iiinova — where your digital self keeps evolving

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Mingju Gao, Qingle Liu, Yuzhao Peng, Xinjie Lin, Ziming Qin, Zheng Jiang, Wenyi Li, Calvin Xiao, Youjie Zheng, Kaisen Yang, Qinhuai Na: World Models' Last Exam in Physics arxiv.org/abs/2610.08791 arxiv.org/pdf/2610.08791 arxiv.org/html/2610.08791

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Jiraphon Yenphraphai, Fang Li, Tianshuo Xu, Depu Meng, Quentin Herau, Yihan Hu, Raymond A. Yeh, Wei Zhan: Building Rome from a Single Image arxiv.org/abs/2610.08790 arxiv.org/pdf/2610.08790 arxiv.org/html/2610.08790

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Shiqi Li, Sean Cho, Yijie Li, Fengzhi Guo, Bowen Wen, Cheng Zhang: 4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction arxiv.org/abs/2610.08782 arxiv.org/pdf/2610.08782 arxiv.org/html/2610.08782

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Zhenghong Zhou, Zhe Lin, Jiebo Luo, Yuqian Zhou: ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing arxiv.org/abs/2610.08779 arxiv.org/pdf/2610.08779 arxiv.org/html/2610.08779

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Shangye Song, Dong Gong, Hong Jia, Yun Sing Koh, Xinyu Zhang: CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching arxiv.org/abs/2610.08777 arxiv.org/pdf/2610.08777 arxiv.org/html/2610.08777

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Liao Ma, Jiayi Song, Yunfeng Wu, Songhua Liu, Peilin Zhao: Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation arxiv.org/abs/2610.08772 arxiv.org/pdf/2610.08772 arxiv.org/html/2610.08772

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Mohammed Q. Alkhatib: Data Leakage in Patch-Based Hyperspectral Image Classification: Quantifying the Impact of Spatial Overlap arxiv.org/abs/2610.08770 arxiv.org/pdf/2610.08770 arxiv.org/html/2610.08770

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Iv\'an Verdugo Guerra, Ezequiel L\'opez Rubio, Jorge Garc\'ia Gonz\'alez: Post-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation Error arxiv.org/abs/2610.08756 arxiv.org/pdf/2610.08756 arxiv.org/html/2610.08756

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Zeyu Michael Li, William Xingxu Chen, Xiang Cheng: Co-Evolving Paths and Flows via Path-Flow Alignment arxiv.org/abs/2610.08717 arxiv.org/pdf/2610.08717 arxiv.org/html/2610.08717

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Hairong Yin, Huangying Zhan, Shin-Fang Chng, Yi Xu, Raymond A. Yeh: SpaTime: Streaming Vision-Language Models for Spatio-temporal Reasoning arxiv.org/abs/2610.08713 arxiv.org/pdf/2610.08713 arxiv.org/html/2610.08713

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Dicong Qiu, Zhiyuan Xu, Yaosheng Liu, Feng Han, Bo Ye: RenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital Twins arxiv.org/abs/2610.08684 arxiv.org/pdf/2610.08684 arxiv.org/html/2610.08684

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Yuhao Qin, Junbo Wang, Yuke Li, Yining Zhu: EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding arxiv.org/abs/2610.08674 arxiv.org/pdf/2610.08674 arxiv.org/html/2610.08674

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Sihun Cha, Hyeonseung Shin, Suah Yu, Junyong Noh: PDB: Point-Based Deformation Blending for Facial Animation Retargeting arxiv.org/abs/2610.08672 arxiv.org/pdf/2610.08672 arxiv.org/html/2610.08672

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Lichen Zhu, Yueqian Lin, Yiheng Wang, Hai "Helen" Li, Yiran Chen: Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction arxiv.org/abs/2610.08663 arxiv.org/pdf/2610.08663 arxiv.org/html/2610.08663

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Suxin Ji, Hungtao Wan, Mingjun Liu, An Zhang: Selective Transfer of RL Updates for Visual Reasoning arxiv.org/abs/2610.08659 arxiv.org/pdf/2610.08659 arxiv.org/html/2610.08659

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Lichen Zhu, Yiheng Wang, Yueqian Lin, Hai "Helen" Li, Yiran Chen: Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation arxiv.org/abs/2610.08649 arxiv.org/pdf/2610.08649 arxiv.org/html/2610.08649

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Jiahua Li, Zixu John, Tom Zhong, Fuping Wu, Tianhao Xu, Jianqing Zheng, Yuanhan Mo, Fei Shen: Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection arxiv.org/abs/2610.08639 arxiv.org/pdf/2610.08639 arxiv.org/html/2610.08639

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Samed Do\u{g}an, Nico Leuze, Alfred Sch\"ottl: LiDAR Resolution Recovery via Foundation-Model-Guided Diffusion arxiv.org/abs/2610.08620 arxiv.org/pdf/2610.08620 arxiv.org/html/2610.08620

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Anabik Pal, Ganesh Patidar, Bikash Santra: FedDermaSeg: Federated Learning for Dermatological Image Segmentation arxiv.org/abs/2610.08574 arxiv.org/pdf/2610.08574 arxiv.org/html/2610.08574

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Lei Yang, Boqi Li, Chunmian Lin, Li Wang, Ziying Song, Shaoqing Xu, Heye Huang, Haibao Yu, Chen Lv: Sparse2comm: Towards Robust Cooperative 3D Object Detection arxiv.org/abs/2610.08573 arxiv.org/pdf/2610.08573 arxiv.org/html/2610.08573

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Dan Ben-Ami, Kobi Cohen, Chaim Baskin: Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness arxiv.org/abs/2610.08560 arxiv.org/pdf/2610.08560 arxiv.org/html/2610.08560

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Dongchen Si, Di Wang, Mingzhen Xu, Jing Zhang, Bo Du, Liangpei Zhang: RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models arxiv.org/abs/2610.08539 arxiv.org/pdf/2610.08539 arxiv.org/html/2610.08539

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Yongsheng Luo, Wengan He, Yu Li, Rouying Wu, Wei Lv: Beyond Perturbation Magnitude: Direction-Dependent Responses in Multimodal Geometric Representations arxiv.org/abs/2610.08533 arxiv.org/pdf/2610.08533 arxiv.org/html/2610.08533

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Asim Khan, Samee Ullah Khan, Dwarikanath Mahapatra: MedCORE: Criteria-Grounded Clinical Reasoning for Interpretable Medical Image Diagnosis arxiv.org/abs/2610.08528 arxiv.org/pdf/2610.08528 arxiv.org/html/2610.08528

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Baizhigitova, Yu, Chen, Subhas, Chen, Wang, Nakamura, Lartey, Li, Yang: Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment arxiv.org/abs/2610.08482 arxiv.org/pdf/2610.08482 arxiv.org/html/2610.08482

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Ricardo Pizarro, Roberto Valle, Jos\'e M. Buenaposada, Luis M. Bergasa, Luis Baumela: HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data arxiv.org/abs/2610.08433 arxiv.org/pdf/2610.08433 arxiv.org/html/2610.08433

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Lach, Wysocki, Li, Azampour, Killeen, Ginzinger, Braun, Steininger, Deutschmann, Navab: Deformable CT-US Registration via Anatomy-Aware Implicit Neural Representations arxiv.org/abs/2610.08419 arxiv.org/pdf/2610.08419 arxiv.org/html/2610.08419

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Li, Yamauchi, Liu, Rao, Guo, Initiative, Initiative: From the Drosophila Visual Connectome to General-Purpose Computer Vision arxiv.org/abs/2610.08418 arxiv.org/pdf/2610.08418 arxiv.org/html/2610.08418

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Tianyi She, Jiawei Liu, Weifeng Liu, Hanqing Zhao, Weiming Zhang, Kejiang Chen: Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses arxiv.org/abs/2610.08417 arxiv.org/pdf/2610.08417 arxiv.org/html/2610.08417

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Zhen Yu, Wenyang Liu, Kejun Wu, Chengwang Xiao, Renjie Qiao, Chengtao Cai: Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT arxiv.org/abs/2610.08414 arxiv.org/pdf/2610.08414 arxiv.org/html/2610.08414

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Seulgi Kim, Zhixiong Zhang, Xinwei Zhang, Jie Ling, Ronn Shaw: GeoPID: Decomposing and Steering Visual Information in Vision-Language Models arxiv.org/abs/2610.08401 arxiv.org/pdf/2610.08401 arxiv.org/html/2610.08401

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Taojie Zhu, Jing Jin, Yuan Xia, Chenyang Ding, Qunshan He, Wanke Xia, Tao Sun, Yan Chen, Jian Wang, Jinjie Gu, Tao Feng: UP-MOPD: Update Projection in Multi-Teacher On-Policy Distillation arxiv.org/abs/2610.08398 arxiv.org/pdf/2610.08398 arxiv.org/html/2610.08398

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Jinshi Liu, Pan Liu, Lei He, Weichao Luo, Rui Qian: UniCounting: Instance-Aware Proposal Consolidation for Image-Query-Free Multi-Category Counting arxiv.org/abs/2610.08379 arxiv.org/pdf/2610.08379 arxiv.org/html/2610.08379

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Kaichun Yang, Jian Chen: A Stevens's Power Law Check-up of GPT-5.5's Image-Based Visualization Reading arxiv.org/abs/2610.08365 arxiv.org/pdf/2610.08365 arxiv.org/html/2610.08365

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Hyeongheon Cha, Young D. Kwon, Sung-Ju Lee: Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration arxiv.org/abs/2610.08358 arxiv.org/pdf/2610.08358 arxiv.org/html/2610.08358

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Beibei Lin, Tingting Chen, Xin Zhang, Wenhao Zhao, Dongjun Li, Zifeng Yuan: PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation arxiv.org/abs/2610.08346 arxiv.org/pdf/2610.08346 arxiv.org/html/2610.08346

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Yang, Li, Yang, Tan, Chen, Chen, Wang, Xu, Zhang: DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models arxiv.org/abs/2610.08341 arxiv.org/pdf/2610.08341 arxiv.org/html/2610.08341

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Hojun Lim, Hyeongseok Jeon, Donghyun Kim, Soonyoung Jung, Heecheol Yoo: Digital Twin-Driven Real2Sim2Real: Simulator-Conditioned Generation via Paired Driving-Scene Reconstruction arxiv.org/abs/2610.08339 arxiv.org/pdf/2610.08339 arxiv.org/html/2610.08339

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Heyam Bin Jahlan Areej Alhothali Abeer Alhothali: Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving arxiv.org/abs/2610.08331 arxiv.org/pdf/2610.08331 arxiv.org/html/2610.08331

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Nguyen, Ziabari, Alsahag: Catastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient Imbalance arxiv.org/abs/2610.08315 arxiv.org/pdf/2610.08315 arxiv.org/html/2610.08315

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Rainer Lienhart, Daniel Kienzle, Shin'ichi Satoh, Anastasiia Bilinska: Event Detection in Table Tennis Videos using 2D Keypoints arxiv.org/abs/2610.08286 arxiv.org/pdf/2610.08286 arxiv.org/html/2610.08286

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Tobias Hallmen, Robin-Nico Kampa, Elisabeth Andr\'e: Whose Face Is It Anyway? A Multi-Model Audit of Facial Affect Recognition on Children, and Why the Gap Is the Head, Not the Features arxiv.org/abs/2610.08279 arxiv.org/pdf/2610.08279 arxiv.org/html/2610.08279

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Nikita Alutis, Danila Evsyukov, Egor Chistov, Mikhail Voronin, Evgeney Bogatyrev, Dmitriy Vatolin: TSRN-RTVD: Real-Time Video Deblurring System arxiv.org/abs/2610.08230 arxiv.org/pdf/2610.08230 arxiv.org/html/2610.08230

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Osman Ali, Xiangjun Kong, Tibebe Yalew, Waiel Elmadih, Samanta Piano: RACE-FPP: A Robust AI-assisted Characterisation Enhancement for Fringe Projection Profilometry arxiv.org/abs/2610.08213 arxiv.org/pdf/2610.08213 arxiv.org/html/2610.08213

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Souptik Sen, Zahra Ahmadi: MacJEPA: Missingness-Robust Audio-Visual Recognition from Untrimmed Egocentric Videos arxiv.org/abs/2610.08192 arxiv.org/pdf/2610.08192 arxiv.org/html/2610.08192

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Xiangze Meng, Guangyu Li, Jing Li, Di Mei, Songchen Ma, Mingkun Xu, Rui Ma: PIE-PS: Photometric Stereo from Physical Irradiance Event Streams arxiv.org/abs/2610.08188 arxiv.org/pdf/2610.08188 arxiv.org/html/2610.08188

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Kaizhe Zhang, Yijie Zhou, Weizhan Zhang, Xuanyu Wang, Feng Lei, Sha Gong: View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing arxiv.org/abs/2610.08179 arxiv.org/pdf/2610.08179 arxiv.org/html/2610.08179

000

arXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 2h

Tobias Hallmen, Fabian Deuser, Robin-Nico Kampa, Norbert Oswald, Elisabeth Andr\'e: The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception arxiv.org/abs/2610.08162 arxiv.org/pdf/2610.08162 arxiv.org/html/2610.08162

000