Overview

Video object segmentation studies how to identify an object in a video and maintain an accurate pixel-level mask as it moves, changes appearance, disappears, or reappears. Common approaches propagate masks using temporal attention, object queries, optical flow, or memory banks; newer systems adapt promptable foundation models such as SAM2 and SAM3, sometimes guided by language, audio, or 3D geometry. Researchers evaluate these methods on benchmarks such as DAVIS, YouTube-VOS, MOSE, and long-video or referring-segmentation datasets, with growing attention to real-time, medical, low-light, and other specialized settings. A central challenge is balancing long-term identity and temporal stability against memory use and inference speed, especially when targets are absent or ambiguous and benchmarks may not fully capture those failures.

Latest papers

CardsList

120 papers9 papers in the last four weeks, down 36% on the four weeks before. 0.1% of all new papers.

  1. π4π^4: A Foundation Model for 4D Scene Geometry and Motion

    Nov 17, 2026Yifan Wang, Weiguang Zhao, Ni Yang +44D Scene UnderstandingMulti-View 3D Reconstruction

  2. PTQ4SAM3: Semantics-Preserving Post-Training Quantization for Segment Anything Model 3

    Nov 4, 2026Xi Xiao, Yunbei Zhang, Lin Zhao +7Post-Training QuantizationNeural Network Quantization

  3. Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation

    Nov 3, 2026Jun Huang, Junyang Zhang, Zijie Yue +3Video ReasoningVideo Object Segmentation

  4. DynOSeg: Dynamic Object Segmentation via Motion-Geometry Fusion

    Nov 3, 2026Xu Han, Yiduo Wang, Yiran Wang +1Motion SegmentationVideo Object Segmentation

  5. ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models

    Oct 24, 2026Xiaoang Zhang, Mert Kiray, Yordanka Velikova +2Motion Segmentation3D Foundation Models

  6. Lightweight Frame Compensation for Real-Time Polyp Segmentation under Frame Skipping

    Oct 22, 2026Weihao GaoPolyp SegmentationVideo Object Segmentation

  7. OccJEPA: Occlusion as Masking for Amodal Video Segmentation

    Oct 21, 2026Genpei Zhang, Runmin Jiang, Xingzu Zhan +3Amodal SegmentationVideo Object Segmentation

  8. Weakly Supervised Fish Segmentation through Point-Supervised Tracking and Motion-Informed Language

    Oct 21, 2026Vedanth Kallakuri, Katherine A. SkinnerImage SegmentationVideo Object Segmentation

  9. Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation

    Oct 18, 2026Junwei Wen, Deshui Miao, Guangming Lu +3Temporal Reasoning in VLMsVideo Object Segmentation

  10. ATLAS: Learning to Adapt LVLM Attention for Reasoning Video Segmentation

    Oct 17, 2026Hamidreza Dastmalchi, Ali Cheraghian, Aijun An +2Video Object SegmentationReferring Video Object Segmentation

  11. OLiVES: An Outdoor Low-Light Video Benchmark for Enhancement and Segmentation

    Oct 14, 2026Yini Li, Joanne Lin, David Blackham +2Low-Light Image EnhancementVideo Object Segmentation

  12. SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking

    Oct 14, 2026Tomáš Čížek, Matej Straka, Illia Volkov +5Visual Object TrackingVideo Object Segmentation

  13. When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation

    Oct 11, 2026Valay Bundele, Susmit Agrawal, Mehran Hosseinzadeh +2Visual Object TrackingVideo Object Segmentation

  14. When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation

    Oct 2, 2026Jihwan Hong, Woohyeon Park, Jaeik Kim +1Video Object SegmentationVisual Object Tracking

  15. FiVOS: A Fish Segmentation Algorithm Based on Interactive Video Object Segmentation and Filter Enhancement

    Oct 1, 2026Yuqing Duan, Song Zhang, Shili Zhao +2Video Object Segmentation

  16. Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation

    Oct 1, 2026Arash Rocky, Q. M. Jonathan WuVideo Object SegmentationInstance Segmentation

  17. Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object Segmentation

    Sep 30, 2026Abu Hanif Muhammad Syarubany, Jaehyun Jang, Siwoo Lim +2Video Object SegmentationReferring Video Object Segmentation

  18. Learning to Reason with Persistent Object States for Video Instance Segmentation

    Sep 28, 2026Yongxue Xu, Boxue Yang, Ziqian Liu +3Video Object SegmentationInstance Segmentation

  19. LVMT: Video Mask Transformer for Long-term Video Segmentation

    Sep 28, 2026Narges Norouzi, Niccolò Cavagnero, Idil Esen Zulfikar +3Truncated Backpropagation Through TimeVideo Object Segmentation

  20. MoVISA: Multi-Token Reasoning for Video Object Segmentation

    Sep 24, 2026Ruining Zhao, Ho Kei Cheng, Alexander G SchwingVideo Object SegmentationReferring Video Object Segmentation

  21. SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation

    Sep 22, 2026Zhengtong Zhu, Jiaqing Fan, Hanwen Qian +1Video Object Segmentation

  22. TEDi: Temporal Memory-Enhanced and Denoising Transformer for Surgical Instrument Segmentation

    Sep 15, 2026Jiahong Yuan, Weiming Mi, Tao Zhang +1Video Object SegmentationMedical Image Segmentation

  23. DynEoMT: Learning Object Dynamicity from Online Segmentation Queries

    Sep 13, 2026Calvin Galagain, Martyna Poreba, François GouletteVideo Object SegmentationVideo Instance Segmentation

  24. Segment Any Motion with Radar: Robust Multimodal Moving-Object Segmentation and Tracking

    Sep 8, 2026Jue Wang, Xuan Wang, Hao Zhou +6Camera-Radar FusionVideo Object Segmentation

  25. WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos

    Sep 8, 2026Giseong Hwang, Minjae Jo, Yeonghyeon Park +9Video Object SegmentationWeakly Supervised Learning

  26. Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation

    Sep 5, 2026Chang Liu, Henghui Ding, Lingyi Hong +36Video Object SegmentationReferring Video Object Segmentation