; Liang, Jixin; Gu, Feifei; Song, Zhan

Yoga-Matnode: Multi-View Attention Neural Ode For Skeleton-Based Yoga Pose Recognition

Niyas P, Rashi ; Tiwari, Hitika; Shinde, Tushar

A Fully Unsupervised Framework For Object Mask Labeling With The Self-Supervised Vision Transformer

KUMAR, SONAL; Jitendrabhai Kathrotiya , Sanket; Daydar, Akshay; Sur, Arijit ; Dutta Baruah, Rashmi

Ls-Mamba: Gated Spatio-Temporal Modulation And Bidirectional State Space Modeling For Eeg Emotion Recognition

Li, Zitao; Gu, Jiayue; Huang, Ziyi; Xiong, Ze

Prototype-Based Label Propagation For Zero-Shot Histopathology Segmentation With Vision-Language Models

Mu, Bingan; Yi, Yuhao

Federated Deep Learning With Client Communication Graphs For Osteosarcoma Histopathology Image Classification

Hafiz, M.M. Golam; Shahriar, Muhammad Muhtasim; Morol, Md Kishor; Prince, Sadek Al; Simi, Safia Akter; Nandi, Dip; Jubair, Md Abdullah Al

Sedtalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization

Jafari, Farzaneh

Lightweight Gating Mechanism For Rnns With Sech-Based Vector Gates

Fujita, Tomohiro; Kawanishi, Yasutomo

Leveraging Human Feedback For Semantically-Relevant Skill Discovery

Hussonnois, Maxence; Karimpanal, Thommen George; Rana, Santu

Pose-Guided Geometric Refinement For Feed-Forward 3D Gaussian Splatting

Wang, Zihan; Ji, Xu; Zhang, Yejun; Rahtu, Esa; Kannala, Juho

Mus: Multilingual Synergy With Shared Representations For Visual Speech Recognition

Fan, Yuheng; Yang, Shuang; Shan, Shiguang; Chen, Xilin

Scale: Semantic- And Confidence-Aware Conditional Variational Autoencoder For Zero-Shot Skeleton-Based Action Recognition

Oraki, Soroush; Ding, Feng; Liang, Jie

Directional Selective Filters For Guiding Spiking Neural Networks In Event-Based Optical Flow Estimation

Benjelloun, Doha; Roussel, David; Bonardi, Fabien; Bouchafa, Samia

Frequency-Aware Multi-Scale Convolution–Transformer Network For Single-Image Dehazing

Koyyada,  Dinesh; Sahoo, Sujit

Extracting Insights From Structured Data Using Hierarchical Clustering Of Itemsets And Llm Based Summarization

Satija, Sanchit; Rawal, Dhar

Gradient Guided Lora For Stable Fine-Tuning Of Llms

Ma, Yuan; Yang, Peipei; fang, hongjian; Zhang, Xu-Yao

Cacmam: Content-Aware Contrastive State Space Model For Unpaired Image Dehazing

Chen, Tong; Li, Jia; Chen, Yunzhi; Huang, Hongyang; Yang, Fengyu; Chen, Ying

Fedadas: Communication-Efficient Federated Distillation For On-Device Driver Yawn Recognition In Vehicular Networks

Mujtaba, Ahmed; Radchenko, Gleb; Masana, Marc; Prodan, Radu

Task-Aware Feature Modulation In Heterogeneous Multitask Learning For Fundus Landmark Extraction

Ko, Seonghyeon; Bum, Junghyun; Le, Duc-Tai; Son, Chang-Hwan; Choo, Hyunseung

Serc: Ldpc-Inspired Semantic Error Correction For Retrieval-Augmented Generation

Kim, Gyumin; Park, Juhwan; Kim, Jaeha; Han, Seunggyun; Son, Kyungrak; Jang, Ikbeom

Cad-Gan+: Classifier-Filtered Synthetic Cmri Generation Towards Robust Detection Of Cad

BASAK, SHUBHAM; HUSSAIN, NUSHRAT; BHATTACHARYA, UJJWAL

Sam2 R-Cnn: Transferring Sam 2 Knowledge For Data Efficient Instance Segmentation

Gharbage, Mehdi; Chateau, Thierry ; Teulière, Céline ; Bouges, Pierre

Sync-Flow: Synchronization-Aware One-Step Generative Model For Audio-Visual Speech Enhancement

Liu, Yichen; Wang, Weiqiang

Spnc-Yolo: An Architecture-Optimized Framework For Real-Time Small Object Detection In Uav Imagery

Li, Feng; Zhang, Yuhang

Cvglobal And Zesco: Geographically Balanced Cross-View Zero-Shot Orientation Estimation

Russo, Leonardo; Marcos, Diego; Fraga Dantas, Cassio; Ienco, Dino

Edge-Guided Feature Enhancement For Self-Supervised Image Deblurring

Li, Jia; Wang, Bo; Chen, Tong; Yang, FengYu; Ma, Ying; Chen, Ying

Comparative Evaluation Of Deep Learning Architectures And Training Strategies For Diabetic Retinopathy Classification

BenHabirech, Mohamed; Belhadj, Mourad; Tamzalit, Dalila; Aiadi, Oussama

Complexity-Efficient Deep Learning For Breast Cancer Detection Using Bi-Rads Descriptors

Ben-Artzi, Gil

Llm-Empowered Dual Exploration-Exploitation Framework For Sequential Recommendation

Zhu, Qianyang; Yang, Bo; Zhou, Zigu; Lu, Yimeng; Liu, Wei; Chen, Chenrui

Fedsfa: Federating Spikes Fired, Approximately

Mateus Martins, Alice Evelyn; Nasrollahi, Kamal

Baysurf-Sanf: Bayesian Surface Reconstruction Using Self-Attention And Normalizing Flows

MA, Xiaoxiao; LAGA, Hamid; SRIVASTAVA, Anuj

Efficient Concept Unlearning In Latent Diffusion Models Via Feature Caching

Sharma, Mridul; Hase, Ajinkya Prakash; Kancharla, Parimala

Probiou+ : Enhanced Probabilistic Iou Loss For Oriented Object Detection

Sakas, Yasmine; Salmane, Pascal Houssam; Rivera, Josué; Danès, Patrick; Saint Pierre, Guillaume

Interaction-Centric Video Scene Graph Generation Via Intended Interaction Targets

Joo, YeEun; Jung, Soon Ki

Lingml: Linguistic-Informed Machine Learning For Enhanced Fake News Detection

Singh, Jasraj; Liu, Fang; Xu, Hong; Ng, Bee Chin; Zhang, Wei

Pafnet: Physics-Aware Free-Water Estimation From Single-Shell Diffusion Mri Via Attention And Anisotropic Advection–Diffusion Networks

Samanta, Soma; Pandey, Deepa; ranjan Jha, Ranjeet; Kumar Pathak, Sudhir; Rathish Kumar, B.V.; Kumar Dwivedi, Durgesh

Closed-Loop Llm Discovery Of Non-Standard Channel Priors In Vision Models

Uzun, Tolgay Atinc; Ignatov, Dmytro; Timofte, Radu

Yolo-Sacam: A Switchable Convolution And Attention-Based Yolo Network For Wind Turbine Blade Defects Detection

Liu, Yi; Liu, Guiping; LIU, NA; Zhang, Yunxin; Yang, Long; Liu, Tan; Liu, Kunjie; Lu, Min; Li, Wenjing

Freq2Clean: Enhancing Calcium Imaging Denoising Via Frequency-Domain Fusion

Morelli, Valerio; Berardini, Daniele; Letti, Giorgio; Curreli, Sebastiano; Mancini, Adriano; Fellin, Tommaso; Murino, Vittorio

Learning Illumination-Invariant Representations For Vehicle Re-Identification

Panda, Arabinda; Dogra, Debi ; Dey, Partha

Cozsr-Vad: Contextual Zero-Shot Reasoning For Video Anomaly Detection

Wani, Mohd; Atito, Sara; Nandam, Srinivasa Rao; Kittler, Josef ; Awais, Muhammad

Cross-Domain Transfer Of Hyperspectral Foundation Models

Theisen, Nick; Neubert, Peer

From Gameplay Traces To Game Mechanics: Causal Induction With Large Language Models

Jiwatode, Mohit; Dockhorn, Alexander; Rosenhahn, Bodo

Attention-Based Radiomics To Predict Histological Grade Of Gliomas

Amato, Domenico; Caruso Bavisotto, Celeste; Calderaro, Salvatore; Lo Bosco, Giosue'; Palazzotto, Francesca Maria; Rizzo, Riccardo; Veiceschi, Pierlorenzo Maria; Vella, Filippo

Ordmix: Ordinal Mixup For Robust Regression Under Domain Shift In Diabetic Retinopathy

Chae, Jiin; Chae, Yeongnam

Radial Distortion Homography Estimation From Affine-Covariant Or Orientation-Covariant Features

Valtonen Örnhag, Marcus; Adalbjörnsson, Stefan

Coinet: Confidence-Aware Involution Network For Joint Contactless Fingerprint Representation

Peddi, Santhoshkumar; Balasubramanian, Arun; Sarma, Monalisa; Samanta, Debasis

Discrete World Models Via Regularization

Bizzaro, Davide; Serafini, Luciano

Spark-Il: Spectral Retrieval-Augmented Rag For Knowledge-Driven Deepfake Detection Via Incremental Learning

Bougueffa Eutamene, Hessen; Sellam, Abdellah Zakaria; Taleb-Ahmed, Abdelmalik ; Hadid, Abdenour

A Step Forward Towards Trustworthy Risk-Aware Facial Retrieval (Ra-Fr)

Siddiqui, Muhammad Emmad; N/A, Muhammad Rafi

Qsfl: A Quasi-Sequential Federated Learning Framework With Performance-Aware Aggregation

Aich, Utathya; Neogi, Soham; Sengupta, Antariksh; Bhanja, Hrishikesh; Gulvanskii, Vyacheslav; Kaplun, Dmitrii; Sarkar, Ram

Connect-Pd: Early Detection Of Parkinson’S Disease Using Temporal Connectivity Graphs From Gait Data

Ujjain, Siddhant; Srivastava, Ekta ; Gandhi, Tapan Kumar; Kumar, Sandeep

Evaluating Age Estimation Robustness Under Realistic Facial Occlusions

Tanveer, Waqar; Franco, Annalisa ; Borghi, Guido; Fernández-Robles, Laura; Fidalgo, Eduardo

Ticr: A New Brazilian-Oriented Benchmark Dataset For Tuberculosis Identification In Chest Radiographs

Pereira, Clayton; Rodrigues, Douglas; Paschoalini, Enzo; Papa, João

Dastatformer: A Hybrid Multibranch Transformer With Statistical Feature Integration For Das-Based Pattern Recognitions

Dione, Michel; Lonlac, Jerry; Louis, Helene; Lecoeuche, Stephane; Fleury, Anthony

Semantic-Guided 3D Gaussian Splatting For Sparse View Reconstruction And Segmentation

Padnekar, S Meena ; Mitra, Kaushik; Das, Sukhendu

Robust 3D Human Pose Estimation From Mmwave Radar Via Spatio-Temporal Representation Learning

Cao, Kai-Ming; Lee, Ming-Han; Hsu, Wei-Che; Wu, Kun-Ru; Lin, Hong-Dun; Xie, Ren-De; Chen, Bo-Yang; Tseng, Yu-Chee

Quartet Of Experts: Multi-Aspect Semantic Guidance For Few-Shot Learning

Ródenas Cumplido, Javier; Aguilar, Eduardo; Radeva, Petia

Negation In Vision-Language Models: A Survey

Pokhrel, Aashish; Ghimire, Bipin; Paudel, Prashanna Mani; Sheshappanavar, Shivanand Venkanna

Srd-Fusion: Self-Supervised Rgb–Depth Fusion For Indoor Scene Categorization

Brito, Alternei; Borges, Paulo; Drews-Jr, Paulo; Oliveira, Felipe

Emmnet: Learning Complementary Temporal And Structural Representations From Eeg And Mri For Early Neurological Disorder Diagnosis

Lee, Injae; Park, Jinhwi; Jo, Hyeonseo; Yoon, Young chul; Paik, Joonki

Spot The Difference: Bilateral Contrastive Representation Learning For Nodule Classification

Haynes, Sophie; Mekala, M S; Elyad, Eyad

Smooth Or Jarring? Evaluating Video Transitions With Transisense And Vt-Bench

Das, Abhirup; Singh, Nishant; Gupta, Anubha

Graph-Based Manifold Learning For Resource Allocation Optimization In Data Center Networks

Kim, Ye Ha; Leung, Oscar; Kang, Lyn

Domain-Agnostic Semantic Segmentation Via Angular Separation And Synthetic Diversity

KAS, Mohamed; Kajo, Ibrahim; Nekamiche, Noha; Ruichek, Yassine

Contextual Scalarisation Thompson Sampling For Multi-Objective Decisions In Public Media

Maetz, Theo; Guillet, Luc; Cavallaro, Andrea

Faster Geodesic Distance Transform On Gpu

Esteban, Baptiste; Carlinet, Edwin

Staer: Temporal Aligned Rehearsal For Continual Spiking Neural Network

Gianferrari, Matteo; Moussadek, Omayma; Salami, Riccardo; Fiorini, Cosimo; Tartarini, Lorenzo; Gandolfi, Daniela; Calderara, Simone

A Pre-Image Representer Theorem In Machine Learning

Honeine, Paul

Histdit: A Structure-Aware Latent Conditional Diffusion Model For High-Fidelity Virtual Staining In Histopathology

Bin Saleem, Raja Aasim; Ahmed, Amr; Behera, Ardhendu; Amin, Hafeez Ullah; Liao, Iman Yi; Khattab, Mahmoud Abdelazim; Jia Wern, Pan; Makmur, Haslina

In-Place Repairing Of Cubic Images

Magillo, Paola; Comic, Lidjia; Seles, Alberto

Agmm-Adp: An Approximated Gaussian Mixture Model Approach Combined With An Adaptive Dynamic Programming For Multi-Threshold Detection

Gabr, Mohamed

Accelerating Vision Foundation Models With Drop-In Depthwise Convolution

Scribano, Carmelo; Mahdi, Mohammad; Prisadnikov, Nedyalko; Fu, Yuqian; Franchini, Giorgia; Paudel, Danda; Bertogna, Marko; Van Gool, Luc

More Than Meets The Ear: Multimodal Driver Alertness Detection Leveraging Llms And Synthetic Speech

Sharak, Salem; Das, Kapotaksha; Burzo, Mihai; Abouelenien, Mohamed

Temporal Modeling With Feature Fusion For Autism Spectrum Disorder Detection From Skeletal Motion

La Quatra, Moreno; Cammarata, Vito; Trovato, Gabriele; Conti, Vincenzo; Salerno, Valerio Mario; Sorce, Salvatore; Cilia, Nicole

Aero-Detr: Coarse-To-Fine Runway Extraction Via Orientation-Normalized Marking Detection

Dhulipudi, Durga Prasad; K S, Rajan; Raja, Sachin

Beyond Visual Appearance: Retrieval-Based Validation Of Object Detectors Via Ood Knowledge Bases

Moustafa, Mohamed Sabry; Bieshaar, Maarten; Albrecht, Andreas; Sick, Bernhard

Assessing Vulnerabilities To Adversarial Perturbations In Eeg-Based Pathology Detection Systems

Masood, Hira; Jahangir, Maham; Athar, Muhammad; Malik, Muhammad Imran; Shafait, Faisal; Khan, Hassan Aqeel

Attention Meets Focus: Enhancing Vision Transformers With Sparse Fractal Focus

Borgi, Mohamed Anouar; Khadhraoui, Taher ; Borji, Rafik ; Nguyen, Thanh Phuong

Combining Facial Videos And Biosignals For Stress Estimation During Driving

Valergaki, Paraskevi; Nikodemou, Vassilis; Oikonomidis, Iason; Argyros, Antonis ; Roussos, Anastasios

Semantic-Guided Reading Order Reconstruction In Historical Armenian Newspapers With Llms

Vidal-Gorène, Chahan; Tomeh, Nadi; Khurshudyan, Victoria

Towards Concept-Based Explanations In Vision–Language Models

Voicu, Laura-Luisa; Negru, Vlad Andrei; Lemnaru, Camelia; Potolea, Rodica

Fdg-Pet Image Diagnosis Using Multi-Angle Projection Analysis With Coupled Weakly And Fully Supervised Frameworks

NEMOTO, MITSUTAKA; NIWA, Yuga; SAHARA, Junnosuke; NAGAOKA, Takashi; MIKAMI, Katsuhiro; KIMURA, Yuichi; TANAKA, Atsuko; KENMOCHI, Yukiko; PASSAT, Nicolas; KAIDA, Hayato; KITAJIMA, Kazuhiro; YAMADA, Takahiro; HANAOKA, Kohei; TUCHITANI, Tatsuya; ISHII, Kazunari

Cezsar: A Contrastive Embedding Method For Zero-Shot Action Recognition

Estevam, Valter; Laroca, Rayson; Pedrini, Hélio; Menotti, David

Rightfeatkd: Selective Feature-Based Knowledge Distillation

Haque, Syed Tousiful ; Yan , Yan ; Hee Hiong Ngu, Anne

Transformer Affinity For Tracking: Efficient Reidentification Of Anchor-Based Detections In Non-Constant Frame Rate Conditions

Belmouhcine, Abdelbadie; Simon, Julien; Lefèvre, Sébastien

Si-Iosr: Hybrid Shape Completion For Intraoral Scan Repair Via Selective Interpolation

Abida, Ons; Rekik, Ahmed; Ben-Hamadou, Achraf; Farhat, Manel

Eegwriter: A Multimodal Deep Learning Framework For Automated Eeg Diagnostic Report Generation

Athar, Muhammad; Masood, Hira; Shafait, Faisal; Khan, Hassan Aqeel

Ab2Nb: A Physics-Guided Framework For Converting Antibodies Into Nanobodies

Wu, Sipeng; Li, Hongzong; Ma, Jiahao; Qian, Jiayu; Liang, Zi; Tang, Shiqin; Hu, Ye-Fan; Huang, Jian-Dong

Reliability-Aware Citizen Science For Environmental Machine Learning

Resende, Hugo; Neto, Eduardo; Cappabianco, Fabio; Fazenda, Álvaro; Faria, Fabio

Neuro-Geometric Zero-Shot Anomaly Detection For Lab Automation

Gandhi, Kashish; Wu, Xiaolong; Liu, Yang; Mertz, Christoph; Xu, Min

Feature-Level Interaction Explanations In Multimodal Transformers

Kim, Yeji; Babiker, Housam; Kim, Mi-Young; Goebel, Randy

Generating Icao-Compliant Synthetic Face Images Via Curriculum-Guided Diffusion

Mudgalgundurao, Raghavendra; Schuch, Patrick; Khurana, Aryan ; Ramachandra, Raghavendra; Raja, Kiran

Hierarchical Binary Space Partitioning Patch Decomposition For Efficient Alzheimer’S Disease Staging From Axial Mri

Haddada, Karim; Zaabi, Marwa; Ibn Khedher, Mohamed; Jemai, Olfa

Deep Spatiotemporal Forecasting From Privacy-Preserving Mobility Traces

Froehlich, Philipp; Chouchane, Amine; Li, Qi; Ben Hamdene, Sarra; Dagtekin, Deniz; Dauth, Benjamin; Koeppl, Heinz

Pap-Nf: Probabilistic Long-Term Time Series Forecasting Via Prefix-As-Prompt Reprogramming And Normalizing Flows

Kim, Minju; Hur, Youngbum

Quantifying Multi-Site Heterogeneity In Tractography-Based Regression Of Srs Cognition In Autism Spectrum Disorder

Khudri, Mohamed; Abdelrahim, Mostafa; Elmelegy, Moumen; Mahmoud, Ali; Ali, Asem; Shalaby, Ahmed; A. Ghazal, Mohammed; Taher, Fatma; Contractor, Sohail; Barnes, Gregory; El-Baz, Ayman

Anomaly Detection Using Density Adaptive Tree Based Clustering

Boral, Subhadip; Ghosal, Sagnik; Ghosh, Ashish

Msf-Yolo: Steel Surface Defect Detection With Multi-Scale Spectral And Spatial Bidirectional Feature Fusion

Huang, Weixing; Ma, Ying; Wang, Bo; Yang, Fengyu; He, Wenting; Chen, Ying

Bidirectional Cross-Modal Attention Gating For Multimodal Estrogen Receptor Status Classification In Breast Cancer

Azam, Mohamed; Mohamed, Walid; Ali, Khadiga; Aboudessouki, Ahmed; Balaha, Hossam Magdy; El-Melegy, Moumen; Ali, Asem; Ghazal, Mohammed; Khalil, Ashraf; Gondim, Dibson; El-Baz, Ayman

Sigref: Verification-Driven Reflection For Faithful Paper-To-Code Development

Zhou, Mingyang; Yao, Quanming; Du, Lun; Wei, Lanning; Zheng, Da

Huemanity: Probing Fine-Grained Visual Perception In Mllms

Grover, Rynaa; Tamarapalli, Jayant Sravan; Yerramilli, Sahiti; Pande, Nilay

A Robust Mlp-Mixer Based Part Assembly Network For Orthognathic Surgery Planning From 3D Point Clouds

Kim, Dahee; Kim, Sujeong; Yi, Won-Jin

Layer-Wise Diagnostic Probing To Enhance Selectivity In Machine Unlearning

Vurity, Anudeep; Yan, Zhisheng; Albanese, Massimiliano

Robust Representation Learning In Masked Autoencoders

Shrivastava, Anika; Rameshan, Renu; Agnihotri, Samar

Evaluating Machine Unlearning In Fingerphoto Presentation Attack Detection

Vurity, Anudeep; Yan, Zhisheng ; Albanese, Massimiliano

Dense Frame Annotations For Low-Resource Isl Fingerspelling Recognition

R, Kirandevraj; Kurmi, Vinod; Namboodiri, Vinay; Jawahar, CV

Toep: Task-Specific Operator Evolution Via Multi-Objective Pareto Optimization For Automatic Workflow Generation

Leng, Chunlin; Kang, Xiaomian; Wang, Haixin; Ren, Shuo; Zhang, Jiajun

Symmamba: A Symmetric Dual-Stream Framework For Multivariate Time Series Forecasting

Yan, Shuangshuang; Zou, Hang; Liu, Qing; Qiu, Xianchao;  Zhang, Dexin; Zhang, Hui

Ican: Information Capacity Approximate Network For Estimating Regression Model Confidence

Zanyovka, Shuki; Regev, Nir; Shabtai, Asaf

Break Out The Silverware: Semantic Understanding Of Stored Household Items

Levi Richter, Michaela; Mirsky, Reuth; Glickman, Oren

H2Gkt: A Hybrid Heterogeneous Graph Framework For Knowledge Tracing

Azizian Foumani, Arash; Qi, Xiaojun

Beam: Exact Benchmarking Of Explainable Ai Attribution Methods

Brandt, Rafaël ; Strisciuglio, Nicola; Raatjes,  Daan; Gaydadjiev, Georgi

Kash: 1-Bit Key-Value Cache Quantizaiton Via Asymmetric Hashing

Zhang, Yifan; Hu, Qinghao; Wei, Zhihui; Cheng, Jian

Beyond Co-Existence: Measuring Attribute Binding Hallucinations In Audio-Language Models

Kim, Mingi; Kwon, Minchol; Ma, Minuk; Pham, Trung X. ; Kim, Junyeong

Multimodal Knowledge Distillation For Acoustic-Aware Object Detection

Hazra, Saheli; Hussain, Nushrat; Das, Sudip; Das, Arindam; Bhattacharya, Ujjwal

East-Spl: Event-Aware Statistical Tiling For Decomposable Soccer Player Localization With An Auxiliary Rejection Network

Chaman Motlagh, Abolfazl; Nilsson, Mikael

Optimizing Three Critical Factors For Practical And Effective Ood Detection Fine-Tuning

Choi, Hyunjun; Chung, JaeHo; Jeong, Hawook

Physics-Guided Prune-Then-Finetune Of Vision Transformers For Wavefield Pattern Analysis

Ye, Jiaxing; Kobayashi, Takumi

Rectifying Self-Supervised Speech Representations For Diffusion-Based Speech Enhancement

Liu, Yichen; Wang, Weiqiang

Optimizing Dimensionality Reduction Hyperparameters For Improved Clustering Performance

Keraghel, Imed; Nadif, Mohamed

Dgssm: Diffusion Guided State-Space Models For Multimodal Salient Object Detection

GHOSH, SUKLAV; Sur, Arijit; Mitra, Pinaki

Task-Free Online Replay With Contrastive Learning And Dynamic Herding

Biswas, Rahul; Mohan, C; Nag, Subhrajit; Dandapat, Sandipan

Video Detox: Purifying Noisy Relevance Signals For Diverse And Long-Form Video Understanding

Han, Sungjin; Ma, Minuk; Pham, Trung Xuan; Kim, Junyeong

When Gnns Meet Moe: From Structural Design To Representation-Level Analysis

Min, Suyeon; Lee, Jaekang; Noh, Dasom; Suh, Minjy; Kwon, Sunyoung

Odornet: An Approach For Smell Digitization And Classification

Sharma, Ajay Kumar; Nigam, Aditya; Bhavsar, Arnav; Shrivastava, Anika; Lakha, Nikita; Kumar, Abhishek; Pandey, Anurag

Learning With Category-Equivariant Representations For Human Activity Recognition

Maruyama, Yoshihiro

Optics-Informed Long Short Term Memory Cells

Avramelou, Loukia; Kirtas, Manos; Passalis, Nikolaos; Pleros, Nikolaos; Tefas, Anastasios

Mitigating Class Imbalance In Neural Network Quantization Via Rank-Based Variance Regularization

Kim, Suk Hyun; Youn, Jongsu; Yoon, Yeonghun; Choi, Jongwon

Sk-Mamba: Synergizing Spectral-Kan Discretization And Multi-Scale Convolution For Robust Wearable Biometrics

Xiao, Yanchao; Wang, Chunxiao; Huang, Yuwen; Yi, Ran; Li, Wenhao; Zheng, Yue; Zhang, Wenzhe; Liu, Ziqiang; Zhou, Zhiwei

Differentially Private Datastore Generation For Retrieval-Augmented Inference

Wael, Abdelrahman; Torki, Marwan

Tprnet: Texture Preserving Network  For Realistic Scenery Image Extrapolation

Lim, Hyoung Jun; Lee, Jooyoung; Choi, Jongwook; Park, Soo Hyun; Choi, Jongwon

Dynamic Augmentation Strategy Selection For Incremental Object Detection

Oh, Yujeong; Kim, Taehoon; Lee, Mingyu; Yun, Kimin; Choi, Jongwon

Blocking Visual Leakage: Visually-Agnostic Text Decomposition For Composed Video Retrieval

Hwang, Jinkwon; Ma, Minuk; Pham, Trung Xuan; Kim, Junyeong

Learning Dynamic Branch Selection Fordomain-Specific Segmentation

SAKKARI, MOHAMED; Iatrides, Marie-Claire ; Gomez, Petra

Fedoap: Cross-Organ Feature Sharing For Rapidly Adaptable Federated Tumor Segmentation

Tashdeed, Ishmam; Rahman, Md. Atiqur; Islam, Sabrina; Hossain, Md. Azam

Zero-Shot Sim2Real Wildfire Frontline Estimation From Uav Imagery Via Vlm-Guided Learning

Ko, Eunseong; Lee, Changmin; Kim, Wonsuk

Rdeltacam: Gradient-Free Causal Inference For Visual Interpretability

Joshi, Shubham; Kumar, Divyanshu; Pant, Millie; Deep, Kusum

Mathematical Foundations Of Monoid-Equivariant Neural Networks

Nasu, Ryo; Maruyama, Yoshihiro

Clid: Controlled Low-Light Image Dataset

Rodrigues, Gabrielly; Santos, Jade; Brito, Alternei; Cavalcanti, João; Pio, José; Oliveira, Felipe

Cross-Domain Synthetic Image Detection Via Few-Shot Adaptation

Chaudhary, Parul; Bhavsar , Arnav

Partial-Correlation Learning For Large Language Models With Skip-Tuning

Lu, Yuheng; Song, Zuhe; Yuan, Caixia; Wang, Xiaojie

Trace: Temporal Radiology With Anatomical Change Explanation For Grounded X-Ray Report Generation

Aranya, OFM Riaz Rahman; Desai, Kevin

Hybrid Guided Variational Autoencoder For Visual Place Recognition

Wang, Ni; You, Zihan; Neftci, Emre ; Schoepe, Thorben

Universal Adversarial Suffixes Using Calibrated Gumbel–Softmax Relaxation

Soor, Sampriti; Ghosh, Suklav; Sur, Arijit

Deep In The Jungle: Towards Automating Chimpanzee Population Estimation

Raynes, Tom; Brookes, Otto; Haucke, Timm; Crunchant, Anne-Sophie; Boesch, Lukas; Kühl, Hjalmar ; Beery, Sara; Mirmehdi, Majid; Burghardt, Tilo

3D Nmibc Segmentation Via Texture-Guided Frequency-Aware Transformer On T2-Weighted Mri

Sharaby, Israa; Alksas, Ahmed ; Ezzat, Osama; A. Elsawy, Amr; T. Abouelkheir, Rasha; Elmahdy, Ahmed; M. Khater, Sherry; Elmelegy, Moumen; Ali, Asem; Mahmoud, Ali; A. Ghazal, Mohammed; Contractor, Sohail; A. Bazeed, Mahmoud; Mosbah, Ahmed; El-Baz, Ayman

C-Feat: A Compact Feature-Centric Network Shattering Training And Inference Latency In Underwater Vision

Silva, Emanuel; Schein, Tatiana; Ramos, José; Oliveira, Felipe; Drews, Paulo

Self-Supervised Learning Of Contextualized Neural Topic Models With Vic Regularization

Hirami, Kengo; Xu, Weiran; Eguchi, Koji

Satmap: Revisiting Satellite Maps As Prior For Online Hd Map Construction

Mazumder, Kanak; Flohr, Fabian

Bikeactions: An Open Platform And Benchmark For Cyclist-Centric Vru Action Recognition

Büttner, Max; Mazumder, Kanak; Koecher, Luca; Finkbeiner, Mario; Niebler, Sebastian; Flohr, Fabian

Cafaclite: Condition Aware Face Anchor Classification For Face Detection With Lightweight Networks

Aggarwal, Yogesh; Guha, Prithwijit

Semantic Prior-Guided Dual Decoder For Long-Tailed Human-Object Interaction Detection

Lee, Jeongae; Nang, Jongho

Empirical Characterization Of Rationale Stability Under Controlled Perturbations For Explainable Pattern Recognition

Sakib, Abu Noman Md; Wang, Zhensen; Roby, Merjulah; Zhang, Zijie

A Collimator-Based Calibration Method For Generic Camera Models

Liang, Shunkun; Sun, Pengju; Guan, Banglei; Liu , Zibin ; Shang, Yang; Li, Zhang; Liu, Xiaolin; Yu, Qifeng

Sensitivity-Integrated Feature Selection (Sifs): Stability-Guaranteed, Model-Agnostic Subset Selection Via Quantile-Delta Sensitivity

Xu, Haiteng

From Short Histories To Long Futures: Horizon-Aware Graph Neural Networks For Long Horizon Forecasting

Liu, Zesheng; Rahnemoonfar, Maryam

Pain In 3D: Controllable Generation Of Synthetic Faces For Automated Pain Assessment

Lin, Xin lei; Mehraban, Soroush; Moturu, Abhishek; Taati, Babak

Optnet: Ordering Point Transformer Network For Post-Disaster 3D Semantic Segmentation

Le, Nhut; Karimi, Ehsan; Rahnemoonfar, Maryam

Llie-Cvt: A Convolutional Vision Transformer For Low Light Image Enhancement

Goswami, Debanjan; Bashyal, Bishal; Chakraborty, Shayok

Data Reduction By Density-Based Instance Selection Combining Clustering And Supervised Classification

Boukir, Samia

On The Invertibility Of Persistence-Based Representations For Imu Gait Signals

Brahimetaj, Redona; Botti, Elena; Jansen, Bart

Mosaic: Orchestrating Collaborative Knowledge Tracing With Hierarchical Semantic Alignment

Li, Xinjin; Wang, Mengyue; Lin, Yuzhen; Feng, Pengbin; Sha, Ziqi; Zhou, Yeyang ; Ma, Yu

Structuring The Unstructured: A Zero-Shot Approach To Video Chaptering And Title Generation

Thakur , Nupur; Paul, Riti; Li, Baoxin

Rapid: Restorative Amortized Protection For Image Diffusion

Jahangir, Maham; Umer, Muhammad Saad; Sajid, Sharjeel; Rehman, Mati Ur; Shafait, Faisal

Improving Model Safety By Targeted Error Correction

Mohammadi-Seif, Abolfazl; Baeza-Yates, Ricardo

Interpretable Hierarchical Local–Global Graph Learning With Recurrent Transformer For Eeg Classification

Kang, Hyunwook; Lee, Young-Eun; Lee, Minji

Hyperbolic Spatio-Temporal Representation Learning For Unsupervised Video Anomaly Detection

Kim, Jinmyeong; Kim, Jieun; Cho, Sung-Bae

Convolutional Neural Networks Using Self-Supervising Learning For Feature Extraction

Cecotti, Hubert; Furtado, Albert

Mambabev: An Bev-Based 3D Detection Model With Mamba2

You, Zihan; Wang, Ni; Wang, Hao; Zhao, Qichao; Wang, Jinxiang

Topgrad-Cf: Gradient-Guided Counterfactual Explanations For Time Series Classification

Hosseinzadeh, Pouya; Li, Peiyu; Filali Boubrahimi, Soukaina; Hamdi, Shah Muhammad

A Multi-Class Defect Detection Unified Model Based On Language-Guided Attention And Confidence-Aware Refinement

Yang, Luyu; Liang, Faqiang; Xie, Shangbin; Nie, Xiangli

Quality-Aware Clinical Ai: Iqa Preprocessing Pipeline For Point Of Care Intraoral Imaging Tool

Yadav, Anshul; Deo, Kunal; Jadhav, Kshitij; Karnani, Achyut; Kulkarni,  Ritwik

Weakly Supervised Spatial Downscaling Via Constrained Inference And Variational Priors

Huang, Dou; Zhang, Haoran; Li, Peiran; Shibasaki, Ryosuke

Bridging Perception And Reasoning: Scene Graph For Explainable Traffic Comprehension

Htun, Swe Nwe Nwe; Dao, Minh-Son; Zettsu, Koji

Minimizing The Effect Of Sleep Deprivation In The Forward-Forward Algorithm

Datta, Joy; Saha, Puja; Rabbi, Rawhatur; Rafin, Nafiz Imtiaz; Shatabda, Swakkhar; Alam, Md. Golam Rabiul; Mourning, Chad

Vits For Action Classification In Videos: An Approach To Risky Tackle Detection In American Football Practice Videos

Zaidi, Syed Ahsan; Hsu, William; Dietrich, Scott

Ccf: A Context Compression Framework For Efficient Long-Sequence Language Modeling

Sun, Bangcheng; Chao, Fei

Xrformer: Multiscale Tokenization For Xrf Representation Learning

DAIMELLAH, Sofiane; Le Hegarat-Mascle, Sylvie; Boust, Clotilde

Dual-Foundation Models For Unsupervised Domain Adaptation

Cheon, Yerin; Balasubramanian, Aruna; Rameau, Francois

Lifganet: Lightweight Frequency- And Gradient-Aware Network For Robust Image Classification

Banerjee, Jotiraditya; Aich, Utathya; Bhattacharya, Ujjwal

Facemixup: Enhancing Facial Expression Recognition Through Mixed Face Regularization

Souza, Mateus; Faria, Fabio; Texeira, Raoni; Segundo, Mauricio

From Post-Hoc To Integrated Calibration: Bilevel Training With Doubly Kernelized Ece

Nunes, João; Coutinho, Felipe; Machado, Inês; Montezuma, Diana; Oliveira, Domingos; Pereira, Tania; Cardoso, Jaime

Puzzlemate: Benchmarking Mllms For Egocentric Puzzle Assistance

Dasgupta, Avijit; Dasgupta, Shayon; Laskar, Zakaria; Jawahar, C. V.; Alahari, Karteek

Splatfill: 3D Scene Inpainting Via Depth-Guided Gaussian Splatting

Dahaghin, Mahtab; Padalkar, Milind Gajanan; Toso, Matteo; Del Bue, Alessio; Murino, Vittorio

Dats-Av: A Dissonance-Aware Two-Stage Framework For Audio–Visual Deepfake Detection

Tonmoy, Rubayet; Rattani, Ajita

Dual-Branch Spectral–Spatial Network With Knowledge- And Data-Driven Band Selection For Uav Hyperspectral Wheat Rust Detection

KIM, SUBIN; Qi, Xiaojun

Smellformer: Stage-Aware Event-Conditioned Transformers For Robust Odor Recognition

Bhansali, Aayush; Niagm, Dr. Aditya

From Cells To Survival: Hierarchical Analysis Of Cell Inter-Relations In Multiplex Microscopy For Lung Cancer Prognosis

Edgren Schüllerqvist, Olle; Baumann, Jens; Lindblad, Joakim; Nordling, Love; Mezheyeuski, Artur; Micke, Patrick; Sladoje, Nataša

Egoafford: Affordance-Aware Zero-Shot Open-Vocabulary Egocentric Action Recognition

Gesualdi, Davide; Santambrogio, Riccardo; Palermo, Francesca; Plizzari, Chiara; Mentasti, Simone; Matteucci, Matteo

Continuous Online Action Detection From Egocentric Videos

Santambrogio, Riccardo; Plizzari, Chiara; Palermo, Francesca; Mentasti, Simone; Matteucci, Matteo

Mamba-Byte-Time: A Token-Free, Byte-Level, Natural-Language-Inspired Approach For Time Series Forecasting

Nguyen, Quang; Sarvi, Majid; Bagloee, Saeed

Cmd-Gcn: Categorical Multi-Domain Graph Convolutional Network For Plasmodium Development Stage Recognition

Tran, Quoc Khanh; Visani, Muriel; Urruty, Thierry; Delandre, Océane; Nguyen, Thi-Oanh

Spatio-Temporal Instability And Epoch-Wise Double Descent

Kobayashi, Keito;  Hiramoto, Reiya; Sekiguchi, Ryoichi; Maeda, Eisaku

Xd : Explainable Drift For Llm'S Robustness In Communication Network Protocols Modelling

Djeachandrane, Abhishek; Lopez, Jorge; Chatzinakis, Charalampos

Versediffuser: Multi-Level Cross-Sentence Structural And Semantic Fusion For Classical Chinese Poetry Generation

Sun, PeiHong; Lu, Jun

Emo-Gnn: Graph Neural Networks For Explainable Monoand Multi-Label Emotion Detection

Fouad, OUESLATI; Bahroun, Sahbi; Zagrouba, Ezzeddine