{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":388,"of_with_code":160,"tagged_in_all":388,"counts":{"archive_papers_tagged":388,"with_a_code_link":160,"where_syntology_ran_a_sample":46,"not_listed_spam_title":0,"listed":388,"listed_where_code_ran":46,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":37,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":37,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/2408-00714","slug":"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":40,"n_constructed":9,"n_ran_checked":29,"n_instrument":11,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":27,"n_pointer_only":8,"phrase":"40 ran (of which 9 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 0 violated, 27 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/2408-00714#ran","syntology_url":"https://syntology.ai/paper/2408.00714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00714"}},"official":{"repos":["facebookresearch/sam2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/one-shot-video-object-segmentation","slug":"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","slug":"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":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mask2former-for-video-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2112.10764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10764"}},"official":{"repos":["facebookresearch/Mask2Former"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/graphecho-graph-driven-unsupervised-domain","slug":"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","slug":"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":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ccnet-criss-cross-attention-for-semantic#ran","syntology_url":"https://syntology.ai/paper/1811.11721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11721"}},"official":{"repos":["speedinghzl/CCNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/youtube-vos-sequence-to-sequence-video-object","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dvis-daq-improving-video-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2404.00086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00086"}},"official":{"repos":["skyworkai/daq-vs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/epic-kitchens-visor-benchmark-video","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/epic-kitchens-visor-benchmark-video#ran","syntology_url":"https://syntology.ai/paper/2209.13064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13064"}},"official":{"repos":["epic-kitchens/visor-hos","epic-kitchens/visor-vos","epic-kitchens/visor-wdtcf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/physarum-powered-differentiable-linear","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}},"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pvuw-2024-challenge-on-complex-video","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/xmem-production-level-video-segmentation-from#ran","syntology_url":"https://syntology.ai/paper/2307.15958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15958"}},"official":{"repos":["max810/XMem2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/video-swinunet-spatio-temporal-deep-learning","slug":"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","slug":"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":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mlseg-image-and-video-segmentation-as-multi#ran","syntology_url":"https://syntology.ai/paper/2203.04187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04187"}},"official":{"repos":["openseg-group/mlseg","openseg-group/rankseg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/d2conv3d-dynamic-dilated-convolutions-for","slug":"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","slug":"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","slug":"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","slug":"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_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tspnet-hierarchical-feature-learning-via#ran","syntology_url":"https://syntology.ai/paper/2010.05468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05468"}},"official":{"repos":["verashira/TSPNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/temporal-aggregate-representations-for-long","slug":"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","slug":"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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-the-evaluation-of-video-summaries#ran","syntology_url":"https://syntology.ai/paper/1903.11328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.11328"}},"official":null}},{"url":"/paper/decoupled-seg-tokens-make-stronger-reasoning","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/sam-i2v-upgrading-sam-to-support-promptable-1#ran","syntology_url":"https://syntology.ai/paper/2506.01304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01304"}},"official":{"repos":["showlab/sam-i2v"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/omnifall-a-unified-staged-to-wild-benchmark","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unlocking-the-power-of-sam-2-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2505.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14100"}},"official":{"repos":["sam1224/fssam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/tempura-temporal-event-masked-prediction-and","slug":"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","slug":"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},{"url":"/paper/glus-global-local-reasoning-unified-into-a","slug":"glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","arxiv_id":"2504.07962","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}},"official":null}},{"url":"/paper/the-1st-solution-for-4th-pvuw-mevis-challenge","slug":"the-1st-solution-for-4th-pvuw-mevis-challenge","title":"The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation","date":"2025-04-07","arxiv_id":"2504.05178","repositories_listed":1,"syntology":null},{"url":"/paper/medsam2-segment-anything-in-3d-medical-images","slug":"medsam2-segment-anything-in-3d-medical-images","title":"MedSAM2: Segment Anything in 3D Medical Images and Videos","date":"2025-04-04","arxiv_id":"2504.03600","repositories_listed":1,"syntology":null},{"url":"/paper/camsam2-segment-anything-accurately-in","slug":"camsam2-segment-anything-accurately-in","title":"CamSAM2: Segment Anything Accurately in Camouflaged Videos","date":"2025-03-25","arxiv_id":"2503.19730","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-annotation-burden-exploiting-image","slug":"reducing-annotation-burden-exploiting-image","title":"Reducing Annotation Burden: Exploiting Image Knowledge for Few-Shot Medical Video Object Segmentation via Spatiotemporal Consistency Relearning","date":"2025-03-19","arxiv_id":"2503.14958","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-vision-language-models-for-open","slug":"leveraging-vision-language-models-for-open","title":"Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking","date":"2025-03-18","arxiv_id":"2503.16538","repositories_listed":1,"syntology":null},{"url":"/paper/bst-badminton-stroke-type-transformer-for","slug":"bst-badminton-stroke-type-transformer-for","title":"BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports","date":"2025-02-28","arxiv_id":"2502.21085","repositories_listed":1,"syntology":null},{"url":"/paper/sasvi-segment-any-surgical-video","slug":"sasvi-segment-any-surgical-video","title":"SASVi - Segment Any Surgical Video","date":"2025-02-12","arxiv_id":"2502.09653","repositories_listed":1,"syntology":null},{"url":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","slug":"mpg-sam-2-adapting-sam-2-with-mask-priors-and","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","date":"2025-01-23","arxiv_id":"2501.13667","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}},"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-frame-extraction-a-novel-approach","slug":"efficient-frame-extraction-a-novel-approach","title":"Efficient Frame Extraction: A Novel Approach Through Frame Similarity and Surgical Tool Tracking for Video Segmentation","date":"2025-01-19","arxiv_id":"2501.11153","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-structure-informed-machinery-part","slug":"few-shot-structure-informed-machinery-part","title":"Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural Networks","date":"2025-01-17","arxiv_id":"2501.10080","repositories_listed":1,"syntology":null},{"url":"/paper/edgetam-on-device-track-anything-model","slug":"edgetam-on-device-track-anything-model","title":"EdgeTAM: On-Device Track Anything Model","date":"2025-01-13","arxiv_id":"2501.07256","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":2,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/edgetam-on-device-track-anything-model#ran","syntology_url":"https://syntology.ai/paper/2501.07256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07256"}},"official":{"repos":["facebookresearch/edgetam"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/vidchain-chain-of-tasks-with-metric-based","slug":"vidchain-chain-of-tasks-with-metric-based","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning","date":"2025-01-12","arxiv_id":"2501.06761","repositories_listed":1,"syntology":null},{"url":"/paper/sa2va-marrying-sam2-with-llava-for-dense","slug":"sa2va-marrying-sam2-with-llava-for-dense","title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","date":"2025-01-07","arxiv_id":"2501.04001","repositories_listed":1,"syntology":null},{"url":"/paper/segment-anything-model-for-zero-shot-single","slug":"segment-anything-model-for-zero-shot-single","title":"Segment Anything Model for Zero-shot Single Particle Tracking in Liquid Phase Transmission Electron Microscopy","date":"2025-01-06","arxiv_id":"2501.03153","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-hybrid-segmentation-assistant-with","slug":"hyperseg-hybrid-segmentation-assistant-with","title":"HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/when-sam2-meets-video-shadow-and-mirror","slug":"when-sam2-meets-video-shadow-and-mirror","title":"When SAM2 Meets Video Shadow and Mirror Detection","date":"2024-12-26","arxiv_id":"2412.19293","repositories_listed":1,"syntology":null},{"url":"/paper/instructseg-unifying-instructed-visual","slug":"instructseg-unifying-instructed-visual","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","date":"2024-12-18","arxiv_id":"2412.14006","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/instructseg-unifying-instructed-visual#ran","syntology_url":"https://syntology.ai/paper/2412.14006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14006"}},"official":{"repos":["congvvc/instructseg"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/holmes-vau-towards-long-term-video-anomaly","slug":"holmes-vau-towards-long-term-video-anomaly","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","date":"2024-12-09","arxiv_id":"2412.06171","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/holmes-vau-towards-long-term-video-anomaly#ran","syntology_url":"https://syntology.ai/paper/2412.06171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06171"}},"official":{"repos":["pipixin321/holmesvau"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/inspiring-the-next-generation-of-segment","slug":"inspiring-the-next-generation-of-segment","title":"Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes","date":"2024-12-02","arxiv_id":"2412.01240","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-video-object-segmentation","slug":"multi-granularity-video-object-segmentation","title":"Multi-Granularity Video Object Segmentation","date":"2024-12-02","arxiv_id":"2412.01471","repositories_listed":1,"syntology":null},{"url":"/paper/det-sam2-technical-report-on-the-self","slug":"det-sam2-technical-report-on-the-self","title":"Det-SAM2:Technical Report on the Self-Prompting Segmentation Framework Based on Segment Anything Model 2","date":"2024-11-28","arxiv_id":"2411.18977","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-track-anything","slug":"efficient-track-anything","title":"Efficient Track Anything","date":"2024-11-28","arxiv_id":"2411.18933","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-track-anything#ran","syntology_url":"https://syntology.ai/paper/2411.18933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18933"}},"official":null}},{"url":"/paper/samwise-infusing-wisdom-in-sam2-for-text","slug":"samwise-infusing-wisdom-in-sam2-for-text","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","date":"2024-11-26","arxiv_id":"2411.17646","repositories_listed":1,"syntology":null},{"url":"/paper/mseg-vcuq-multimodal-segmentation-with","slug":"mseg-vcuq-multimodal-segmentation-with","title":"MSEG-VCUQ: Multimodal SEGmentation with Enhanced Vision Foundation Models, Convolutional Neural Networks, and Uncertainty Quantification for High-Speed Video Phase Detection Data","date":"2024-11-12","arxiv_id":"2411.07463","repositories_listed":1,"syntology":null},{"url":"/paper/smite-segment-me-in-time","slug":"smite-segment-me-in-time","title":"SMITE: Segment Me In TimE","date":"2024-10-24","arxiv_id":"2410.18538","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/smite-segment-me-in-time#ran","syntology_url":"https://syntology.ai/paper/2410.18538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18538"}},"official":{"repos":["alimohammadiamirhossein/smite"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/videosam-a-large-vision-foundation-model-for","slug":"videosam-a-large-vision-foundation-model-for","title":"VideoSAM: A Large Vision Foundation Model for High-Speed Video Segmentation","date":"2024-10-22","arxiv_id":"2410.21304","repositories_listed":1,"syntology":null},{"url":"/paper/sam2long-enhancing-sam-2-for-long-video","slug":"sam2long-enhancing-sam-2-for-long-video","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","date":"2024-10-21","arxiv_id":"2410.16268","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sam2long-enhancing-sam-2-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2410.16268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16268"}},"official":{"repos":["mark12ding/sam2long"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-prompting-polyp-segmentation-in","slug":"self-prompting-polyp-segmentation-in","title":"Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model","date":"2024-09-14","arxiv_id":"2409.09484","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-potential-of-sam2-for","slug":"unleashing-the-potential-of-sam2-for","title":"Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey","date":"2024-08-23","arxiv_id":"2408.12889","repositories_listed":1,"syntology":null},{"url":"/paper/surgical-sam-2-real-time-segment-anything-in","slug":"surgical-sam-2-real-time-segment-anything-in","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","date":"2024-08-15","arxiv_id":"2408.07931","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/surgical-sam-2-real-time-segment-anything-in#ran","syntology_url":"https://syntology.ai/paper/2408.07931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07931"}},"official":{"repos":["jinlab-imvr/surgical-sam-2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03286","slug":"2408-03286","title":"Biomedical SAM 2: Segment Anything in Biomedical Images and Videos","date":"2024-08-06","arxiv_id":"2408.03286","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-03286#ran","syntology_url":"https://syntology.ai/paper/2408.03286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03286"}},"official":{"repos":["ZhilingYan/Biomedical-SAM-2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03322","slug":"2408-03322","title":"Segment Anything in Medical Images and Videos: Benchmark and Deployment","date":"2024-08-06","arxiv_id":"2408.03322","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01648","slug":"2408-01648","title":"Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2","date":"2024-08-03","arxiv_id":"2408.01648","repositories_listed":1,"syntology":null},{"url":"/paper/villa-video-reasoning-segmentation-with-large","slug":"villa-video-reasoning-segmentation-with-large","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","date":"2024-07-18","arxiv_id":"2407.14500","repositories_listed":1,"syntology":null},{"url":"/paper/general-and-task-oriented-video-segmentation","slug":"general-and-task-oriented-video-segmentation","title":"General and Task-Oriented Video Segmentation","date":"2024-07-09","arxiv_id":"2407.06540","repositories_listed":1,"syntology":null},{"url":"/paper/uni-dvps-unified-model-for-depth-aware-video","slug":"uni-dvps-unified-model-for-depth-aware-video","title":"Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation","date":"2024-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sali-short-term-alignment-and-long-term-1","slug":"sali-short-term-alignment-and-long-term-1","title":"SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation","date":"2024-06-19","arxiv_id":"2406.13532","repositories_listed":1,"syntology":null},{"url":"/paper/1st-place-solution-for-mevis-track-in-cvpr","slug":"1st-place-solution-for-mevis-track-in-cvpr","title":"1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","date":"2024-06-11","arxiv_id":"2406.07043","repositories_listed":1,"syntology":null},{"url":"/paper/arcjetcv-an-open-source-software-to-analyze","slug":"arcjetcv-an-open-source-software-to-analyze","title":"arcjetCV: an open-source software to analyze material ablation","date":"2024-04-17","arxiv_id":"2404.11492","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-static-and-hierarchical-motion","slug":"decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","arxiv_id":"2404.03645","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/decoupling-static-and-hierarchical-motion#ran","syntology_url":"https://syntology.ai/paper/2404.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03645"}},"official":{"repos":["heshuting555/dshmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}},"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/univs-unified-and-universal-video","slug":"univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","arxiv_id":"2402.18115","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/univs-unified-and-universal-video#ran","syntology_url":"https://syntology.ai/paper/2402.18115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18115"}},"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/polypnextlstm-a-lightweight-and-fast-polyp","slug":"polypnextlstm-a-lightweight-and-fast-polyp","title":"PolypNextLSTM: A lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM","date":"2024-02-18","arxiv_id":"2402.11585","repositories_listed":1,"syntology":null},{"url":"/paper/we-re-not-using-videos-effectively-an-updated","slug":"we-re-not-using-videos-effectively-an-updated","title":"We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline","date":"2024-02-01","arxiv_id":"2402.00868","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/we-re-not-using-videos-effectively-an-updated#ran","syntology_url":"https://syntology.ai/paper/2402.00868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00868"}},"official":{"repos":["simarkareer/unifiedvideoda"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rap-sam-towards-real-time-all-purpose-segment","slug":"rap-sam-towards-real-time-all-purpose-segment","title":"RAP-SAM: Towards Real-Time All-Purpose Segment Anything","date":"2024-01-18","arxiv_id":"2401.10228","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rap-sam-towards-real-time-all-purpose-segment#ran","syntology_url":"https://syntology.ai/paper/2401.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10228"}},"official":{"repos":["xushilin1/rap-sam"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infer-from-what-you-have-seen-before","slug":"infer-from-what-you-have-seen-before","title":"Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/memsam-taming-segment-anything-model-for","slug":"memsam-taming-segment-anything-model-for","title":"MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dvis-improved-decoupled-framework-for","slug":"dvis-improved-decoupled-framework-for","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","date":"2023-12-20","arxiv_id":"2312.13305","repositories_listed":1,"syntology":null},{"url":"/paper/autovisual-fusion-suite-a-comprehensive","slug":"autovisual-fusion-suite-a-comprehensive","title":"AutoVisual Fusion Suite: A Comprehensive Evaluation of Image Segmentation and Voice Conversion Tools on HuggingFace Platform","date":"2023-12-17","arxiv_id":"2401.05379","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-graph-pattern-understanding-for","slug":"hierarchical-graph-pattern-understanding-for","title":"Hierarchical Graph Pattern Understanding for Zero-Shot VOS","date":"2023-12-15","arxiv_id":"2312.09525","repositories_listed":1,"syntology":null},{"url":"/paper/betrayed-by-attention-a-simple-yet-effective","slug":"betrayed-by-attention-a-simple-yet-effective","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","date":"2023-11-29","arxiv_id":"2311.17893","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/betrayed-by-attention-a-simple-yet-effective#ran","syntology_url":"https://syntology.ai/paper/2311.17893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17893"}},"official":{"repos":["shvdiwnkozbw/ssl-uvos"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/datasetnerf-efficient-3d-aware-data-factory","slug":"datasetnerf-efficient-3d-aware-data-factory","title":"DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields","date":"2023-11-18","arxiv_id":"2311.12063","repositories_listed":1,"syntology":null},{"url":"/paper/concatenated-masked-autoencoders-as-spatial","slug":"concatenated-masked-autoencoders-as-spatial","title":"Concatenated Masked Autoencoders as Spatial-Temporal Learner","date":"2023-11-02","arxiv_id":"2311.00961","repositories_listed":1,"syntology":null},{"url":"/paper/medivista-sam-zero-shot-medical-video","slug":"medivista-sam-zero-shot-medical-video","title":"MediViSTA: Medical Video Segmentation via Temporal Fusion SAM Adaptation for Echocardiography","date":"2023-09-24","arxiv_id":"2309.13539","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-amodal-video-segmentation-from","slug":"rethinking-amodal-video-segmentation-from","title":"Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation","date":"2023-09-23","arxiv_id":"2309.13248","repositories_listed":1,"syntology":null},{"url":"/paper/moda-leveraging-motion-priors-from-videos-for","slug":"moda-leveraging-motion-priors-from-videos-for","title":"MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation","date":"2023-09-21","arxiv_id":"2309.11711","repositories_listed":1,"syntology":null},{"url":"/paper/panovos-bridging-non-panoramic-and-panoramic","slug":"panovos-bridging-non-panoramic-and-panoramic","title":"PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation","date":"2023-09-21","arxiv_id":"2309.12303","repositories_listed":1,"syntology":null},{"url":"/paper/gl-fusion-global-local-fusion-network-for","slug":"gl-fusion-global-local-fusion-network-for","title":"GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation","date":"2023-09-20","arxiv_id":"2309.11144","repositories_listed":1,"syntology":null},{"url":"/paper/catr-combinatorial-dependence-audio-queried","slug":"catr-combinatorial-dependence-audio-queried","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","date":"2023-09-18","arxiv_id":"2309.09709","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/catr-combinatorial-dependence-audio-queried#ran","syntology_url":"https://syntology.ai/paper/2309.09709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09709"}},"official":{"repos":["aspirinone/catr.github.io"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}},"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/videocutler-surprisingly-simple-unsupervised","slug":"videocutler-surprisingly-simple-unsupervised","title":"VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation","date":"2023-08-28","arxiv_id":"2308.14710","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videocutler-surprisingly-simple-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2308.14710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14710"}},"official":{"repos":["facebookresearch/cutler"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robotic-scene-segmentation-with-memory","slug":"robotic-scene-segmentation-with-memory","title":"Robotic Scene Segmentation with Memory Network for Runtime Surgical Context Inference","date":"2023-08-24","arxiv_id":"2308.12789","repositories_listed":1,"syntology":null},{"url":"/paper/mevis-a-large-scale-benchmark-for-video","slug":"mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","arxiv_id":"2308.08544","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mevis-a-large-scale-benchmark-for-video#ran","syntology_url":"https://syntology.ai/paper/2308.08544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08544"}},"official":{"repos":["henghuiding/MeViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/predicting-masked-tokens-in-stochastic","slug":"predicting-masked-tokens-in-stochastic","title":"Stochastic positional embeddings improve masked image modeling","date":"2023-07-31","arxiv_id":"2308.00566","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/predicting-masked-tokens-in-stochastic#ran","syntology_url":"https://syntology.ai/paper/2308.00566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00566"}},"official":{"repos":["amirbar/stop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multiscale-memory-comparator-transformer-for","slug":"multiscale-memory-comparator-transformer-for","title":"Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation","date":"2023-07-15","arxiv_id":"2307.07812","repositories_listed":1,"syntology":null},{"url":"/paper/rectifying-noisy-labels-with-sequential-prior","slug":"rectifying-noisy-labels-with-sequential-prior","title":"Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation","date":"2023-07-12","arxiv_id":"2307.05898","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rectifying-noisy-labels-with-sequential-prior#ran","syntology_url":"https://syntology.ai/paper/2307.05898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05898"}},"official":{"repos":["beileicui/ms-tfal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/segment-anything-meets-point-tracking","slug":"segment-anything-meets-point-tracking","title":"Segment Anything Meets Point Tracking","date":"2023-07-03","arxiv_id":"2307.01197","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/segment-anything-meets-point-tracking#ran","syntology_url":"https://syntology.ai/paper/2307.01197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01197"}},"official":{"repos":["syscv/sam-pt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tube-link-a-flexible-cross-tube-baseline-for","slug":"tube-link-a-flexible-cross-tube-baseline-for","title":"Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation","date":"2023-03-22","arxiv_id":"2303.12782","repositories_listed":1,"syntology":null},{"url":"/paper/unified-mask-embedding-and-correspondence","slug":"unified-mask-embedding-and-correspondence","title":"Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation","date":"2023-03-17","arxiv_id":"2303.10100","repositories_listed":1,"syntology":null}],"syntology_records":35,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":46,"papers_where_code_ran_first_page":"/task/video-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/video-segmentation/papers/2","json":"/task/video-segmentation/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/video-segmentation/papers/3","json":"/task/video-segmentation/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/video-segmentation/papers/4","json":"/task/video-segmentation/papers/4.json","rows":88},{"order":"ran","page":1,"of":1,"url":"/task/video-segmentation/papers/ran/1","json":"/task/video-segmentation/papers/ran/1.json","rows":46}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"3ef18476e1dbf37b0c3a68d91f99b1232b1df24d93408f04f91a06ac76cf5a7c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}