| 9 |
TDiR: Transformer based Diffusion for Image Restoration Tasks |
Abbas Anwar, Ibrahim Radwan, Ali Arshad Nasir, Mudassir Masood, Saeed Anwar |
| 13 |
Beyond Red and Green: Flashing Traffic Light Recognition in Autonomous Driving |
Shehzad Ali, Md Tanvir Islam, Saeed Anwar, Rafal Scherer, Sambit Bakshi, HAYOUNG OH, Khan Muhammad |
| 14 |
Cover the Motion, Not the Look: Motion Coverage Predicts Correspondence Transfer |
Spencer Low, Matthew Gabbitas, Connor Anderson, Dane Christensen, Evelyn Gaskin, Ryan Farrell |
| 22 |
Self-Aware Object Detection via Degradation Manifolds |
Stefan Becker, Simon Weiss, Wolfgang Hübner, Michael Arens |
| 24 |
Tamaththul3D: High-Fidelity 3D Saudi Sign Language Avatars from Monocular Video |
Eyad Alghamdi, Sattam Altuuaim, Obay Ghulam, Abdulrahman Qutah, Yousef Basoodan |
| 26 |
Risk-Controlled Adaptive Visual Token Compression for Long-Video Multimodal Language Models |
Junliang Jiang, Andy Song, Haytham M. Fayek |
| 29 |
CLIC-3D: A Low-Resolution LiDAR-Camera Benchmark for 3D Detection in Campus and Residential Autonomy |
Xiao Lin, Zhenbo Song, Han Sun, Jianfeng Lu |
| 33 |
Counting Contributions, Not Views: Occlusion-Aware Densification for 3D Gaussian Splatting |
Marcel Rogge, René Schuster, Didier Stricker |
| 35 |
Learned Warp-Equivariant Canonicalization for Multi-Modal Image Matching and Registration |
Anton Frolov, Volker Rodehorst |
| 36 |
Covert Visual Data Exfiltration via Trigger Embeddings in Diffusion Models |
Cheng-Yu Yeo, Yi-Lun Wu, Ling Lo, Hong-Han Shuai |
| 43 |
TRAILNet: Frequency-Aware Transformer for Residual Artifact Identification in Generative Object Removal |
Vishwajeet Shukla, Ajay Bedi |
| 50 |
PG-ST-VMamba: Prior-Guided Spatio-Temporal VMamba for Blind Video Deflickering |
Zekun Hu, Yingyuan Xiao, Qingbo Hao, Jin Yang, WenguangZheng |
| 51 |
SFXGraph: Causal-Compositional Graph Learning for Stylized Sound Effects in Webtoons |
Sakang Hong, Haeyun Lee, Gunha Hong, Jinyoung Jung, Sanga Ahn, Kyungsu Lee |
| 64 |
GeoBlur: Epipolar Geometry Estimation from a Single Motion-Blurred Image |
Bao-Long Tran, Cuong Le, Fredrik Viksten, Per-Erik Forssen |
| 77 |
RefCal-Gate: Confidence-Free Reference Calibration for Edge-Cloud Industrial VLM Inspection |
Chenyu Zhou, Qiliang Jiang |
| 81 |
BiCAA-Net: Bidirectional Cross-Agent Attention Network for Semantic Segmentation |
Wuhan Yan, Jianhao Liu, Zhenglang Jiang, Xianfang wang, Yibo Wang, Sun Tianyi, Jingjing Wang, Zhao li |
| 84 |
The Role of Initialization in 3D Gaussian Splatting |
Ivan Desiatov, Torsten Sattler |
| 88 |
Modality-Observable Factorized Text Alignment for RGB-Skeleton Open-Vocabulary Action Recognition |
Sanghyeon Lee, Jong Taek Lee |
| 92 |
VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges |
Sungjae Choi, Hanna Bae, Sunghyun Baek, Junmo Kim |
| 98 |
Mixture of Multi-Sequence Feature Difference for Contrast-Enhanced MRI Synthesis |
Jonghun Kim, Junmo Kwon, Hyunjin Park |
| 113 |
A Single-Pass Generative Framework for Intrinsic Dense Visual Explanations |
Hongbi Jeong, An Huang, Zuobin Xiong, Junggab Son |
| 116 |
Feature-Mesh: Semantic Mesh Reconstruction for Open-Vocabulary 3D Segmentation within One Minute |
Zhen Ling, Runsong Zhu, Zhixin Duan, Qingzhou Mao |
| 121 |
ScreenLocNet: Display Screen Localization from Gaze Directions |
Yifeng Huang, Huy Anh Nguyen, Prasanth Chandran, Sidney K. DMello, N. Sanjay Rebello, Lester Loschky, Minh Hoai |
| 122 |
Bridging Convolutional Priors and Transformer Expressivity: A Unified Framework for Hyperspectral Image Reconstruction |
Xian-Hua Han |
| 125 |
Towards Initialization-free Calibrated Bundle Adjustment |
Amanda Nilsson, Carl Olsson |
| 132 |
OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute |
Brandon Leblanc, Charalambos Poullis |
| 137 |
Synthesizing Expressive Human-Object Interactions via Test-time Latent Adaptation |
Zijing Wu, Yiping Li, ZhiPeng Yu, Yuzhou Zheng, Ziyazhuo Wang, Binghui Zuo, Yangang Wang |
| 144 |
BOCCHI: A More Realistic and Challenging Benchmark for Local Motion Blur Detection with MSDCT-UNet |
Kuan-Lin Chen, Yuan-Kang Lee, Cheng-Yuan Chiang, Jian-Jiun Ding |
| 154 |
MapPano3D: Map-Guided Large-Scale Urban Reconstruction from Panoramic Videos |
Yi Zhu, Kiyoharu Aizawa, Sebastien Valette, Satoshi Ikehata |
| 157 |
RGBD-to-3D Object Mesh Refinement via Depth Matching and Symmetry Propagation |
Ahyun Seo, Minsu Cho |
| 158 |
Uncertainty Reduction via Boundary-Aware Noise Augmentation in Action Segmentation |
Chi-Hun Sung, Hyemin Ahn |
| 159 |
Credibility-Guided Dual-Level Learning for Incomplete Multi-View Classification |
Wenxin Zhang, Qingbei Guo, Tianhong Zhang |
| 161 |
Gravity-Guided Contact Dynamics Estimation from 3D Human Motions |
Cuong Le, Urs Waldmann, Bastian Wandt, Mårten Wadenbäck |
| 162 |
MACRO: Occlusion-Robust Single-Shot Whole-Body Mesh Recovery via Multi-Anchor Context Refinement |
Yiming Chen, Quanfeng Li, Hongbin Liu, Nan Zhang |
| 164 |
What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining? |
Nikolaos Giakoumoglou, Paschalis Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki |
| 169 |
Uncertainty-Guided Structural Routing and Consensus-Aware Re-Ranking for Open-Vocabulary Camouflaged Object Segmentation |
Jisang Lee, SeoYeon Oh, Cheoneum Park, Haneol Jang |
| 175 |
Reflect for Free: Symmetry for Training-Free Point Cloud 3D Anomaly Detection |
Jun-Ting Wu, Yuan-Chiun Lo, Chao-Yu Chen, Kuan-Hung Chen, Ming-Ching Chang, Jhih-Ciang Wu |
| 181 |
Equine-Inspired Vision System: Partially Self-supervised 360° Stereo Panoramic Depth Estimation |
Han Yu, Jianfeng Li, Shigang Li |
| 182 |
Label by Looking, Steer by Thinking: Visual Concept Labeling and Intervention |
Patrick Ramos, Yuta Nakashima, Noa Garcia |
| 184 |
DeCo: Decoupled Multi-Modal Conditioning for Controllable Low-Light Image Enhancement |
Youngjin Oh, Junhyeong Kwon, Junyoung Park, Nam Ik Cho |
| 190 |
PaveSplat: Resolution-Robust Feed-Forward Gaussian Splatting with Residually Corrected Surface-Aligned Covariances |
Janghun Kim, Hyun-Cheol Kim, Eunbin An, Myeonghun OH, Hyon-Gon Choo |
| 196 |
Orthogonal-DIVERSE: Diversity-Promoting Rashomon Set Exploration via Orthogonal FiLM Modulations |
Takuto Sawamura, Ryoichi Koga, Ryusuke Nakaoka, Tatsuya Yokota, Hidekata Hontani |
| 197 |
RIR-Conditioned FiLM Modulation for Panoramic Depth Estimation |
Mihyun Kim, Hyemin Ahn |
| 200 |
Beyond RGB: Cross-Domain Visual Enhancement via Differentiable Irradiance Modeling |
Ruiqi Mao, tiefeng li |
| 209 |
GeoWorld: Geometry-Aware World Model for Robotic Manipulation |
Jia-Hua Lee, Bo-Yi Mao, YA YU CHIEN, Chun-Yi Lee |
| 215 |
SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence |
Gyeonggwan Lee, Eunsoo Im, Seunghwan Hong, Junghun suh |
| 216 |
On-Device Diffusion Sampling Acceleration with Efficient Brownian Motion Generation |
Yuchen Yang, Guoxiang Liu, Yunsheng Li, Qilong Wu, Cheng Zhiyang |
| 218 |
SoccerNet 2026 Challenges Results |
Anthony Cioppa, Silvio Giancola, Håkan Ardö, Mohamad Dalal, Jan Held, Jérémie Ochin, Jiayuan Rao, Karen Sanchez, Renaud Vandeghen, Artur Xarles, Olivier Barnich, Albert Clapés, Mathieu Delvaux, Sergio Escalera, Bernard Ghanem, Cédric Hons, Antoine Houet, Sotiris Manitsaris, Tom Michel, Pierre Miralles, Thomas B. Moeslund, Mikael Nilsson, Bogdan Stanciulescu, Marc Van Droogenbroeck, Yanfeng Wang, Weidi Xie, Faisal S. Altwaijry, Mohamed Atef Abouelhadid, Semen Budennyy, Vasiliy Chelpanov, Puhua Chen, Yixin Chen, Lechao Cheng, Jianling Chu, Ju-Seong Do, Oleg Durygin, Omar Fetouh, Mirco Fuchs, Youssef Ghallab, Falguni Ghosh, Wonjun Heo, Hu yufeng, Weixuan Huang, Phuong-Linh Huynh-Ha, Matvey Isupov, Yangguang Ji, Siyuan Jiang, Zhenxiang Jiang, Wonyong Jo, Ho-Young Jung, Seongheon Kang, MinJae Kim, Youngseon Kim, Jakub Komosa, Artem Konshin, Trung-Hoang Le, Jongmin Lee, Lingling Li, Litao Li, Vadim Linkov, Fang Liu, Hao-Xuan Ma, Shun Makino, Ismail H. Mathkour, Konstantin Mitin, Mikhail Moiseev, Takumi Nagaya, Yuki Nakamura, Thanh Khoi Nguyen, Hoang-Phuc Nguyen, Trong-Thuan Nguyen, Christian Orduz, Kwanyong Park, Fabian Perez, Parthsarthi Rawat, SuHyun Rim, Hoover Rueda-Chacón, Atom Scott, Minori Sugimura, Yuyang Sun, Shengeng Tang, Minh-Triet Tran, Ikuma Uchida, Juan David Vanegas Echeverria, Thanh-Nhan Vo, Jiangtao Wang, Yaxiong Wang, Xiaogang Wang, Ruifeng Wang, Rio Watanabe, Jiali Wen, Yongliang Wu, Di Yang, Xu Yang, Zhuo Yang, Xinyu Ye, Yibo Yu, Zihan Zhai, Yu Zhang, Zhenyu Zhao, Zhun Zhong, Yixi Zhou, Xingyu Zhu, Wenbo Zhu, Julian Ziegler |
| 219 |
EndoPrior-GS: Dynamic Endoscopic Reconstruction with a Joint Texture Prior |
Jiaqi Huang, Shidong Wang, Tong Xin, Kabita Adhikari |
| 221 |
Local Gaussian Conditioning and Trust-Region Guidance for Flow Matching |
Bertan Turan, Vincent Varga, Julius B. Kirkegaard |
| 228 |
ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model |
Weitai Kang, Weiming Zhuang, Zhizhong Li, Yan Yan, Lingjuan Lyu |
| 240 |
GLoVe: A Global–Local Visual Verification Framework for Medical Hallucination Detection |
Nan Zhou, Ke Zou, Linchao He, Yi Zhang, Hu Chen, Huazhu Fu |
| 242 |
Distance Consistency Regularization towards Diffeomorphic Image Registration |
Zhicheng Wang, Hongkang Song, Liang Xu, Xin Jin, Wenjun Zeng, Chen Xu, Yu Xin, Bo Yang |
| 244 |
ARDOR: Amodal Reachable Disocclusion for Ground-View Active 3D Object Reconstruction |
Janghoon Lee, Minse Ha, Juyeong Lee, Gyuri Nam, Jong Taek Lee |
| 245 |
Efficient Scene-Distribution-Aware Second-Order Optimization for 3D Gaussian Splatting |
HyunSeung Son, Young Sun Choi, Youngsik Yun, Kibeom Hong, Youngjung Uh |
| 246 |
Image-Space Rule Discovery |
Misora Sugiyama, Toya Oyama, Hirokatsu Kataoka |
| 247 |
MeshRefiner: High Resolution Multi-view Normal Maps Enhancement based on Stable Video Diffusion |
Jialiang Liu, Ye Tao, Yahao Shi, Dongqing Zou, Bin Zhou |
| 250 |
QCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Action Recognition |
Nanzhu Chen, Feixiang He, Yunfeng Diao, Duygu Sarikaya, He Wang |
| 251 |
A Benchmark and Robust Pipeline for Stem Reconstruction from Handheld SLAM-LiDAR |
Haitian Wang, Xinyu Wang, Xia Cheng, Fiona Wei, Sheldon Fung |
| 257 |
Quad-tree Packing: CTU-Aligned V-PCC Atlas Generation Scheme for Efficient 3D Gaussian Splatting Reconstruction |
Hyemin Shin, YONG-HWAN KIM |
| 258 |
AnoleVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile Manipulation |
Yusuke Takagi, Motonari Kambara, Daichi Yashima, Koki Seno, Kento Tokura, Komei Sugiura |
| 265 |
AG-JEPA: Anatomy-Guided Joint-Embedding Predictive Architecture for 3D CT Image Classification |
Chathura Wimalasiri, Yuchong Yao, Nandakishor Desai, Marimuthu Palaniswami |
| 266 |
SkyPoseX: Skyline-Aware Cross-View Visual Place Recognition with Panorama-BEV-3D Fusion |
Juyong Jeong, SungRok Kwon, Sangyun Lee, MinCheng Piao, Jong-Il Park |
| 272 |
LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes |
Haozhuo Zhang, Jingkai SUN, Michele Caprio, Angelo Cangelosi, Jian Tang, Shanghang Zhang, Qiang Zhang, Wei Pan |
| 274 |
Discovering Subtype-Specific Cell Nuclei in Malignant Lymphoma via Conformal Prediction |
Wataru Kanegae, Tatsuya Yokota, Noriaki Hashimoto, Ichiro Takeuchi, Hiroaki Miyoshi, Yuki Noto, Ryoichi Koga, Hidekata Hontani |
| 283 |
Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving |
Ahmed Abouelazm, Rupert Polley, Qingyuan Zhang, Yin Wu, Philip Schörner, Carl Esselborn, J. Marius Zöllner |
| 287 |
Foundation-Model-Based Hyperbolic Multi-Scale Representation Learning and Density-Ratio Analysis for Subtype-Specific Nuclei Discovery |
Kazumasa Ohara, Kei Taguchi, Tatsuya Yokota, Noriaki Hashimoto, Ichiro Takeuchi, Hiroaki Miyoshi, Ryoichi Koga, Hidekata Hontani |
| 289 |
Self-Distilled Diffusion for Super-Resolution |
JoonKyu Park, Kyoung Mu Lee |
| 295 |
MEGS: Monocular Event-based Gaussian Splatting with Depth Supervision |
Bowen Chen, Ruoming Shi, Juncheng Jiang, Yuzhi Wang, ZiFan Ni |
| 297 |
DLC: Dynamic Loss Controller for Multi-Objective Image Restoration |
Jaewan Ko, Janghoon Choi |
| 300 |
Spatial Head-guided Contrastive Decoding for Hallucination Mitigation in Large Vision-Language Models |
Wanyu Huang, Tai-Ming Huang, Kailung Hua, Jun-Cheng Chen |
| 301 |
From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification |
Yi-Shan Chu |
| 312 |
ICGS: Illumination Cue-Driven Densification for 3D Gaussian Splatting |
Dongbeen Kim, Moonsoo Jeong, Sungkil Lee |
| 314 |
Decoupled Supervised Contrastive Learning for Federated Learning |
Hyungbin Kim, Incheol Baek, Yon Dohn Chung |
| 318 |
VFI-Gen3D: Volumetric Feature Interaction for 3D CT Pair-Dataset Co-Generation |
Hong-Shuo Hsu, Lu-Yan Wang, Che-Tsung Lin, Tzung-Dau Wang, Shang-Hong Lai |
| 319 |
Industrial Synthetic Segment Pre-training |
Shinichi Mae, Hirokatsu Kataoka, Ryousuke Yamada, Yoshihiro Fukuhara, Risa Shinoda, Christian Rupprecht |
| 320 |
Dominating vs. Dominated: Concept-Level Generative Collapse in Diffusion Models |
Hayeon Jeong, Jong-Seok Lee |
| 322 |
Event-based Scene Synthesis via Inter-Frame Residual Alignment |
Jiyun Kong, Jun-Hyuk Kim, Jong-Seok Lee |
| 323 |
SLIM: Semantic-based Low-bitrate Image Compression for Machines |
Hyeonjin Lee, Jun-Hyuk Kim, Jong-Seok Lee |
| 328 |
VLM-Aware Meta-Optic Front-End Design for Frozen Vision-Language Models |
Chanik Kang, Raphaël Pestourie, Haejun Chung |
| 331 |
DiffMatch: Differential Transformer–Mamba Networks for Dense Image Matching |
Yusen Ai, Shen gang, Lv Xuefei, Chenglong Wu, Yuru Pei |
| 332 |
DuoMamba: A Vision Backbone with Duo Scan and Resolution-Aware Mixer Scheduling |
Gwangsoo Kim, Seungkyu Oh, Dohhoon Kim, Nirmal Adhikari, Bimal Thapa Magar, Suan Lee, Wookey Lee |
| 334 |
One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation |
Sanghyun Jo, Seo Jin Lee, Seohyung Hong, Yoorim Gang, Hyeongsub Kim, Hyungseok Seo, Kyungsu Kim |
| 335 |
DiffGround: Semantic Difference-Guided Zero-Shot Video Question Grounding |
Cheng-Han Lee, Amir Salimi, Hsiang-Wei Huang, Che-Chun Su, Min Sun, Cheng-Hao Kuo |
| 338 |
MDIL-Net: Multi-Domain Inconsistency Localization for AI-Inpainted Image Regions |
Hailin Zhong, Shengxin Zhu |
| 346 |
SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages |
Puja Ahmad Habibi, Faiz Assabil Firdaus, Ashvanth.S, Ekapol Chuangsuwanich, Pume Tuchinda, Peerat Limkonchotiwat |
| 351 |
Geometric SimCity-LM: Designing Urban Layouts in Harmony with Microclimate |
Jaeyeon Kim, Po-Yen Lai, Jian Cheng Wong, Chin Chun Ooi, Yew-Soon Ong, Ivor Tsang |
| 352 |
Self-Calibrated Consistency: 3D-Aware Synthesis001 001 from Pretrained 2D Generators without 3D Data |
Jaeyeon Kim, Ka Chun SHUM, Binh-Son Hua, Duc Thanh Nguyen, Yaxin Shi, Ivor Tsang, Sai-Kit Yeung |
| 355 |
GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration |
Karim SLIMANI, Catherine Achard, Eric Marchand, Brahim TAMADAZTE |
| 358 |
Reading Token Importance from Selective State Propagation for Vision Mamba Pruning |
Dahee Lim, Jihun Park |
| 361 |
Progressive Permutation Alignment with Temperature-Controlled Spectral Sharpening |
Yuta Horioka, Naoya Chiba, Yuki Uranishi |
| 366 |
FreeCOD: Finding Camouflaged Objects without Task-Specific Learning |
Minghao Sun, Qing Zhang, Zeming Liu, Xiaowei Chen |
| 367 |
Cross-Modality Text-Image Interchange: Serverless Federated Learning by Lightweight Diffusion Model |
Huyu Peng, Sheng Wu |
| 372 |
MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection |
Kiet Dang Vu, Cao Le Minh Khoa, Nguyen Viet Tri Pham, An Nguyen Gia, Tam Le Thuc Ho, Duc Dung Nguyen |
| 373 |
SECG: A Dataset and Benchmark for Seamless Egocentric Continuous Gesture Recognition |
Chia-Chen Chiang, HSUAN CHUNG, Kevin Tandian, CHIA-YEN LIN, Charlene Shawn, Tang Chen Chang, Edwin Arkel Rios, Chih-Tsun Huang, Tse-Yu Pan, Min-Chun Hu |
| 379 |
Feature Space Analysis by Guided Diffusion Model |
Kimiaki Shirahama, Kaduki Yamashita, Miki Yanobu, Miho Ohsaki |
| 385 |
Self-Supervised Video Object Segmentation with Distillation Learning of Deformable Attention |
Quang-Trung Truong, Duc Thanh Nguyen, Binh-Son Hua, Sai-Kit Yeung |
| 387 |
Nexus: Structured Synergy for Efficient Text-to-Image Generation using Rectified Flow Model |
Yizhao Wang |
| 389 |
MomentumDiff: Risk-Adaptive Momentum and Tangent-Projected Safety Priors for End-to-End Diffusion Planning |
JinMiao Song, Shu Xu |
| 390 |
BAMC: Barker-Aligned Monte Carlo for Preference-Guided Search |
Sungwon Kim |
| 393 |
FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation |
Yukinori Yamamoto, Kazuya Nishimura, Tsukasa Fukusato, Hirokazu Nosato, Tetsuya Ogata, Hirokatsu Kataoka |
| 394 |
PoseFormerV2++: Dynamic Spectral Attention and Graph-Enhanced Spatial Modeling for 3D Human Pose Estimation |
Jiajie Wen, Mingjia Zhang, Le Zhang, zijian kong, Li Haifeng, Xuejun Yue |
| 396 |
CoRSA: Continuous Rank Selection Algorithm for Truncated SVD for Transformer Compression |
Cheng-yu Sie, Che-Rung Lee |
| 410 |
K-STR-Bench: A Challenge-Aware Benchmark Suite for Korean Scene Text Recognition |
MyoungHun Han, Jin-Hyuk Hong |
| 418 |
Interference-Gated Continual Learning for Deepfake Detection |
Hayoung Park, Jinhee Park, Choongsang Cho, Guisik Kim |
| 421 |
Generating Crease Data: from 3D Model to Origami Art |
Binh Minh Truong, Nguyen Bao Tran, Duc Dung Nguyen |
| 423 |
Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priors |
Jaeha Kim, Kyoung Mu Lee |
| 424 |
Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling |
SeungJu Cha, Ye-Chan Kim, Kwanyoung Lee, Dong-Jin Kim |
| 428 |
MatSense: A Multimodal Dataset and Benchmark for Material Classification |
Suman, Biswajit Bera, Sudhakar Kumawat, Manisha Verma, Hajime Nagahara |
| 437 |
SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection |
Yuting Zhao, Ziyi Zheng, Shuxiao Li |
| 439 |
Neural Collapse-Guided Plasticity Regularization for Prompt-based Few-Shot Class-Incremental Learning |
Geonwoo Im, Sang Min Yoon |
| 441 |
Beyond Single Sentences: Composed Image Retrieval with Long-Form Modification Texts |
Junyeong Jang, Seongwon Lee |
| 444 |
Reading Between the Layers: Residual Stream Norm Trajectories as a Training-Free, Complementary OOD Signal for Vision Transformers |
Minhyeok Lee |
| 446 |
Anatomical Prior-Guided Routing for 3D Lung Tumor Segmentation |
Uihyeon Maeng, Jonghun Kim, Hyunjin Park |
| 449 |
LCM-KD: Teacher-Compatible Channel Merging for Recoverability-Oriented Compression and Distillation |
EunjoungYoo, Eunseo Kim, Jaehyeong Sim |
| 450 |
A Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures |
Wonseok Shin, Songkuk Kim |
| 452 |
SAGA: Stable Acceleration Guidance for Autoregressive Video Generation |
Thanh-Nhan Vo, Trong-Thuan Nguyen, Trung-Hoang Le, Tam V. Nguyen, Minh-Triet Tran |
| 456 |
From Global Alignment to Local Grounding: Zero-Shot Chinese Character Recognition with Radical Verification |
Yu-Heng Shih, Bing-Chen Wu, Tsz-To Wong, Ting-En Yen, Hong-Han Shuai, Bin-Hua Hsieh, ChienAn Chen, Yi-Ren Yeh, Ching-Chun Huang |
| 458 |
The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models |
Moshiur Farazi, Sameera Ramasinghe, Bekir Sait Ciftler, Mahbub Ahmed Turza, Shafin Rahman |
| 459 |
NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields |
Shota Kobayashi, Koki Seno, Daichi Yashima, Komei Sugiura |
| 460 |
Biomarker-Aware Mixture-of-Experts for Device-Invariant Personalized Skin Diagnosis |
Seo-Yeon Choi, Kyungsu Lee |
| 461 |
Weave Mamba Fusion: Global Cross-Scale Interaction for Lightweight Face Detection |
Dohun Kim, Jinmyung Jung |
| 464 |
Back from the Past: Using Past Model States to Remove Watermarks in Federated Learning |
Yana Sakhnovych, Rudolf Mayer |
| 466 |
SAGA: Spatio-Temporal Graph Cut Using Adaptive Spectral Analysis for Unsupervised Temporal Action Localization |
Vipul Baghel, Ravi Hegde |
| 469 |
MicroFaceViM: Efficient Face Recognition via Partial State-Space Duality |
Novendra Setyawan, Mas Nurul Achmadiah, Mao-Hsiu HSU, Chi-Chia Sun, Jun-Wei Hsieh |
| 470 |
Frequency-Decomposed Avatar Representation for Varying Camera Distances |
David Svitov, Pietro Morerio, Lourdes Agapito, Alessio Del Bue |
| 471 |
NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction |
David Svitov, Mahtab Dahaghin, Pietro Morerio, Alessio Del Bue |
| 473 |
UGround: Efficient Ground Filtering of Airborne LiDAR via 2.5D Raster Segmentation |
Bertram David Matabang, Rowel Atienza |
| 477 |
CASSP: Channel Attention with Spatial Structure Preservation through QKV Decomposition |
Guilherme Dias Nunes de Abreu, Nina S. T. Hirata |
| 479 |
Hier-SLAM++: Neuro-Symbolic Semantic SLAM with a Hierarchically Categorical Gaussian Splatting |
Boying Li, Vuong Chi Hao, Peter J. Stuckey, Ian Reid, Hamid Rezatofighi |
| 481 |
Rethinking Skip Connections for Medical Image Segmentation under Domain Shift and Corruptions |
Ju-Hyeon Nam, Dong Hyun Moon, Sang-Chul Lee |
| 483 |
PhysGA: Physics-Guided Garment Dynamics for Topology-Aware Gaussian Avatars |
Yong Deng, Baoxing Li, Xu Zhao |
| 485 |
Group-regularized Adaptive Structured Pruning (GASP) |
Leandro Palma, Kyle Poe, Salma Tarmoun, Lachlan Ewen MacDonald, Benjamin David Haeffele, Rene Vidal |
| 491 |
Subtoken Vision Transformer for Fine-grained Recognition |
Jie Zhu, Ivy Zhang, Minchul Kim, Xiaoming Liu |
| 492 |
MaRO-GS: Mask-Robust Object-Centric Gaussian Splatting from Inconsistent Multi-view Masks |
Eunji Kim, Gahyeon Kim, Gianella Cravioto, Dong-hun Lee, Chaewon Moon, Chae-yeong Song, Sang-hyo Park |
| 493 |
Learning Semantic Inpainting for Animatable Gaussian Head Avatars |
Pilseo Park, Fizza Rubab, Yiying Tong |
| 508 |
Lightweight and Resource-Efficient Perception for Robotic Guide Dogs |
Jinse Kwon, Yoojin Lim, Choonghan Lee, Yongseung Yu, Yongin Kwon, Jemin Lee |
| 518 |
DragVAR: Cache-Consistent Cross-Scale Propagation for Drag Editing in Visual Autoregressive Generators |
Sin-Bum Kang, Ju-Hyeon Nam, Sang-Chul Lee |
| 522 |
GAP-Pose: An Unseen Object Pose Estimation Framework from a Single RGB Query Built on Depth Prediction and Affine-Perspective Alignment |
Peng Chen, Qiulin Li, Heshan Zuo, Fangyuan Niu |
| 537 |
YCB-Ev SD: Synthetic Event-Camera Dataset for 6D Object Pose Estimation |
Pavel Rojtberg, Paul Julius Kühn |
| 541 |
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction |
Yao Zhang, Zhuchenyang Liu, Yalan He, Thomas Ploetz, Yu Xiao |
| 547 |
ImCorr: Sub-pixel Semantic Correspondence via Implicit Feature Decoding |
Yusung Choi |
| 551 |
VDRShadow: Visual Detail Restoration with Lightweight Feature Adaptation for Shadow Detection |
Masakazu Ohkoba, JunFeng Xue, Marin Wada, Miho Adachi, Ryusuke Miyamoto |
| 554 |
MambaSplat-4D: Rotation-Invariant 4D Classification of Gaussian Splatting Sequences |
Alessandro Verdiesen, H Peter Hofstee, Zaid Al-Ars |
| 557 |
MSFP-Track: Multi-Scale Feature Pyramid Fusion with Instance-Adaptive Attention for Real-Time Multi-Object Tracking |
Toshpulatov Mukhiddin, Wookey Lee |
| 563 |
RT-NeLF: A Framework for Real-Time Light Field Video Streaming using Codec-Friendly Neural Representations |
Seojun Yang, Hyunmin Jung |
| 564 |
SFCell: Spatial-Frequency Driven Mamba for High-performance Unstained Cell Classification |
Xinyun Wang, Boyao Wan, Kewei Zong, Lei Kang, Xu Ding, Jing Yang, Yan Chen, Jiarui Han, Haofeng Li, Lian Zhang |
| 566 |
Boosting Fine-Grained Visual Counting Using Count-Only Annotations |
Yifeng Huang, Minh Hoai |
| 567 |
M2P-AD: Memory-to-Prototype Learning with Boundary-aware Score Refinement for 3D Anomaly Detection |
Seyoung Jeong, Jong Pil Yun, Sang Jun Lee |
| 570 |
FBard: Feature-Level Background Recalibration for Unsupervised Anomaly Detection in Unconstrained Environments |
Aoyang Hu, Kun Yu, Jie Ma |
| 574 |
ILLRAW: Illumination-Aware RAW Object Detection |
Xinzhe Wang, Xiao Liang, xiaoli zhang, Kang Ma |
| 577 |
DCR-TSF: Dual-Level Compositional Reasoning with Triadic Spherical Fusion for Training-Free Zero-Shot Composed Image Retrieval |
Gwang-Ho Na, Ho-Joong Kim, Seong-Whan Lee |
| 586 |
Dynamics-Inspired Diffusion for Foreground-Preserving Document Background Editing |
Taewon Kang, Yu Shen, Ming Lin |
| 588 |
CrossDD: Cross-Reference Disparity Estimation and Defocus Deblurring Using Dual-Pixel Sensor |
Zhuofeng Wu, Yusuke Monno, Masatoshi Okutomi |
| 590 |
CASE: Concept-Aware Segmentation from Positive and Negative Visual Exemplars |
Yi-Jen Tsai, Yen-Yu Lin, Chien-Yao Wang |
| 597 |
SHEAR: Semantic Hierarchical Elimination to Alleviate Retrieval-induced Redundancy in Multimodal RAG |
Wonjun Hwang, Seungil Lee, Hyun Kim |
| 611 |
SF-VO: Self-Supervised Few-Shot Adaptation for Visual Odometry |
Junhee Lee, Inha Lee, Jean Oh, Ukcheol Shin, Kyungdon Joo |
| 613 |
BoDA: Boundary-Distance-Aware Coreset Selection for Efficient Machine Unlearning |
Hyunjune Kim, Sangyong Lee, Simon S. Woo |
| 616 |
AULD: Adaptive Continuous Dual-Weighting for Uncertainty Calibration in Medical Image Segmentation |
Kun Cheng, Yukun Zhang, Tonggang Zhao, William Henry Nailon, Yifan Liu |
| 617 |
Region-Aware Consistency Regularization with Weight Scheduling for Calibrated Medical Image Segmentation |
Kun Cheng, Yukun Zhang, Tonggang Zhao, William Henry Nailon, Yifan Liu |
| 621 |
Query-Driven Contrastive Decoding for Hallucination Mitigation in LVLMs |
Shunya Shimomura, Kazuhiro Hotta |
| 624 |
Rethinking Streaming-Perception Evaluation on Heterogeneous Edge Platforms |
Misun Yu, Jemin Lee, Jinyoung Moon |
| 627 |
Guiding Visual Evidence with Saliency Maps for Video Emotion Recognition |
Sumin Lee, ChaeEun Woo, Byung Hyung Kim |
| 629 |
TIRAD: Text-guided Image Residual Learning for Generalist Anomaly Detection |
Seongsu Lee, Seunghyun Oh, Seungjae Moon, Youngmin Ro |
| 630 |
ProX-MAD: Aggregating Spatial Context into Representative Proxies for Few-shot Medical Anomaly Detection |
Seunghyun Oh, Seongsu Lee, SeunghyeChae, Youngmin Ro |
| 633 |
MCC-TTA: Mitigating Class Confusion for Federated Test-Time Adaptation of Vision-Language Models |
Yicheng Zhang, lixin Liu, Jingyu Wang, Yun Hao, Yumei Wang, Gang Li |
| 634 |
BiDiC: Selective Binarization for Efficient Convolutional Diffusion Models via Direction-Aware Decomposition |
Chang Yin, Yikai Wang, Qin Li, xiaoxiong xi |
| 635 |
FedStabilize: Tackling Non-IID and Noisy Labels in Federated Learning via Prototype-Based Global Alignment |
Oussama Choubane, Fantin Girard, Vincent Despiegel, Ngoc-Son Vu |
| 640 |
A Transferable Variant Signal That Grocery Retrieval Cannot Reach |
Emmanuel Maminta, Rowel Atienza |
| 646 |
MotionID: Motion-Aware Identity Anchoring for Identity-Preserving Video Generation |
Yiming Zhong, Haoming Shen, Jianjie Luo, Jiajie LIN, Yi Yu, Zhenguo Yang |
| 655 |
Motion-Aware Temporal Alignment for Event-Based Deblurring |
Jin-Seon Oh, Tae Hyun Kim |
| 657 |
Optical Music Recognition for Handwritten Kateishiki-fu Scores Using Symbol Detection and Melody Completion |
Emika Kurita, Wataru Ikeda, Shuhei Yamada, Haruyoshi Suzuki, Maki Sugimoto, Mariko Isogawa |
| 659 |
Physics-Informed Multi-Task Spatio-Temporal Graph Convolutional Networks for Pickleball Action Recognition |
Guiwen Tan, Yinwei Zhan |
| 664 |
MELinA: Multi-Task Embedding Learning for Dual-View Mammogram Assessment |
Phollawat Janesiripanich, Patawee Prakrankamanant, Ekapol Chuangsuwanich |
| 673 |
DGFlow: Plug-and-Play Depth and Camera Geometry Modules for Unsupervised Optical Flow Estimation |
Subin Lee, AJeong Kim, Jinsun Park |
| 675 |
FVSSM: Frequency-Aware Visual State Space Model for Image Motion Deblurring |
Mingsi Yuan, Shuailiang Song, Xiaopeng Hu |
| 676 |
SCOPE: Semantic COdec Pre-Editing for Object-Preserving Compression |
Silvia Dani, Leonardo Galteri, Marco Bertini |
| 682 |
Bridging the Prompt Distribution Gap: An Evolving Runtime Harness for Text-to-Image Generators |
Jinuk Lee |
| 686 |
MTV: Revisiting Multi-Task Visual Representation Learning |
Shangzhe Di, Zhonghua Zhai, Weidi Xie |
| 699 |
FFNet: MetaMixer-based Efficient Convolutional Mixer Design |
Seokju Yun, Dongheon Lee, Youngmin Ro |
| 700 |
Learned Suppression for 3D Keypoint Detection with a Graph-Transformer Backbone |
Batuhan Arda Bekar, Can Sarı, Hüseyin Can Gülkan, Barış Özcan |
| 705 |
Masked Feature Encoding for Large-Scale Whole Slide Image Representation |
Haoyu He, Basile Tessier-Cloutier, Yang Wang, Mahdi S. Hosseini |
| 707 |
Camera-Aware Scene Tokens for Pose Refinement |
Kent Selwyn The, Hang-Hsi Chen, Koichi Ito, Hwann-Tzong Chen, Takafumi Aoki |
| 710 |
Does Peer Observation Help? Vision-Sharing Collaboration for Vision-Language Navigation |
Qunchao Jin, Yiliao Song, Qi Wu |
| 713 |
Robust Novel View Synthesis of Athletes from Monocular Videos under Low-Resolution and Fast Motion |
Hao-Chiang Shao, Chiang-Yu Lin, Chia-Wen Lin |
| 714 |
VIREO: Visual-Inertial-based Reconstruction with Euclidean-Distance Optimization |
Yuze Du, Chuchu Chen, Zijun Sha, Guoquan Huang |
| 731 |
Zero-DIPE: A Zero-Shot Differentiable Image Processing Engine for Low-Light Enhancement |
Lele Yu, Jingkang Yang, Zimo Zhang, Yining Liu |
| 737 |
Reflection-Robust 6DoF Object Tracking with Light Fields |
Nikolai Goncharov, Donald G. Dansereau |
| 740 |
TAESAN(Trustworthy Acquisition-aware Evidence-grounded Selective AbsteNtion) |
Jiwon Park, HAYOUNG OH |
| 741 |
Compressed Structural Tokens: Quantisation-Robust Frame-to-Graph Generation with Small VLMs |
Lewis Watson, carl strathearn, Yanchao Yu |
| 742 |
HAAC-Mamba: Multi-Axis State Space Modeling with Hierarchical Codebooks for Aortic Segmentation |
Jongbin Chae, Dong-Gyu Lee |
| 744 |
Geometry-Guided Density Control for Compact Gaussian Face Reconstruction |
Yiwei Liu, Senjian An, Ling Li, Petra Helmholz, Richard Palmer, Gareth Baynam |
| 747 |
SplatLR: Towards Scene-Conditioned Learning-Rate Scheduling for 3D Gaussian Splatting |
Ahmed Haroon, Mohsen Ali, Rehan Hafiz, Hyon-Gon Choo, Yongju Cho |
| 750 |
Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling |
Kwanyoung Lee, SeungJu Cha, Yebin Ahn, Sungho Koh, Dong-Jin Kim |
| 751 |
OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception |
Binh Long Nguyen, Kien Nguyen, Clinton Fookes, Peyman Moghadam |
| 752 |
SOFA: Selective Opacity Suppression for Floater Removal in Gaussian Surface Reconstruction |
Shin Jiho, Seungkyu Lee |
| 753 |
Complex Normality Matters: A Benchmark and Lightweight Detector for Anomaly Detection |
Yuta Nakanishi, Kazuhiro Kamada, Akira Minezawa, Naoki Murakami, Manabu Hashimoto |
| 755 |
Relation-Transition-Aware Transformer for Video Scene Graph Generation |
Jaeyeon Heo, Geuntaek Lim, Yukyung Choi |
| 759 |
Brightening the Blur: Spatial-Frequency Collaborative Restoration for Low-Light Blurry Images |
Lu Hu, Peng Feng, FengLiang Chen, Yuhao Gu |
| 760 |
Entropy-Programmed Diffusion Models |
Yunkai Li, Bo Tang |
| 761 |
TRACE: Time-Adaptive Residual Attention Control with Content–Style decomposition for Training-Free Diffusion Style Transfer |
Le Duc Khoan, Kim Ngoc Tran, Minh Nhat Le, Tran Thanh An, Nguyen Viet Toan, Lay Khanh An, Tran Thai Son, Hoang Pham Minh |
| 763 |
Task-Aware Active Learning for Cross Modality Image Matching |
Srivatsa Kadaba Abhiram, Bihan Wen, Xun Xu, Xulei Yang, Lile Cai |
| 764 |
CCTR-VLN: Candidate-Conditioned Temporal Reasoning for Vision-Language Navigation in Continuous Environments |
Kai-Ming Han, Fu-Zhao Ou, Yuan-Gen Wang |
| 767 |
TopoDiSE: Topology-Preserving Representations for Corneal IVCM Diagnosis |
Xueyao Wan, Hang Yu |
| 776 |
Mean Pooling Is the DC Component: Spatial-Frequency Structure of Frozen Vision Transformer Tokens across Pretraining Objectives |
Minhyeok Lee |
| 777 |
GARF-IR: Guided Adaptive Residual-Frequency Calibration for All-in-One Image Restoration |
Muhammad Ali Iqbal, Yeo Chan Yoon, Gyeongmin Kim, In-Chul Han, SOO KYUN KIM |
| 780 |
Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images |
Kaname Kitamura, Asako Kanezaki |
| 784 |
ATARIBench: Assess Temporal Abstract Perception and Reasoning of Symbolic Interaction with LLMs |
Karam Tomotaki-Dawoud, Alexander Ehrenhöfer, Katerina Katsarou, Sebastian Bosse |
| 786 |
MFilter: Pair-Conditioned Keypoint Matchability for Lightweight Sparse Matching |
Xinpeng Zhu, Zhixiong Zhang, Wentao Cheng |
| 787 |
Anonymized but Not Anonymous: Multi-Cue Identity Leakage in Privacy-Preserving Action Recognition |
Safwan Nabeel, Farah Alshiha, Muzammil Behzad |
| 788 |
TCA: Lightweight Template-Conditioned Aggregation for Accurate Few-Shot Object Recognition |
Lingtao Zhan, YanHui, Jiale Zhu, Xi Chen, Jie Zhan, Yixuan Zhu, Teng ZHANG, Yeliang Wang |
| 789 |
GLIDE: Guided LiDAR Intensity Adjustment for Detection Evaluation |
Akinobu Ikeda, Chikao Tsuchiya |
| 794 |
Do Not Merge the Registers: Register-Aware Reduction for Extreme Token Compression in Vision Encoders with Registers |
ChoHyunJun, JooHyoung Cha, Yongin Kwon |
| 798 |
Temporal Residual Bottleneck for Robust Asynchronous Collaborative Perception |
Melih Yazgan, Ahmed Abouelazm, J. Marius Zöllner |
| 799 |
VFM-3DAD: Language-Free Zero-shot 3D Anomaly Detection via Visual Foundation Models |
Ryusei Mikami, Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama |
| 803 |
FORUM: Frozen Outputs Reconciled via Uncorrelated Model Errors for Visual Grounding |
Taiyo Sato, Takamasa Sanda, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, Shunya Nagashima |
| 804 |
PARS: Unifying Reasoning and Perceptual Reinforcement for Multimodal Segmentation |
Hikaru Tanabe, Yuta Baba, Keiji Yanai |
| 806 |
Multi-View Action Spotting of Collisions in Sports |
Clément Vermeylen, Renaud Vandeghen, Leonardo R. Brandão, Robert J. Klaassen, Patricia E. Longmuir, Marc Van Droogenbroeck, Anthony Cioppa |
| 810 |
Structure-Aware Functional Tensor Decomposition for Real-Time Semantic Segmentation |
Zhang Lei, Li He, Hui Chen, Xingyu Yuan |
| 811 |
STAMPose: Spatial-Temporal Attention-Mamba for Efficient 3D Human Pose Estimation |
Hyun-il Kim, Seungbo Park |
| 815 |
DA-CoLoR: Scalable Text-Guided Long-Video Colorization with Dual Attention and Video Diffusion |
Rintaro Kimura, Keiji Yanai |
| 817 |
Self-Generated Learnable Spatial Prompting for Tumor-Aware Abdominal Organ Segmentation |
Asad Imam, Iftikhar Ahmad, Soon Ki Jung |
| 821 |
IA-Era: Image-Aligned Concept Erasure |
Qingchen Tang, Flora D. Salim, Sanjay Kumar Jha, Catarina Moreira, Yang Song |
| 825 |
Point-MF: Stabilizing One-Step Mean Flow for Single-Image Point Cloud Reconstruction |
Yuta Baba, Keiji Yanai |
| 832 |
Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation |
Chaehun Shin, Jooyoung Choi, Johan Barthelemy, Jungbeom Lee, Sungroh Yoon |
| 834 |
BindTrack: Binding Cross-Modal Trajectories for Robust 3D Multi-Object Tracking |
Weidong Wu, Wang Wenhao, Dongchen Zhu, Li Bo, Lei Wang |
| 837 |
LFIR2ThermoBody: 3D Human Model with Surface Thermal Distribution from Low-Resolution Far-Infrared Image Sequences |
Taiyo Tamaki, Motoharu Sonogashira, Kazuya Kitano, Yuki Fujimura, Yasuhiro Mukaigawa, Yasutomo Kawanishi |
| 838 |
Kalman Filter-Inspired Visual-Inertial Odometry with Motion Priors |
Minje Kim, Changwoo Kang, Jeong hwan Jeon, Kyungdon Joo |
| 839 |
CALIMAP: Plug-and-Play Query Adaptation for Robust Vectorized HD Map Construction |
Juyoung Kim, Ji-Hong Park, Sang-Min Choi, Gun-Woo Kim |
| 840 |
SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos |
Jacobus Arthur, Ahmad Sait, Batool Hani, Merey Ramazanova, Jan Held, Marc Van Droogenbroeck, Bernard Ghanem, Anthony Cioppa, Silvio Giancola |
| 842 |
HLCU: Heterogeneity-Guided Local Consensus Gaussian Splatting for Underwater Reconstruction and Rendering |
Jiacheng Li, Ximan Zhao, Xuanhe Chu, Miaoxin Lu, Siyuan Liu |
| 846 |
SALT: Safe Anchored Low-Rank Adaptation at Test Time for Spectral Compressive Imaging |
Zhaolu Chen, Xian-Hua Han |
| 848 |
SatCoRe: Satellite-guided Complementary Reliability Propagation for 3D Semantic Scene Completion |
Gayeon Kim, Hyunseop Kim, Hanul Kim, Yeong Jun Koh |
| 857 |
DiffPyr: Frequency-Motivated Spectral Diffusion with Multi-Scale Context for Partial Shape Correspondence |
Zhaochen Zhang, Xuguang Zhu, Yuichiro Hayashi, Masahiro Oda, Kensaku Mori |
| 858 |
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack |
Hoseong Tae, Jong-Seok Lee |
| 860 |
Grounded Concepts Meet SAM3 for Training-Free Logical Anomaly Detection |
Haidong Gao, Yangyang Zuo, Yutong Lin, Xu Tan |
| 863 |
DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration |
Mikołaj Jastrzębski, Wojciech Maciej Kozłowski, Kamil Adamczewski |
| 869 |
Boundary-Guided Vision Mamba with Active Consistency for Robust Crack Segmentation |
Weixin Su, Junqi Luo |
| 870 |
GHARP: Real-time Gaussian Head Animation from Large-scale Reconstruction Prior |
Ali Benlalah, Mohammad Mahdi Johari, Patricia Vitoria, Armin Kappeler, Artem Sevastopolsky, Alexander Jung, Gabriele Fanelli, Kevin S Mader, Manuel Breitenstein, Claudia Plüss, Jan Rüegg, Simon Biland, Thomas Etterlin, Dmitry Kostiaev, Mathias Deschler, Brian Amberg, Sebastian Martin |
| 873 |
UBMNet: Uncertainty-driven Bidirectional Mamba Network for Infrared Small Target Detection |
yan li, Luyang Tian, Qing Zhang, Xiaowei Chen, Qiao Ye |
| 876 |
DGS: Robust and Diverse Watermarks for Diffusion Models |
Yuxuan Li, Hao Tang |
| 878 |
Direction-Aware Kinematics-Conditioned Graph Hypernetwork for Human Trajectory Prediction |
Amirreza M. Shebly, Mohammad Sarhangzadeh, Doruk Oner |
| 879 |
Meta-Learned Adaptive Optimization for Robust Human Mesh Recovery with Uncertainty-Aware Parameter Updates |
Shaurjya Mandal, Nutan Sharma, John Galeotti |
| 884 |
Distilling Physiological Priors: A Teacher-Student Framework for Remote Photoplethysmography |
Xiaoyu Wang, Yan Chen, Yang Hu |
| 891 |
ImIR: Image-Instruction Tuning for All-in-One Image Restoration |
Süleyman Aslan, Görkay Aydemir, Mısra Yavuz, Yunus Bilge Kurt, Nasrin Rahimi, Ahmet Rasim Emirdagi, Burak Can Biner, MUSTAFA AKIN YILMAZ |
| 893 |
CleanEdit: Decoupling Editing and Preservation in Rectified Flow via Clean Estimates |
Zijian Wu, Jinjia Zhou |
| 895 |
Training-free Logical Anomaly Detection via VLM-based Automated Prompting and Patch-Text Alignment |
Taeheon Jin, Dongwoo Kim, Jaehoon Lim, ChanMin An, MINJAE KWEUN, Jaeyo Chang, Jongpil Jeong |
| 896 |
CovHiS: Bridging Covariance and Subspace History for Classifier-free guidance |
Nazmus Saqib, Masud An-Nur Islam Fahim, Gyeongmin Kim, Joon-Min Gil |
| 898 |
Counterfactual Reward Learning for Autonomous Driving |
Eray Çakar, Shadi Hamdan, Jiazhi Yang, Tianyu Li, Hongyang Li, Fatma Güney |
| 900 |
Direction-Aware Spectral Artifact Modeling for Generalizable AI-Generated Image Detection |
Bingyan Wu, Weiming Chen, Youming Li, Zhiwei Hu, Zhihan Zhu, Zhihai He |
| 902 |
HyMS: Hybrid Multi-Scale Token Fusion via Soft Mixture-of-Experts for Deep Metric Learning |
Trong Nhan Nguyen |
| 904 |
Improving Skeleton Representations for Anticipation through Feature-Space Self-Supervised Pre-Training |
Raphael Lorenzo-Louis, Serena Ivaldi, Bertrand Luvison |
| 906 |
FTC: Fourier Transcoder for Monosemantic Sparse Feature Decomposition in Vision Language Models |
Kyeongjun Cho, Juheon Kang, Hyunseo Shin, Hongseok Oh, Wonseok Hwang |
| 907 |
Physics-Aware Source Selection for Few-Shot Domain Adaptation in Single-Photon LiDAR Perception |
Wenle Dong, Ziting Wen, Zili Zhang, Hongzhou Dong, Guodong Shi, Xiaoqiang Ren |
| 915 |
Self-Consistency Geometry Injection for Multi-view Consistent Image Generation |
Yupeng Xiao, Yankai Wu, Jianjie Luo, Jiajie LIN, Yi Yu, Zhenguo Yang |
| 926 |
When, Where, and Why: Hierarchical Causal Explainability for Video Face Understanding with MLLMs |
Anubhav Kataria, Shreya Ghosh, Jingwen Ye, Abhinav Dhall |
| 928 |
More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe |
Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi, Luc Van Gool, Danda Pani Paudel |
| 930 |
Quantifying Annotation Agreement in Object Detection with Optimal Transport |
Kirill Prokhorov, Alexandr A. Kalinin |
| 935 |
RECAL-Bench: A Unified Benchmark for REalistic, Context Aware Listener's Reaction Generation |
Lownish Rai Sookha, Shreya Ghosh, Mudasir Ganaie, Abhinav Dhall |
| 936 |
Higher-Order Structural Relation Learning for Semi-Supervised Pathology Image Classification |
Gayathri C, Rony Hait, Rajeshreddy Datla, Sobhan Babu |
| 944 |
Dressing for the Occasion: Context-Aware Clothing Synthesis |
Chiang Tseng, Wei-Chih Chen, Yu-Ting Shen, Bo-Kai Ruan, Hong-Han Shuai |
| 950 |
Feature Suppression for Black-Box Vanishing Adversarial Attack in Object Detection |
Alexis Winter, Romaric Audigier, Angelique Loesch, Bertrand Luvison |
| 951 |
Physics-Guided Flow-Map Matching for Precipitation Nowcasting |
Shunya Nagashima, Takumi Bannai, Makoto Misaizu, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama |
| 952 |
DETSAC: Transformer Set Prediction for Robust Multi-Model Fitting |
Panithi Vanasirikul, Piyanon Charoenpoonpanich, Ronnapee Chaichaowarat, Ekapol Chuangsuwanich |
| 954 |
PoE-Fuse: Precision-Weighted Expert Fusion for Bi-Temporal Change Understanding |
Haruki Watase, Shunya Nagashima, Nishimura Takayuki |
| 959 |
STRUCTURED FUSION EXTENSIONS TO IMPROVE MULTI-MODAL CROSS FUSION TRANSFORMER FOR OBJECT DETECTION |
Wael Bouchaala, Hichem Frigui |
| 960 |
Confident, Stable, and Wrong: Penalizing Depth-Trajectory Agreement for Out-of-Distribution Selective Prediction in Vision Transformers |
Minhyeok Lee |
| 961 |
Stabilizing and Aligning Self-Supervised Knowledge for Medical Image Classification |
Soyoun Bang, Jeongwoo Ju, Sanjar Karshiev, Jiuk Hong, Eungjoo Lee, Heechul Jung |
| 966 |
Detecting Diffusion-Generated DeepFakes via Fine-Scale Realization Artifacts |
Dong-Hyeon Kang, Ju-Hyeon Nam, Sang-Chul Lee |
| 968 |
Respiration-Aware 3D Reconstruction for Thoracoscopic Surgery |
Zuxin Fan, Shunyi Zhao, Jiayi Geng, Xiuyuan Chen, Lecheng Ruan, Qining Wang |
| 970 |
MonoMIP: Multi-Height Inverse Perspective Mapping for Monocular 3D Object Detection |
Emir Ulurak, Furkan Kıraç |
| 975 |
LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder |
Duc Anh Khoa Dinh, Duc-Tai Dinh, Tam V. Nguyen, Minh-Triet Tran |
| 984 |
Adaptive Observation Control for Active Visual Recognition |
Dikai Li, Weijia Wang, Yuan-Gen Wang |
| 986 |
S2D-Match: A Dataset and Sparse-to-Dense Framework with Dual-Kernel RKHS-Based Interpolation for UAV Visible–Infrared Matching |
zixuan xiao, Ruigang Fu, Songyu, Zhao Zhang, Jiajun Xiang, Ping Zhong |
| 988 |
vSV-ViT: Variable-size SuperVertex Vision Transformer for Cortical Surface Learning in Alzheimer's Disease |
Geonwoo Baek, Ikbeom Jang |
| 990 |
VFM-Guided Multi-Dataset Multi-Task Label Completion for Road-Scene Understanding |
Kai-Jun Liang, Chien-Yao Wang, Yi-Ting Huang |
| 992 |
Learning Residual Reliability for 3DGS-based Pose-Agnostic Anomaly Detection |
Seo Yun O, Myung Han Hyun |
| 995 |
DVIM: Dynamic Viewport Interaction Modeling for Omnidirectional Image Quality Assessment |
Bo Hu, Qiqi Zheng |
| 996 |
Atlas-Guided Reasoning for Fine-Grained Visual Recognition |
Daisuke Kobayashi |
| 999 |
Tracking and Inferring Behavior of Marmosets from Videos |
Makkawan Burana-amnuay, Titipat Achakulvisut, Lalitta Suriya-Arunroj, Prarinya Siritanawan, Konlakorn Wongpatikaseree |
| 1006 |
EnVid: Posterior-Aware Energy Scoring for Autoregressive Image-to-Video Generation |
SeokHo You, HyunJin Kim |
| 1014 |
When Does Post-Hoc Prototype Refinement Help? : Adaptive Boundary Refinement as a Controlled Study for Few-Shot Learning |
Garthigan Kumarasamy, Uthayasanker Thayasivam, Damminda Alahakoon |
| 1015 |
Where Did Monocular 3D Detection Improve? A Twelve-Detector Anatomy of Progress |
SangJin Jung, YongHwan Lee |
| 1016 |
SURE: Scalable Uncertainty Estimation for Pretrained Multimodal Models with Missing Modalities |
Duy A. Nguyen, Do Huu Quan, Khoa D Doan, Minh N. Do |
| 1024 |
PathoS2VD: From 2D Histopathology to Pseudo Z-Stack Representations |
Jiamu Wang, Keunho Byeon, Ji-Uk Kim, Jin Tae Kwak, Heounjeong Go |
| 1031 |
Mask-Aware Assignment and Semantic-Spatial Decoupling for Real-Time Instance Segmentation |
KIM JIN WOONG, Muhammad Ali Iqbal, Junho Ahn, SOO KYUN KIM |
| 1034 |
HybridHOT: Learning Human-Centric Priors for Fine-Grained Human–Object Contact Segmentation |
Qihui Chen, Junwen Chen, Keiji Yanai |
| 1038 |
Borrowed Realism: Ground-Truth Leakage in Token-Curated Autoregressive Video Generation |
Nirmal Adhikari, Dohhoon Kim, Chingiz Tursunbaev, Ahyun Kim, John Heong Lee, Nirvika Gupta, Wookey Lee |
| 1039 |
Drift-adaptive Representation Preservation for Domain-Incremental Learning |
Hyunmin Kong, Gyutae Oh, Jitae Shin |
| 1040 |
Change Detection in Longitudinal Chest X-rays Is Readout-Limited, Not Task-Limited |
Seungin Baek, Gyutae Oh, Jitae Shin |
| 1041 |
Virtual Point Removal for 3D Point Cloud with Arbitrarily Shaped Reflective Surfaces |
DaeHyeon Jeon, Jae-Young Sim |
| 1046 |
Motion That Survives the Dark: Illumination-Robust Riesz-Phase Motion for Frozen Foundation-Model Video Recognition |
Dohhoon Kim, Nirmal Adhikari, Chingiz Tursunbaev, Ahyun Kim, John Heong Lee, Wookey Lee |
| 1048 |
Spectral Descriptor Conditioning: Efficient and Interpretable All-in-One Image Restoration via Polar Frequency Signatures |
Jungwoo Bae, Gyutae Oh, Hyunmin Kong, Jitae Shin |
| 1049 |
Same Person, Different Perception: Adversarial Identity Substitution against LVLM-Based Out-of-Context Detection |
Zhi-Tang Lin, Sih-Cin Huang, Ming-Hung Wang |
| 1061 |
Analytic Feature Adaptation for Point Cloud FSCIL via Closed-Form Alignment |
Gakuto Kita, Yutaro Hirao, Monica Perusquia-Hernandez, Hideaki Uchiyama, Kiyoshi Kiyokawa |
| 1065 |
Scale-Aware Fusion and Constant False-Alarm-Rate Regularization for Small-Object Detection in Real-Time DETRs |
Yoav Shalev, Bashar Elnashef, Lior Wolf |
| 1072 |
BAMspecies: A Benchmark Dataset for Individual Tree Species Classification from Ultra High-Resolution RGB and LiDAR Point Cloud |
Mareike Weishaupt, Wen Fan, Youcef Ben Ghorbel, Daniel Panangian, Jonas Troles, Ute Schmid, Jiaojiao Tian |
| 1075 |
Cold Hands, Warm Start: When Sign-Specific Pretraining Pays for Continuous Sign Language Recognition |
Chingiz Tursunbaev, Nirmal Adhikari, Dohhoon Kim, Abdullokh Asatullaev, Rustamov Giyosbek, Ahyun Kim, John Heong Lee, Wookey Lee |
| 1080 |
Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging |
Hyunjoong Cho, Jinhyeok Jang |
| 1081 |
CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation |
Jin Hyun, Jung Gyu Min, Gyuhyun Jung, Youngjoo Lee |
| 1084 |
TAOSV: Trajectory Reconstruction Assisted Chinese Offline Signature Verification |
Shaoxin Ma, Lizhong Zheng, Xu Zhao |
| 1086 |
HetReg: Structuring Heterogeneous Latent Geometry for Visual World Models |
Lingfan Yuan, Xuezi Li, Hitoshi Iyatomi, Jinjia Zhou |
| 1087 |
Boundary-Aware Hard Negative Learning and KG-Assisted Dynamic Slot Memory for Class-Incremental Learning |
Haixuan Wang, Yiran Chen, Zongcheng Chu |
| 1092 |
Surface-Attribute Text Conditioning for RGB-to-Hyperspectral Reconstruction |
Chan Hur, Woonggyu Min, Ho-Youl Jung, Soo Jun Park, Myungeun Lim |
| 1100 |
Frequency-Aware Dynamic Aggregation for Robust RGBT Tracking |
Jianming Zhang, Yonghang Liu, Jun Long, Yiting Yang |
| 1102 |
Score Sharp, Refine Soft: Un-Paired Objectives for Locally-Optimized Robust Estimation |
James Pritts, Kevin Köser |
| 1111 |
Removing One Identity, Creating Another: Identity Collision in Face Anonymization |
Jinhyeong Park, Muhammad Shaheryar, Minsu Shin, Hyeonseo Yoon, Seangmin Lee, Soon Ki Jung |
| 1115 |
MTSU: Multi-scale Timestep-aware Sparse Unlearning for Fine-grained Diffusion Concept Erasure |
Yixin Lou, Xinwen Cheng, Xiaolin Huang |
| 1118 |
Minimum Visual Evidence for Recovery in Frozen Vision-Language-Action Policies |
Ruizhi Zhang, Zhuofeng Zhao |
| 1124 |
Pose Mutation: Target-Pose-Free Consistent Pose Exploration for Portrait Generation |
Masaru Mizuochi, Takashi Shibuya, Masato Ishii, vali lalioti |
| 1126 |
Diagnosing and Correcting Skin-Tone Color Casts in Ultra-Lightweight Photo Retouching Networks |
Choulhyouc Lee |
| 1128 |
EchoScene: A Bio-Inspired Sonar Dataset for Depth Prediction |
Nazrul Ismail, Muhammad Amirul Raziq Rosman, Owais Ahmed Malik, Wee Hong Ong |
| 1129 |
MedPruneVLM: Anatomy-Aware Hallucination Reduction for Medical Large Vision Language Models |
Akhmadjon Tursunov, Sheraz Babar, HAYOUNG OH, Farman Ali |
| 1130 |
Factorized Temporal–Spatial–Modal Alignment for Cross-Sensor Spatiotemporal Image Fusion |
Jiyuan Qiu, Xin Xu, Xiaowei Tong, Rasmus Fensholt, Martin Brandt |
| 1133 |
Personalized Quantum Federated Visual Learning via Raced Architecture Search and Ensemble Calibration |
Seok Bin Son, Soohyun Park, Joongheon Kim, Wonjun Lee |
| 1134 |
ReLEAP: Upcycling Vision Datasets through Cross-Task Unification and Semi-Supervised Annotation |
Julia Simon, Daniel Steininger, Andreas Trondl |
| 1136 |
TAPSN: A Multimodal Simulation Dataset for Transferring Autonomous Driving Paradigms to Social Navigation |
Mohan Zhou, Ruicong Zhi, Xiaoyuan Liang |
| 1151 |
Unlearnable Faces: Privacy Protection Surviving Extraction Pipeline |
Byunghoon Oh, Sunghwan Park, Jaewoo Lee |
| 1152 |
PatchPlan: Text-to-Floorplan Generation via Patch-Based Diffusion Transformers |
Minjun Zhao, Wenming Wu, Tianlei Sheng, Kang Ding, Gaofeng Zhang, Liping Zheng |
| 1159 |
Probabilistic Structured Event Modeling for Video Event Retrieval under Perceptual Uncertainty |
Nhan Thanh Ho, Anh Dong Nguyen, Thuan Duc Tran, Nguyễn Văn Thắng, Bui Anh Thinh, Nguyên Bảo Trần, Long Nhat Ho |
| 1164 |
FineBP: Fine-Grained Pixel-Level Attribution for Vision Transformers through Surrogate Representation Transformation |
Aditi Wekhande, Shilpy Kaur, Aruna Tiwari |
| 1169 |
REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation |
Mantha Sai Gopal, Jaison Saji Chacko, Harsh Nandwana, Sandesha Hegde, Debarshi Banerjee, Uma Mahesh |
| 1173 |
VERTAG: Visual Examiner Rationales for Trademarks with Atomic Grounding |
Sheng-Yuan Yen, Chia-Yi Chou, Chi-Tse Peng, Chian-Yu Ye, Tsan-Wei Yu, Chih-Chun Ko, Yi-Chieh Wu |
| 1175 |
MSO-Diff: Tuning-Free Controlled Multi-Subject and Multi-Object Personalization in Text-to-Image Diffusion Models |
Muhammad Rifqi Fauzi, Novanto Yudistira, Gembong Edhi Setyawan, Yuta Nakashima |
| 1178 |
On the Uncertainty of Night-Time Object Detection: Annotation or Enhancement, What Matters More? |
Fatemeh Siar, Francisco C. Pereira |
| 1179 |
Disagreement-Guided Pseudo-Label Selection for Annotation-Free Camouflaged Object Detection |
Suhang Li, Osamu Yoshie, Yuya Ieiri |
| 1181 |
Confidence-Driven Side-Window Guided Filtering via Scale-Weighted Regularization and Adaptive Fusion |
Soyeon Ahn, Suk-Ho Lee, Moon Gi Kang |
| 1184 |
AnchorCache: Quadrature Composition of Cache Errors for Anchor Schedule Synthesis in Video Rectified-Flow Inference |
Tianbi Deng, Shuhua Xie, Yiming Su |
| 1185 |
Adversarial Diffusion Distillation via Characteristic Function Matching |
Jinyoung Choi, Chunsan Hong, Do Young Eun, Bohyung Han |
| 1189 |
Rethinking Uncertainty Quantification and Entanglement in Image Segmentation |
Jakob Lønborg Christensen, Vedrana Andersen Dahl, Morten Rieger Hannemose, Anders Dahl, Christian F. Baumgartner |
| 1200 |
DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion |
Sithu Aung, Viktor Kocur, Yaqing Ding, Torsten Sattler, Zuzana Kukelova |
| 1201 |
SPACE-CLIPv2: Decoding Local Geometry from Frozen CLIP for Monocular Depth Estimation |
Hyun Song, Taewan Cho, Kangmin Kim, Andrew Jaeyong Choi |
| 1219 |
UrbanStreetVQA: A Benchmark for Visual Understanding of Urban Street Views |
Ziliang Huang, Kosuke Kurihara, Kiyoharu Aizawa, Takayuki Hamamoto |
| 1220 |
EviGraph: Evidence-Graph Frame Selection for Long-Video Question Answering |
Ning Ding, Keisuke Fujii, Toru Tamaki |
| 1223 |
Optical Character Recognition for Lao: A Benchmark and Zone-Aware Height Pooling |
SOULIXAY VILAIPHONE, Qiuchi Li, Khonepaseuth SOUNAKHEN |
| 1224 |
CARE: Camera-Residual Reserves for First Sightings in Adaptive LiDAR Sensing |
JIACHEN GONG, Yun Li, Ehsan Javanmardi, Wencan Mao, Manabu Tsukada |
| 1225 |
ThermalManhattan: Robust Thermal Compass under Radiometric Flatness in Manhattan World |
Hyeonji Shin, Junpyo Kim, Pyojin Kim |
| 1226 |
TriggerCraft: A Reproducible Framework for Physical Backdoor Dataset Synthesis |
Sze Jue Yang, Chinh Duc La, Quang H Nguyen, Eugene Bagdasarian, Kok-Seng Wong, Chee Seng Chan, Khoa D Doan |
| 1234 |
Calibrated Entity-aware Relation Matching for Multimodal Relation Extraction |
Yunhao Li, Yikang Huang, Zhuoyu Du, Bin Huang, Kunli Zhang |
| 1236 |
Knowing Where to Look Is Not Enough: Purified Attended Evidence for Large Vision-Language Model Hallucination Mitigation |
Yining Wang, Zining Chen, Fei Su |
| 1237 |
Cascaded Diffusion Models for Augmenting Imbalanced Cell Nuclei Classification |
Haofeng Li, Yang Ji, Guanbin Li |
| 1239 |
Source-Sensitive Audit-and-Response: Claim-Level Reporting for Text-to-Image Evaluation |
Hyejin Kim, Suan Lee |
| 1242 |
Learning Aligned RGB-Event Representations for All-Day Semantic Segmentation |
Carl Cao, JieyunLi |
| 1246 |
HindsightVLA: Learning Actionable Predictive World Latents for Autonomous Driving |
Jiajie Huang, Ning Li, jichao jiao, Ziyi Bao, Risheng Fan |
| 1248 |
ADIScene: Affordance-Guided Diffusion for Interaction-Feasible 3D Scene Generation |
Misong Kim, JuYeong Hwang, SeungJeh Chung, Jaeyoung Seon, Ri Yu, HyeongYeop Kang |
| 1249 |
Fine-Grained Generative Hallucination Detection and Correction for Aerial Image Captioning |
Debolena Basak, Somsubhra De, Maunendra Sankar Desarkar |
| 1252 |
Same Outputs, Opposite Verdicts: Object-Claim Churn in Compressed Vision–Language Models |
Lee GyeomSoo, Suan Lee |
| 1257 |
Frequency-Decoupled Spatial-Spectral State Space Modeling for Hyperspectral Image Dehazing |
Xin Sun, Wei Liu |
| 1258 |
TiTok: Audio-Visual LLM for Multi-Segment Temporal Grounding |
Eunji Shin, Dahyun Choi, Seungyeon Jo, Yejin Hong, Jiyoung Lee |
| 1262 |
GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models |
Nicolae Cudlenco, Mihai Masala, Marius Leordeanu |
| 1263 |
Toward robust mmWave-based human pose reconstruction via Signal Attenuation Compensation and Limb Point Refinement |
Yoko Nakajima, Yusuke Oumi, Dixin Yang, Shohei Mori, Mariko Isogawa |
| 1264 |
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces |
Chethan Krishnamurthy Ramanaik, Tobias Callies, Michael Hecht, Eirini Ntoutsi |
| 1266 |
CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking |
German Devchich, Timur Akhtyamov, Denis Fatykhoph, Gonzalo Ferrer |
| 1268 |
SFDA-Net: Spatial-Frequency Feature Learning and Dynamic Affine Correlation for Generalizable Stereo Matching |
Fuyuan Tan, Taiping Xiong, Yue Feng |
| 1274 |
Multi-Robot Exploration and Target Coverage via Large Language Models |
TaoMing Yu, Lina Zhu, Chenyang Li, Qianyao Qiang |
| 1279 |
From Points to Chains: Quality-Aware Temporal Action Localization in Soccer Videos |
Kotaro Matsui, Jinhui Chen |
| 1284 |
ZLP-Net: Zernike-Guided Lightweight Phase Reconstruction for Efficient Sensorless Wavefront Sensing |
Tao Zhang, Li Zeng, Jie Tan, Yuchen Hua, Yang Shen, Xin Liu, Xiaoguang Ren |
| 1285 |
TEPNet for Tri-stage Evidence Preservation in Insulator Defect Detection |
MohanZeng, Pan Ruihan, ShiWeilin |
| 1301 |
FreqPhys: Synergistic Frequency-Domain Fusion for Remote Physiological Measurement |
Pengtao Tao, Yan Chen, Yang Hu |
| 1304 |
FreqAlign: Frequency-Aware Physical Alignment and Wavelet Fusion for Video-RF Remote Physiological Measurement |
Pengtao Tao, Yan Chen, Yang Hu |
| 1306 |
Hand–Object Contact Transition Detection in Egocentric Video |
Huy Anh Nguyen, Chang Dong, Feras Dayoub, Minh Hoai |
| 1308 |
A Parameter-Efficient Conditional Path Model for Human Trajectory Prediction under Set Geometry |
Haeyun Seo |
| 1310 |
Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging |
Aon Safdar, Mohamed Saadeldin |
| 1311 |
DogMotion: Unanchored Sketch-Guided Diffusion for Controllable Dog Motion Generation |
Yixuan Yin, Zonglin Yang, Wei Liang, Liyuan Pan |
| 1325 |
Do VLMs Really Look at the Road? A Diagnostic Evaluation for Autonomous Driving |
Shankar Gangisetty, Muskan Singh, C.V. Jawahar |
| 1328 |
Less Spectral Data, More Degradations: Rethinking Generalization Problem in CASSI Reconstruction |
Xiaodong Wang, Yifan Si, Xin Yuan |
| 1329 |
Diagnosing Proposal Bottlenecks in Open-Vocabulary 3D Instance Segmentation |
Chih-Yuan Cheng, Yi-Hsuan Huang, Bor Jiunn Hwang |
| 1338 |
From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning? |
Krishna Kanth Nakka, Vedasri Nakka |
| 1340 |
Learning Across Layers and Time for Deepfake Detection |
Krishna Nohwal, Pawan Soni, Vivek Kanhangad |
| 1345 |
Learning Sports Motion Feasibility via Quantile Regression on Tracking Data |
Marc Gutiérrez-Pérez, Antonio Agudo |
| 1367 |
Crop2Pose: Geometric Transformations for 6DoF Head Pose Estimation From A Face Crop |
Harshita Soni, Nikhil Tirumala, Jaswin Kasi |
| 1368 |
Diagnosing Negative Prompt Collapse under Global Presence Gating in Promptable Concept Segmentation |
Saiankit Shankar, Geethika Choudhary Yadlapalli, Cherith Reddy Yerabolu, Prafulla Kalapatapu |
| 1373 |
Enhancing Diabetic Retinopathy Grading via Entropy-driven Knowledge Distillation with Mamba fused Frequency Cross-Attention |
Dev Rishi Verma, Dipankar Das, Deepak Ranjan Nayak, TAPAN K GANDHI |
| 1377 |
Causal Footprint Localization: Model-Internal Attribute Binding for Text-to-Image Diffusion Transformers |
Jihun Park, Heechul Jung |
| 1391 |
MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors |
Denis Fatykhoph, Timur Akhtyamov, Konstantin Pakulev, German Devchich, Gonzalo Ferrer |
| 1395 |
Where Does Binding Live? From UNet Cross-Attention Heads to the MM-DiT Text Stream |
Sangyeol Baek, Suan Lee |
| 1404 |
Spectral Cohesion Loss: Shaping Embedding Geometry via Differentiable Spectral Relaxation |
Ahmed Begga, Sebastiano Vascon, Francisco Escolano, Marcello Pelillo |
| 1417 |
DEQ-Stereo: Deep Equilibrium Video Stereo Matching via Adaptive Convergence |
Kiljoon Han, Kyumin Hwang, Wonhyeok Choi, Jeonghoon Kim, Sunghoon Im |
