{"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":"/dataset/youtubevis","name":"YouTube-VIS 2019","full_name":null,"description_markdown":"YouTubeVIS is a new dataset tailored for tasks like simultaneous detection, segmentation and tracking of object instances in videos and is collected based on the current largest video object segmentation dataset YouTubeVOS.\r\n\r\nSource: [YouTubeVIS](https://github.com/youtubevos/MaskTrackRCNN)","description_withheld":null,"homepage":"https://github.com/youtubevos/MaskTrackRCNN","introduced_date":"2019-05-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/video-instance-segmentation","title":"Video Instance Segmentation","first_author":"Linjie Yang","url":null},"license":{"name":"CC BY 4.0","url":"https://youtube-vos.org/dataset/term/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Video Instance Segmentation","url":"/task/video-instance-segmentation","datasets_with_task":"/datasets/task/video-instance-segmentation"}],"languages":[],"variants":["YouTube-VIS","YouTube-VIS validation","YouTube-VIS 2019"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/youtube_vis","frameworks":["tf","jax"]},{"repo":"https://github.com/youtubevos/MaskTrackRCNN","url":"https://github.com/youtubevos/MaskTrackRCNN","frameworks":["pytorch"]}],"num_papers_in_archive":163,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset_variant":"YouTube-VIS validation","rows":44,"metrics":["mask AP","AP50","AP75","AR1","AR10"],"first_row_in_archive_order":{"model":"CAVIS(ViT-L, Online)","paper":"/paper/context-aware-video-instance-segmentation","metrics":{"AP50":"89.3","AP75":"76.2","AR1":"58.3","AR10":"73.6","mask AP":"68.9"},"code_links":[{"title":"Seung-Hun-Lee/CAVIS","url":"https://github.com/Seung-Hun-Lee/CAVIS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis","task":"Video Instance Segmentation","dataset_variant":"YouTube-VIS","rows":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"Temporal ROI Align","paper":"/paper/temporal-roi-align-for-video-object","metrics":{"mask AP":"38"},"code_links":[{"title":"open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":34,"of":34,"counts":{"papers_with_a_benchmark_row":34,"with_a_code_link":31,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":34,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":2,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":14,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/novis-a-case-for-end-to-end-near-online-video","slug":"novis-a-case-for-end-to-end-near-online-video","title":"NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation","date":"2023-08-29","arxiv_id":"2308.15266","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":11,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stc-spatio-temporal-contrastive-learning-for","slug":"stc-spatio-temporal-contrastive-learning-for","title":"STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation","date":"2022-02-08","arxiv_id":"2202.03747","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/1st-place-solution-for-youtubevos-challenge","slug":"1st-place-solution-for-youtubevos-challenge","title":"1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation","date":"2021-06-12","arxiv_id":"2106.06649","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-instance-segmentation","slug":"video-instance-segmentation","title":"Video Instance Segmentation","date":"2019-05-12","arxiv_id":"1905.04804","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":75,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":29,"samples_constructed":0,"samples_ran_checked":24,"samples_ran_instrument_failed":5,"samples_unverified":11,"pointer_only_for_licence":9,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":14,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/novis-a-case-for-end-to-end-near-online-video","slug":"novis-a-case-for-end-to-end-near-online-video","title":"NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation","date":"2023-08-29","arxiv_id":"2308.15266","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":11,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stc-spatio-temporal-contrastive-learning-for","slug":"stc-spatio-temporal-contrastive-learning-for","title":"STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation","date":"2022-02-08","arxiv_id":"2202.03747","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/1st-place-solution-for-youtubevos-challenge","slug":"1st-place-solution-for-youtubevos-challenge","title":"1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation","date":"2021-06-12","arxiv_id":"2106.06649","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/video-instance-segmentation","slug":"video-instance-segmentation","title":"Video Instance Segmentation","date":"2019-05-12","arxiv_id":"1905.04804","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":75,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":29,"samples_constructed":0,"samples_ran_checked":24,"samples_ran_instrument_failed":5,"samples_unverified":11,"pointer_only_for_licence":9,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/dataset/youtubevis/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/youtubevis/papers/ran/1","json":"/dataset/youtubevis/papers/ran/1.json","rows":11}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":11,"samples_harvested":121,"samples_ran":89,"samples_constructed":6,"samples_ran_checked":61,"samples_ran_instrument_failed":28,"samples_unverified":32,"pointer_only_for_licence":41,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":11,"papers_with_a_run_with_no_instrument_failure":9,"papers_where_every_run_was_an_instrument_failure":2,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"82a1e4983f7d035ee79d7adf27cec24c01036d855d3ea149be28b327c8ff0b78","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}