{"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-instance-segmentation","name":"Video Instance Segmentation","slug":"video-instance-segmentation","description_markdown":"The goal of video instance segmentation is simultaneous detection, segmentation and tracking of instances in videos. In words, it is the first time that the image instance segmentation problem is extended to the video domain.\r\n\r\nTo facilitate research on this new task, a large-scale benchmark called YouTube-VIS, which consists of 2,883 high-resolution YouTube videos, a 40-category label set and 131k high-quality instance masks is built.","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":148,"papers_with_code":94,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":8,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","slug":"video-instance-segmentation-on-ovis-1","dataset":"OVIS validation","dataset_url":"/dataset/ovis","rows_in_archive":44,"metrics":["mask AP","AP50","AP75","APho","APmo","AR1","APso","AR10"],"first_row_in_archive_order":{"model":"DVIS-DAQ(VIT-L, Offline)","paper_title":"DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries","paper_url":"/paper/dvis-daq-improving-video-segmentation-via","paper_date":"2024-03-29","arxiv_id":"2404.00086","code_links":[{"title":"zhang-tao-whu/DVIS","url":"https://github.com/zhang-tao-whu/DVIS"},{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"},{"title":"skyworkai/daq-vs","url":"https://github.com/skyworkai/daq-vs"}],"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"]}}}},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","slug":"video-instance-segmentation-on-youtube-vis-1","dataset":"YouTube-VIS validation","dataset_url":"/dataset/youtubevis","rows_in_archive":44,"metrics":["mask AP","AP50","AP75","AR1","AR10"],"first_row_in_archive_order":{"model":"CAVIS(ViT-L, Online)","paper_title":"Context-Aware Video Instance Segmentation","paper_url":"/paper/context-aware-video-instance-segmentation","paper_date":"2024-07-03","arxiv_id":"2407.03010","code_links":[{"title":"Seung-Hun-Lee/CAVIS","url":"https://github.com/Seung-Hun-Lee/CAVIS"}],"syntology":null}},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-2","slug":"video-instance-segmentation-on-youtube-vis-2","dataset":"YouTube-VIS 2021","dataset_url":"/dataset/youtube-vis-2021-validation","rows_in_archive":26,"metrics":["mask AP","AP50","AP75","AR1","AR10"],"first_row_in_archive_order":{"model":"CAVIS(VIT-L, Offline)","paper_title":"Context-Aware Video Instance Segmentation","paper_url":"/paper/context-aware-video-instance-segmentation","paper_date":"2024-07-03","arxiv_id":"2407.03010","code_links":[{"title":"Seung-Hun-Lee/CAVIS","url":"https://github.com/Seung-Hun-Lee/CAVIS"}],"syntology":null}},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-3","slug":"video-instance-segmentation-on-youtube-vis-3","dataset":"Youtube-VIS 2022 Validation","dataset_url":"/dataset/youtube-vis-2022-validation","rows_in_archive":7,"metrics":["mAP_L","AP50_L","AP75_L","AR1_L","AR10_L"],"first_row_in_archive_order":{"model":"DVIS++(VIT-L)","paper_title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","paper_url":"/paper/dvis-improved-decoupled-framework-for","paper_date":"2023-12-20","arxiv_id":"2312.13305","code_links":[{"title":"zhang-tao-whu/DVIS_Plus","url":"https://github.com/zhang-tao-whu/DVIS_Plus"}],"syntology":null}},{"leaderboard":"/sota/video-instance-segmentation-on-bdd100k-val","slug":"video-instance-segmentation-on-bdd100k-val","dataset":"BDD100K val","dataset_url":"/dataset/bdd100k","rows_in_archive":6,"metrics":["mMOTSA"],"first_row_in_archive_order":{"model":"PCAN","paper_title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","paper_url":"/paper/prototypical-cross-attention-networks-for","paper_date":"2021-06-22","arxiv_id":"2106.11958","code_links":[{"title":"SysCV/pcan","url":"https://github.com/SysCV/pcan"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prototypical-cross-attention-networks-for#ran","syntology_url":"https://syntology.ai/paper/2106.11958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11958"}},"official":{"repos":["SysCV/pcan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-instance-segmentation-on-hq-ytvis","slug":"video-instance-segmentation-on-hq-ytvis","dataset":"HQ-YTVIS","dataset_url":"/dataset/hq-ytvis","rows_in_archive":4,"metrics":["Tube-Boundary AP"],"first_row_in_archive_order":{"model":"VMT (Swin-L)","paper_title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","paper_url":"/paper/video-mask-transfiner-for-high-quality-video","paper_date":"2022-07-28","arxiv_id":"2207.14012","code_links":[{"title":"SysCV/vmt","url":"https://github.com/SysCV/vmt"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-mask-transfiner-for-high-quality-video#ran","syntology_url":"https://syntology.ai/paper/2207.14012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14012"}},"official":null}}},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis","slug":"video-instance-segmentation-on-youtube-vis","dataset":"YouTube-VIS","dataset_url":"/dataset/youtubevis","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"Temporal ROI Align","paper_title":"Temporal RoI Align for Video Object Recognition","paper_url":"/paper/temporal-roi-align-for-video-object","paper_date":"2021-09-08","arxiv_id":"2109.03495","code_links":[{"title":"open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking"}],"syntology":null}},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-4","slug":"video-instance-segmentation-on-youtube-vis-4","dataset":"Youtube-VIS (trained with no video masks)","dataset_url":null,"rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"MaskFreeVIS","paper_title":"Mask-Free Video Instance Segmentation","paper_url":"/paper/mask-free-video-instance-segmentation","paper_date":"2023-03-28","arxiv_id":"2303.15904","code_links":[{"title":"syscv/maskfreevis","url":"https://github.com/syscv/maskfreevis"}],"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mask-free-video-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2303.15904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15904"}},"official":{"repos":["syscv/maskfreevis"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/youtubevis","name":"YouTube-VIS 2019","full_name":"","num_papers_in_archive":163},{"url":"/dataset/ovis","name":"OVIS","full_name":"Occluded Video Instance Segmentation","num_papers_in_archive":75},{"url":"/dataset/youtube-vis-2021-validation","name":"YouTube-VIS 2021","full_name":"Video Instance Segmentation on YouTube-VIS 2021 validation","num_papers_in_archive":52},{"url":"/dataset/uvo","name":"UVO","full_name":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","num_papers_in_archive":27},{"url":"/dataset/burst","name":"BURST","full_name":"","num_papers_in_archive":18},{"url":"/dataset/youtube-vis-2022-validation","name":"Youtube-VIS 2022 Validation","full_name":"","num_papers_in_archive":6},{"url":"/dataset/hq-ytvis","name":"HQ-YTVIS","full_name":"","num_papers_in_archive":5}],"subtasks":[],"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":2,"rows_per_page":100,"shown":100,"of":148,"of_with_code":94,"tagged_in_all":148,"counts":{"archive_papers_tagged":148,"with_a_code_link":94,"where_syntology_ran_a_sample":30,"not_listed_spam_title":0,"listed":148,"listed_where_code_ran":30,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":27,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":27,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/simple-online-and-realtime-tracking-with-a","slug":"simple-online-and-realtime-tracking-with-a","title":"Simple Online and Realtime Tracking with a Deep Association Metric","date":"2017-03-21","arxiv_id":"1703.07402","repositories_listed":75,"syntology":{"n":40,"n_ran":29,"n_constructed":0,"n_ran_checked":24,"n_instrument":5,"n_unverified":11,"n_honours":4,"n_violates":3,"n_no_contract":17,"n_pointer_only":9,"phrase":"29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 4 honoured, 3 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/simple-online-and-realtime-tracking-with-a#ran","syntology_url":"https://syntology.ai/paper/1703.07402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07402"}},"official":{"repos":["nwojke/deep_sort"],"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/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/video-instance-segmentation","slug":"video-instance-segmentation","title":"Video Instance Segmentation","date":"2019-05-12","arxiv_id":"1905.04804","repositories_listed":6,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1905.04804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04804"}},"official":{"repos":["Epiphqny/VisTR"],"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/queryinst-parallelly-supervised-mask-query","slug":"queryinst-parallelly-supervised-mask-query","title":"Instances as Queries","date":"2021-05-05","arxiv_id":"2105.01928","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/queryinst-parallelly-supervised-mask-query#ran","syntology_url":"https://syntology.ai/paper/2105.01928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01928"}},"official":{"repos":["hustvl/QueryInst"],"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/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/temporally-efficient-vision-transformer-for","slug":"temporally-efficient-vision-transformer-for","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","date":"2022-04-18","arxiv_id":"2204.08412","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/temporally-efficient-vision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2204.08412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08412"}},"official":{"repos":["hustvl/tevit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/spatio-temporal-prompting-network-for-robust-1","slug":"spatio-temporal-prompting-network-for-robust-1","title":"Spatio-temporal Prompting Network for Robust Video Feature Extraction","date":"2024-02-04","arxiv_id":"2402.02574","repositories_listed":2,"syntology":null},{"url":"/paper/minvis-a-minimal-video-instance-segmentation","slug":"minvis-a-minimal-video-instance-segmentation","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","date":"2022-08-03","arxiv_id":"2208.02245","repositories_listed":2,"syntology":null},{"url":"/paper/in-defense-of-online-models-for-video","slug":"in-defense-of-online-models-for-video","title":"In Defense of Online Models for Video Instance Segmentation","date":"2022-07-21","arxiv_id":"2207.10661","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/in-defense-of-online-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2207.10661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10661"}},"official":{"repos":["wjf5203/vnext"],"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/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/seqformer-a-frustratingly-simple-model-for","slug":"seqformer-a-frustratingly-simple-model-for","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","date":"2021-12-15","arxiv_id":"2112.08275","repositories_listed":2,"syntology":null},{"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/1st-place-solution-for-the-uvo-challenge-on-1","slug":"1st-place-solution-for-the-uvo-challenge-on-1","title":"UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution","date":"2021-10-22","arxiv_id":"2110.11661","repositories_listed":2,"syntology":null},{"url":"/paper/revisiting-contrastive-methods-for","slug":"revisiting-contrastive-methods-for","title":"Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations","date":"2021-06-10","arxiv_id":"2106.05967","repositories_listed":2,"syntology":null},{"url":"/paper/occluded-video-instance-segmentation","slug":"occluded-video-instance-segmentation","title":"Occluded Video Instance Segmentation: A Benchmark","date":"2021-02-02","arxiv_id":"2102.01558","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-video-instance-segmentation-with","slug":"end-to-end-video-instance-segmentation-with","title":"End-to-End Video Instance Segmentation with Transformers","date":"2020-11-30","arxiv_id":"2011.14503","repositories_listed":2,"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/syncvis-synchronized-video-instance","slug":"syncvis-synchronized-video-instance","title":"SyncVIS: Synchronized Video Instance Segmentation","date":"2024-12-01","arxiv_id":"2412.00882","repositories_listed":1,"syntology":null},{"url":"/paper/foundation-models-for-amodal-video-instance","slug":"foundation-models-for-amodal-video-instance","title":"Foundation Models for Amodal Video Instance Segmentation in Automated Driving","date":"2024-09-21","arxiv_id":"2409.14095","repositories_listed":1,"syntology":null},{"url":"/paper/mousesis-a-frames-and-events-dataset-for","slug":"mousesis-a-frames-and-events-dataset-for","title":"MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice","date":"2024-09-05","arxiv_id":"2409.03358","repositories_listed":1,"syntology":null},{"url":"/paper/eigen-cluster-vis-improving-weakly-supervised","slug":"eigen-cluster-vis-improving-weakly-supervised","title":"Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency","date":"2024-08-29","arxiv_id":"2408.16661","repositories_listed":1,"syntology":null},{"url":"/paper/unified-embedding-alignment-for-open","slug":"unified-embedding-alignment-for-open","title":"Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation","date":"2024-07-10","arxiv_id":"2407.07427","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-video-instance-segmentation","slug":"context-aware-video-instance-segmentation","title":"Context-Aware Video Instance Segmentation","date":"2024-07-03","arxiv_id":"2407.03010","repositories_listed":1,"syntology":null},{"url":"/paper/pm-vis-high-performance-video-instance","slug":"pm-vis-high-performance-video-instance","title":"PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation","date":"2024-06-28","arxiv_id":"2406.19665","repositories_listed":1,"syntology":null},{"url":"/paper/clip-vis-adapting-clip-for-open-vocabulary","slug":"clip-vis-adapting-clip-for-open-vocabulary","title":"CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation","date":"2024-03-19","arxiv_id":"2403.12455","repositories_listed":1,"syntology":null},{"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/tdvit-temporal-dilated-video-transformer-for","slug":"tdvit-temporal-dilated-video-transformer-for","title":"TDViT: Temporal Dilated Video Transformer for Dense Video Tasks","date":"2024-02-14","arxiv_id":"2402.09257","repositories_listed":1,"syntology":null},{"url":"/paper/instance-brownian-bridge-as-texts-for-open","slug":"instance-brownian-bridge-as-texts-for-open","title":"Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation","date":"2024-01-18","arxiv_id":"2401.09732","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/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"11 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; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}},"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tmt-vis-taxonomy-aware-multi-dataset-joint-1","slug":"tmt-vis-taxonomy-aware-multi-dataset-joint-1","title":"TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation","date":"2023-12-11","arxiv_id":"2312.06630","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tmt-vis-taxonomy-aware-multi-dataset-joint-1#ran","syntology_url":"https://syntology.ai/paper/2312.06630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06630"}},"official":{"repos":["rkzheng99/tmt-vis"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visage-video-instance-segmentation-with","slug":"visage-video-instance-segmentation-with","title":"VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement","date":"2023-12-08","arxiv_id":"2312.04885","repositories_listed":1,"syntology":null},{"url":"/paper/video-instance-matting","slug":"video-instance-matting","title":"Video Instance Matting","date":"2023-11-07","arxiv_id":"2311.04212","repositories_listed":1,"syntology":null},{"url":"/paper/tcovis-temporally-consistent-online-video","slug":"tcovis-temporally-consistent-online-video","title":"TCOVIS: Temporally Consistent Online Video Instance Segmentation","date":"2023-09-21","arxiv_id":"2309.11857","repositories_listed":1,"syntology":null},{"url":"/paper/1st-place-solution-for-the-5th-lsvos","slug":"1st-place-solution-for-the-5th-lsvos","title":"1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation","date":"2023-08-28","arxiv_id":"2308.14392","repositories_listed":1,"syntology":null},{"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/ctvis-consistent-training-for-online-video","slug":"ctvis-consistent-training-for-online-video","title":"CTVIS: Consistent Training for Online Video Instance Segmentation","date":"2023-07-24","arxiv_id":"2307.12616","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ctvis-consistent-training-for-online-video#ran","syntology_url":"https://syntology.ai/paper/2307.12616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12616"}},"official":{"repos":["kainingying/ctvis"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dq-det-learning-dynamic-query-combinations","slug":"dq-det-learning-dynamic-query-combinations","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","date":"2023-07-23","arxiv_id":"2307.12239","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dq-det-learning-dynamic-query-combinations#ran","syntology_url":"https://syntology.ai/paper/2307.12239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12239"}},"official":{"repos":["bytedance/dq-det"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"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/dvis-decoupled-video-instance-segmentation","slug":"dvis-decoupled-video-instance-segmentation","title":"DVIS: Decoupled Video Instance Segmentation Framework","date":"2023-06-06","arxiv_id":"2306.03413","repositories_listed":1,"syntology":null},{"url":"/paper/gratt-vis-gated-residual-attention-for-auto","slug":"gratt-vis-gated-residual-attention-for-auto","title":"GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation","date":"2023-05-26","arxiv_id":"2305.17096","repositories_listed":1,"syntology":null},{"url":"/paper/openvis-open-vocabulary-video-instance","slug":"openvis-open-vocabulary-video-instance","title":"OpenVIS: Open-vocabulary Video Instance Segmentation","date":"2023-05-26","arxiv_id":"2305.16835","repositories_listed":1,"syntology":null},{"url":"/paper/towards-open-vocabulary-video-instance","slug":"towards-open-vocabulary-video-instance","title":"Towards Open-Vocabulary Video Instance Segmentation","date":"2023-04-04","arxiv_id":"2304.01715","repositories_listed":1,"syntology":null},{"url":"/paper/video-instance-segmentation-in-an-open-world","slug":"video-instance-segmentation-in-an-open-world","title":"Video Instance Segmentation in an Open-World","date":"2023-04-03","arxiv_id":"2304.01200","repositories_listed":1,"syntology":null},{"url":"/paper/mask-free-video-instance-segmentation","slug":"mask-free-video-instance-segmentation","title":"Mask-Free Video Instance Segmentation","date":"2023-03-28","arxiv_id":"2303.15904","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mask-free-video-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2303.15904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15904"}},"official":{"repos":["syscv/maskfreevis"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boxvis-video-instance-segmentation-with-box","slug":"boxvis-video-instance-segmentation-with-box","title":"BoxVIS: Video Instance Segmentation with Box Annotations","date":"2023-03-26","arxiv_id":"2303.14618","repositories_listed":1,"syntology":null},{"url":"/paper/mdqe-mining-discriminative-query-embeddings","slug":"mdqe-mining-discriminative-query-embeddings","title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","date":"2023-03-25","arxiv_id":"2303.14395","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mdqe-mining-discriminative-query-embeddings#ran","syntology_url":"https://syntology.ai/paper/2303.14395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14395"}},"official":{"repos":["minghanli/mdqe_cvpr2023"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"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/universal-instance-perception-as-object","slug":"universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}},"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tarvis-a-unified-approach-for-target-based","slug":"tarvis-a-unified-approach-for-target-based","title":"TarViS: A Unified Approach for Target-based Video Segmentation","date":"2023-01-06","arxiv_id":"2301.02657","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tarvis-a-unified-approach-for-target-based#ran","syntology_url":"https://syntology.ai/paper/2301.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02657"}},"official":{"repos":["Ali2500/TarViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/context-aware-relative-object-queries-to","slug":"context-aware-relative-object-queries-to","title":"Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-generalized-framework-for-video-instance","slug":"a-generalized-framework-for-video-instance","title":"A Generalized Framework for Video Instance Segmentation","date":"2022-11-16","arxiv_id":"2211.08834","repositories_listed":1,"syntology":null},{"url":"/paper/robust-online-video-instance-segmentation","slug":"robust-online-video-instance-segmentation","title":"Robust Online Video Instance Segmentation with Track Queries","date":"2022-11-16","arxiv_id":"2211.09108","repositories_listed":1,"syntology":null},{"url":"/paper/two-level-temporal-relation-model-for-online","slug":"two-level-temporal-relation-model-for-online","title":"Two-Level Temporal Relation Model for Online Video Instance Segmentation","date":"2022-10-30","arxiv_id":"2210.16795","repositories_listed":1,"syntology":null},{"url":"/paper/tive-a-toolbox-for-identifying-video-instance","slug":"tive-a-toolbox-for-identifying-video-instance","title":"TIVE: A Toolbox for Identifying Video Instance Segmentation Errors","date":"2022-10-17","arxiv_id":"2210.08856","repositories_listed":1,"syntology":null},{"url":"/paper/instanceformer-an-online-video-instance","slug":"instanceformer-an-online-video-instance","title":"InstanceFormer: An Online Video Instance Segmentation Framework","date":"2022-08-22","arxiv_id":"2208.10547","repositories_listed":1,"syntology":null},{"url":"/paper/occlusion-aware-instance-segmentation-via","slug":"occlusion-aware-instance-segmentation-via","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","date":"2022-08-08","arxiv_id":"2208.04438","repositories_listed":1,"syntology":null},{"url":"/paper/instance-as-identity-a-generic-online","slug":"instance-as-identity-a-generic-online","title":"Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation","date":"2022-08-05","arxiv_id":"2208.03079","repositories_listed":1,"syntology":null},{"url":"/paper/video-mask-transfiner-for-high-quality-video","slug":"video-mask-transfiner-for-high-quality-video","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","date":"2022-07-28","arxiv_id":"2207.14012","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-mask-transfiner-for-high-quality-video#ran","syntology_url":"https://syntology.ai/paper/2207.14012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14012"}},"official":null}},{"url":"/paper/devis-making-deformable-transformers-work-for","slug":"devis-making-deformable-transformers-work-for","title":"DeVIS: Making Deformable Transformers Work for Video Instance Segmentation","date":"2022-07-22","arxiv_id":"2207.11103","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/devis-making-deformable-transformers-work-for#ran","syntology_url":"https://syntology.ai/paper/2207.11103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11103"}},"official":{"repos":["acaelles97/devis"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/video-sparse-transformer-with-attention","slug":"video-sparse-transformer-with-attention","title":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","date":"2022-06-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vita-video-instance-segmentation-via-object","slug":"vita-video-instance-segmentation-via-object","title":"VITA: Video Instance Segmentation via Object Token Association","date":"2022-06-09","arxiv_id":"2206.04403","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vita-video-instance-segmentation-via-object#ran","syntology_url":"https://syntology.ai/paper/2206.04403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04403"}},"official":{"repos":["sukjunhwang/vita"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-k-net-a-simple-strong-and-unified","slug":"video-k-net-a-simple-strong-and-unified","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","date":"2022-04-10","arxiv_id":"2204.04656","repositories_listed":1,"syntology":null},{"url":"/paper/video-instance-segmentation-via-multi-scale","slug":"video-instance-segmentation-via-multi-scale","title":"Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer","date":"2022-03-24","arxiv_id":"2203.13253","repositories_listed":1,"syntology":null},{"url":"/paper/deformable-vistr-spatio-temporal-deformable","slug":"deformable-vistr-spatio-temporal-deformable","title":"Deformable VisTR: Spatio temporal deformable attention for video instance segmentation","date":"2022-03-12","arxiv_id":"2203.06318","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-video-instance-segmentation-via-1","slug":"end-to-end-video-instance-segmentation-via-1","title":"End-to-end video instance segmentation via spatial-temporal graph neural networks","date":"2022-03-07","arxiv_id":"2203.03145","repositories_listed":1,"syntology":null},{"url":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}},"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-feature-refinement-for-instance","slug":"implicit-feature-refinement-for-instance","title":"Implicit Feature Refinement for Instance Segmentation","date":"2021-12-09","arxiv_id":"2112.04709","repositories_listed":1,"syntology":null},{"url":"/paper/visolo-grid-based-space-time-aggregation-for","slug":"visolo-grid-based-space-time-aggregation-for","title":"VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation","date":"2021-12-08","arxiv_id":"2112.04177","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/visolo-grid-based-space-time-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2112.04177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04177"}},"official":{"repos":["suhohan95/visolo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/object-propagation-via-inter-frame-attentions","slug":"object-propagation-via-inter-frame-attentions","title":"Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation","date":"2021-11-15","arxiv_id":"2111.07529","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-roi-align-for-video-object","slug":"temporal-roi-align-for-video-object","title":"Temporal RoI Align for Video Object Recognition","date":"2021-09-08","arxiv_id":"2109.03495","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-human-centric-segmentation-for","slug":"real-time-human-centric-segmentation-for","title":"Real-time Human-Centric Segmentation for Complex Video Scenes","date":"2021-08-16","arxiv_id":"2108.07199","repositories_listed":1,"syntology":null},{"url":"/paper/improving-video-instance-segmentation-via","slug":"improving-video-instance-segmentation-via","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","date":"2021-07-28","arxiv_id":"2107.13155","repositories_listed":1,"syntology":null},{"url":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_constructed":4,"n_ran_checked":4,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}},"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/false-negative-reduction-in-video-instance","slug":"false-negative-reduction-in-video-instance","title":"False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates","date":"2021-06-28","arxiv_id":"2106.14474","repositories_listed":1,"syntology":null},{"url":"/paper/prototypical-cross-attention-networks-for","slug":"prototypical-cross-attention-networks-for","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","date":"2021-06-22","arxiv_id":"2106.11958","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prototypical-cross-attention-networks-for#ran","syntology_url":"https://syntology.ai/paper/2106.11958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11958"}},"official":{"repos":["SysCV/pcan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tracking-instances-as-queries","slug":"tracking-instances-as-queries","title":"Tracking Instances as Queries","date":"2021-06-22","arxiv_id":"2106.11963","repositories_listed":1,"syntology":null},{"url":"/paper/msn-efficient-online-mask-selection-network","slug":"msn-efficient-online-mask-selection-network","title":"MSN: Efficient Online Mask Selection Network for Video Instance Segmentation","date":"2021-06-19","arxiv_id":"2106.10452","repositories_listed":1,"syntology":null},{"url":"/paper/video-instance-segmentation-using-inter-frame","slug":"video-instance-segmentation-using-inter-frame","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","date":"2021-06-07","arxiv_id":"2106.03299","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-instance-segmentation-using-inter-frame#ran","syntology_url":"https://syntology.ai/paper/2106.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03299"}},"official":{"repos":["sukjunhwang/IFC"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/crossover-learning-for-fast-online-video","slug":"crossover-learning-for-fast-online-video","title":"Crossover Learning for Fast Online Video Instance Segmentation","date":"2021-04-13","arxiv_id":"2104.05970","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-feature-calibration-and-temporal","slug":"spatial-feature-calibration-and-temporal","title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","date":"2021-04-06","arxiv_id":"2104.05606","repositories_listed":1,"syntology":null},{"url":"/paper/video-instance-segmentation-with-a-propose","slug":"video-instance-segmentation-with-a-propose","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","date":"2021-03-25","arxiv_id":"2103.13746","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/video-instance-segmentation-with-a-propose#ran","syntology_url":"https://syntology.ai/paper/2103.13746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13746"}},"official":{"repos":["dvlab-research/proposereduce"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sg-net-spatial-granularity-network-for-one","slug":"sg-net-spatial-granularity-network-for-one","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","date":"2021-03-18","arxiv_id":"2103.10284","repositories_listed":1,"syntology":null},{"url":"/paper/track-to-detect-and-segment-an-online-multi","slug":"track-to-detect-and-segment-an-online-multi","title":"Track to Detect and Segment: An Online Multi-Object Tracker","date":"2021-03-16","arxiv_id":"2103.08808","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/track-to-detect-and-segment-an-online-multi#ran","syntology_url":"https://syntology.ai/paper/2103.08808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.08808"}},"official":{"repos":["JialianW/TraDeS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-monocular-depth-in-dynamic-scenes","slug":"learning-monocular-depth-in-dynamic-scenes","title":"Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency","date":"2021-02-04","arxiv_id":"2102.02629","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-monocular-depth-in-dynamic-scenes#ran","syntology_url":"https://syntology.ai/paper/2102.02629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02629"}},"official":{"repos":["SeokjuLee/Insta-DM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-video-instance-segmentation-by","slug":"improving-video-instance-segmentation-by","title":"Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates","date":"2020-12-14","arxiv_id":"2012.07504","repositories_listed":1,"syntology":null},{"url":"/paper/compfeat-comprehensive-feature-aggregation","slug":"compfeat-comprehensive-feature-aggregation","title":"CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation","date":"2020-12-07","arxiv_id":"2012.03400","repositories_listed":1,"syntology":null},{"url":"/paper/sipmask-spatial-information-preservation-for","slug":"sipmask-spatial-information-preservation-for","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","date":"2020-07-29","arxiv_id":"2007.14772","repositories_listed":1,"syntology":null},{"url":"/paper/video-panoptic-segmentation-1","slug":"video-panoptic-segmentation-1","title":"Video Panoptic Segmentation","date":"2020-06-19","arxiv_id":"2006.11339","repositories_listed":1,"syntology":null},{"url":"/paper/stem-seg-spatio-temporal-embeddings-for","slug":"stem-seg-spatio-temporal-embeddings-for","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","date":"2020-03-18","arxiv_id":"2003.08429","repositories_listed":1,"syntology":null},{"url":"/paper/instance-wise-depth-and-motion-learning-from","slug":"instance-wise-depth-and-motion-learning-from","title":"Instance-wise Depth and Motion Learning from Monocular Videos","date":"2019-12-19","arxiv_id":"1912.09351","repositories_listed":1,"syntology":null},{"url":"/paper/learning-a-spatio-temporal-embedding-for-1","slug":"learning-a-spatio-temporal-embedding-for-1","title":"Learning a Spatio-Temporal Embedding for Video Instance Segmentation","date":"2019-12-19","arxiv_id":"1912.08969","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-video-object-segmentation-via","slug":"efficient-video-object-segmentation-via","title":"Efficient Video Object Segmentation via Network Modulation","date":"2018-02-04","arxiv_id":"1802.01218","repositories_listed":1,"syntology":null},{"url":null,"slug":"beyond-appearance-geometric-cues-for-robust","title":"Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation","date":"2025-07-08","arxiv_id":"2507.05948","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-video-scene-parsing","title":"A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects","date":"2025-06-16","arxiv_id":"2506.13552","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam2auto-auto-annotation-using-flash","title":"SAM2Auto: Auto Annotation Using FLASH","date":"2025-06-09","arxiv_id":"2506.07850","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowcut-unsupervised-video-instance","title":"FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching","date":"2025-05-19","arxiv_id":"2505.13174","repositories_listed":0,"syntology":null},{"url":null,"slug":"mosam-motion-guided-segment-anything-model","title":"MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection","date":"2025-04-30","arxiv_id":"2505.00739","repositories_listed":0,"syntology":null},{"url":null,"slug":"ripvis-rip-currents-video-instance","title":"RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety","date":"2025-04-01","arxiv_id":"2504.01128","repositories_listed":0,"syntology":null}],"syntology_records":30,"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":30,"papers_where_code_ran_first_page":"/task/video-instance-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":2,"url":"/task/video-instance-segmentation/papers/2","json":"/task/video-instance-segmentation/papers/2.json","rows":48},{"order":"ran","page":1,"of":1,"url":"/task/video-instance-segmentation/papers/ran/1","json":"/task/video-instance-segmentation/papers/ran/1.json","rows":30}],"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":"86d3c2755fa7d36222fb491e4ba3d27e362b48b9194e6f4234470c142b5f623c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}