{"url":"/task/video-segmentation","name":"Video Segmentation","slug":"video-segmentation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":388,"papers_with_code":160,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/video-segmentation-on-segtrack-v2","slug":"video-segmentation-on-segtrack-v2","dataset":"SegTrack v2","dataset_url":"/dataset/segtrack-v2-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GDHF","paper_title":"Geodesic Distance Histogram Feature for Video Segmentation","paper_url":"/paper/geodesic-distance-histogram-feature-for-video","paper_date":"2017-03-31","arxiv_id":"1704.00077","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/segtrack-v2-1","name":"SegTrack-v2","full_name":"","num_papers_in_archive":107},{"url":"/dataset/dynamic-replica","name":"Dynamic Replica","full_name":"","num_papers_in_archive":10},{"url":"/dataset/egoprocel","name":"EgoProceL","full_name":"","num_papers_in_archive":9},{"url":"/dataset/tiktok-dataset","name":"TikTok Dataset","full_name":"Learning High Fidelity Depths of Dressed Humans  by Watching Social Media Dance Videos","num_papers_in_archive":8},{"url":"/dataset/mm-or","name":"MM-OR","full_name":"","num_papers_in_archive":3},{"url":"/dataset/moma-lrg","name":"MOMA-LRG","full_name":"Multi-Object Multi-Actor activity parsing with Language-Refined Graphs","num_papers_in_archive":3},{"url":"/dataset/petraw","name":"PETRAW","full_name":"PEg TRAnsfer Workflow recognition by different modalities","num_papers_in_archive":3},{"url":"/dataset/pp-humanseg14k","name":"PP-HumanSeg14K","full_name":"","num_papers_in_archive":3},{"url":"/dataset/conferencevideosegmentationdataset","name":"ConferenceVideoSegmentationDataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lsdbench","name":"LSDBench","full_name":"Long-video Sampling Dilemma Benchmark","num_papers_in_archive":1},{"url":"/dataset/infinity-spills-basic-dataset","name":"Infinity Spills Basic Dataset","full_name":"Infinity Spills Basic Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/camera-shot-boundary-detection","name":"Camera shot boundary detection"},{"url":"/task/open-vocabulary-video-segmentation","name":"Open-Vocabulary Video Segmentation"},{"url":"/task/open-world-video-segmentation","name":"Open-World Video Segmentation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":160,"tagged_in_all":388,"items":[{"url":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","repositories_listed":11,"syntology":{"n":49,"n_ran":28,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/one-shot-video-object-segmentation","title":"One-Shot Video Object Segmentation","date":"2016-11-16","arxiv_id":"1611.05198","repositories_listed":8,"syntology":null},{"url":"/paper/mask2former-for-video-instance-segmentation","title":"Mask2Former for Video Instance Segmentation","date":"2021-12-20","arxiv_id":"2112.10764","repositories_listed":6,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/graphecho-graph-driven-unsupervised-domain","title":"GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation","date":"2023-09-20","arxiv_id":"2309.11145","repositories_listed":4,"syntology":null},{"url":"/paper/ccnet-criss-cross-attention-for-semantic","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","date":"2018-11-28","arxiv_id":"1811.11721","repositories_listed":4,"syntology":{"n":14,"n_ran":9,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/youtube-vos-sequence-to-sequence-video-object","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","date":"2018-09-03","arxiv_id":"1809.00461","repositories_listed":4,"syntology":null},{"url":"/paper/dvis-daq-improving-video-segmentation-via","title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","date":"2024-03-29","arxiv_id":"2404.00086","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/epic-kitchens-visor-benchmark-video","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","date":"2022-09-26","arxiv_id":"2209.13064","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/physarum-powered-differentiable-linear","title":"Physarum Powered Differentiable Linear Programming Layers and Applications","date":"2020-04-30","arxiv_id":"2004.14539","repositories_listed":3,"syntology":null},{"url":"/paper/video-object-segmentation-with-re","title":"Video Object Segmentation with Re-identification","date":"2017-08-01","arxiv_id":"1708.00197","repositories_listed":3,"syntology":null},{"url":"/paper/towards-underwater-camouflaged-object","title":"Underwater Camouflaged Object Tracking Meets Vision-Language SAM2","date":"2024-09-25","arxiv_id":"2409.16902","repositories_listed":2,"syntology":null},{"url":"/paper/visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/pvuw-2024-challenge-on-complex-video","title":"PVUW 2024 Challenge on Complex Video Understanding: Methods and Results","date":"2024-06-24","arxiv_id":"2406.17005","repositories_listed":2,"syntology":null},{"url":"/paper/maxtron-mask-transformer-with-trajectory","title":"A Simple Video Segmenter by Tracking Objects Along Axial Trajectories","date":"2023-11-30","arxiv_id":"2311.18537","repositories_listed":2,"syntology":null},{"url":"/paper/xmem-production-level-video-segmentation-from","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","date":"2023-07-29","arxiv_id":"2307.15958","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/video-swinunet-spatio-temporal-deep-learning","title":"Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance Segmentation","date":"2023-02-22","arxiv_id":"2302.11325","repositories_listed":2,"syntology":null},{"url":"/paper/mlseg-image-and-video-segmentation-as-multi","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","date":"2022-03-08","arxiv_id":"2203.04187","repositories_listed":2,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/d2conv3d-dynamic-dilated-convolutions-for","title":"D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos","date":"2021-11-15","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/auxadapt-stable-and-efficient-test-time","title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","date":"2021-10-24","arxiv_id":"2110.12369","repositories_listed":2,"syntology":null},{"url":"/paper/generic-event-boundary-detection-a-benchmark","title":"Generic Event Boundary Detection: A Benchmark for Event Segmentation","date":"2021-01-26","arxiv_id":"2101.10511","repositories_listed":2,"syntology":null},{"url":"/paper/tspnet-hierarchical-feature-learning-via","title":"TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation","date":"2020-10-12","arxiv_id":"2010.05468","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/temporal-aggregate-representations-for-long","title":"Temporal Aggregate Representations for Long-Range Video Understanding","date":"2020-06-01","arxiv_id":"2006.00830","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-the-evaluation-of-video-summaries","title":"Rethinking the Evaluation of Video Summaries","date":"2019-03-27","arxiv_id":"1903.11328","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/decoupled-seg-tokens-make-stronger-reasoning","title":"Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder","date":"2025-06-28","arxiv_id":"2506.22880","repositories_listed":1,"syntology":null},{"url":"/paper/sam-i2v-upgrading-sam-to-support-promptable-1","title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","date":"2025-06-02","arxiv_id":"2506.01304","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/omnifall-a-unified-staged-to-wild-benchmark","title":"OmniFall: A Unified Staged-to-Wild Benchmark for Human Fall Detection","date":"2025-05-26","arxiv_id":"2505.19889","repositories_listed":1,"syntology":null},{"url":"/paper/thinkvideo-high-quality-reasoning-video","title":"ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts","date":"2025-05-24","arxiv_id":"2505.18561","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-the-power-of-sam-2-for-few-shot","title":"Unlocking the Power of SAM 2 for Few-Shot Segmentation","date":"2025-05-20","arxiv_id":"2505.14100","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/tempura-temporal-event-masked-prediction-and","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action","date":"2025-05-02","arxiv_id":"2505.01583","repositories_listed":1,"syntology":null},{"url":"/paper/dc-sam-in-context-segment-anything-in-images","title":"DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency","date":"2025-04-16","arxiv_id":"2504.12080","repositories_listed":1,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}