{"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/papers/2","list_of":"/task/video-instance-segmentation","task":"Video Instance Segmentation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,148],"of":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":28,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":28,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-instance-segmentation","prev":"/task/video-instance-segmentation","next":null,"papers":[{"url":null,"slug":"a-temporal-modeling-framework-for-video-pre","title":"A Temporal Modeling Framework for Video Pre-Training on Video Instance Segmentation","date":"2025-03-22","arxiv_id":"2503.17672","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-motion-expression-video","title":"Decoupled Motion Expression Video Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"minimizing-labeled-maximizing-unlabeled-an","title":"Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-real-time-open-vocabulary-video","title":"Towards Real-Time Open-Vocabulary Video Instance Segmentation","date":"2024-12-05","arxiv_id":"2412.04434","repositories_listed":0,"syntology":null},{"url":null,"slug":"a2vis-amodal-aware-approach-to-video-instance","title":"A2VIS: Amodal-Aware Approach to Video Instance Segmentation","date":"2024-12-02","arxiv_id":"2412.01147","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-video-instance-segmentation","title":"Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps","date":"2024-11-26","arxiv_id":"2411.17425","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdi-paste-synthetic-dynamic-instance-copy","title":"SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation","date":"2024-10-16","arxiv_id":"2410.13565","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-deep-learning-models-robust-to-partial","title":"Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?","date":"2024-09-16","arxiv_id":"2409.10775","repositories_listed":0,"syntology":null},{"url":null,"slug":"lsvos-challenge-3rd-place-report-sam2-and","title":"LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS","date":"2024-08-20","arxiv_id":"2408.10469","repositories_listed":0,"syntology":null},{"url":null,"slug":"2nd-place-solution-for-mevis-track-in-cvpr","title":"2nd Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","date":"2024-06-20","arxiv_id":"2406.13939","repositories_listed":0,"syntology":null},{"url":null,"slug":"uvis-unsupervised-video-instance-segmentation","title":"UVIS: Unsupervised Video Instance Segmentation","date":"2024-06-11","arxiv_id":"2406.06908","repositories_listed":0,"syntology":null},{"url":null,"slug":"1st-place-winner-of-the-2024-pixel-level","title":"1st Place Winner of the 2024 Pixel-level Video Understanding in the Wild (CVPR'24 PVUW) Challenge in Video Panoptic Segmentation and Best Long Video Consistency of Video Semantic Segmentation","date":"2024-06-08","arxiv_id":"2406.05352","repositories_listed":0,"syntology":null},{"url":null,"slug":"pm-vis-high-performance-box-supervised-video","title":"PM-VIS: High-Performance Box-Supervised Video Instance Segmentation","date":"2024-04-22","arxiv_id":"2404.13863","repositories_listed":0,"syntology":null},{"url":null,"slug":"ow-viscap-open-world-video-instance","title":"OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning","date":"2024-04-04","arxiv_id":"2404.03657","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-point-supervision-worth-in-video","title":"What is Point Supervision Worth in Video Instance Segmentation?","date":"2024-04-01","arxiv_id":"2404.01990","repositories_listed":0,"syntology":null},{"url":null,"slug":"cml-mots-collaborative-multi-task-learning","title":"CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","date":"2023-11-02","arxiv_id":"2311.00987","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-techniques-for-video-instance","title":"Deep Learning Techniques for Video Instance Segmentation: A Survey","date":"2023-10-19","arxiv_id":"2310.12393","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"1st-place-solution-for-cvpr2023-burst-long","title":"1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges","date":"2023-08-08","arxiv_id":"2308.04598","repositories_listed":0,"syntology":null},{"url":null,"slug":"3rd-place-solution-for-pvuw-challenge-2023","title":"3rd Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation","date":"2023-06-11","arxiv_id":"2306.06753","repositories_listed":0,"syntology":null},{"url":"/paper/refinevis-video-instance-segmentation-with","slug":"refinevis-video-instance-segmentation-with","title":"RefineVIS: Video Instance Segmentation with Temporal Attention Refinement","date":"2023-06-07","arxiv_id":"2306.04774","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobileinst-video-instance-segmentation-on-the","title":"MobileInst: Video Instance Segmentation on the Mobile","date":"2023-03-30","arxiv_id":"2303.17594","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-to-online-knowledge-distillation-for","title":"Offline-to-Online Knowledge Distillation for Video Instance Segmentation","date":"2023-02-15","arxiv_id":"2302.07516","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximal-cliques-on-multi-frame-proposal-graph","title":"Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation","date":"2023-01-29","arxiv_id":"2301.12352","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-video-instance-segmentation","title":"Towards Robust Video Instance Segmentation with Temporal-Aware Transformer","date":"2023-01-20","arxiv_id":"2301.09416","repositories_listed":0,"syntology":null},{"url":null,"slug":"inspro-propagating-instance-query-and","title":"InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation","date":"2023-01-05","arxiv_id":"2301.01882","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-segmentation-with-audio-context","title":"Object Segmentation with Audio Context","date":"2023-01-04","arxiv_id":"2301.10295","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-runner-up-solution-for-youtube-vis-long","title":"The Runner-up Solution for YouTube-VIS Long Video Challenge 2022","date":"2022-11-18","arxiv_id":"2211.09973","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-and-learning-static-vs-dynamic","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","date":"2022-11-03","arxiv_id":"2211.01783","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-video-instance-segmentation-via-robust","title":"Online Video Instance Segmentation via Robust Context Fusion","date":"2022-07-12","arxiv_id":"2207.05580","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistent-video-instance-segmentation-with","title":"Consistent Video Instance Segmentation with Inter-Frame Recurrent Attention","date":"2022-06-14","arxiv_id":"2206.07011","repositories_listed":0,"syntology":null},{"url":null,"slug":"tag-based-attention-guided-bottom-up-approach","title":"Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation","date":"2022-04-22","arxiv_id":"2204.10765","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-than-few-self-shot-video-instance","title":"Less than Few: Self-Shot Video Instance Segmentation","date":"2022-04-19","arxiv_id":"2204.08874","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-instance-segmentation-and-tracking-via","title":"Human Instance Segmentation and Tracking via Data Association and Single-stage Detector","date":"2022-03-31","arxiv_id":"2203.16966","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-stage-video-instance-segmentation-from","title":"One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out","date":"2022-03-12","arxiv_id":"2203.06421","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-video-instance-segmentation-via","title":"Efficient Video Instance Segmentation via Tracklet Query and Proposal","date":"2022-03-03","arxiv_id":"2203.01853","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-video-segmentation-models-with-per","title":"Efficient Video Segmentation Models with Per-frame Inference","date":"2022-02-24","arxiv_id":"2202.12427","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-matching-perspective-with","title":"A Graph Matching Perspective With Transformers on Video Instance Segmentation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-instance-aware-temporal-fusion-for","title":"Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation","date":"2021-12-03","arxiv_id":"2112.01695","repositories_listed":0,"syntology":null},{"url":null,"slug":"occluded-video-instance-segmentation-dataset","title":"Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge","date":"2021-11-15","arxiv_id":"2111.07950","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-instance-segmentation-by-instance-flow","title":"Video Instance Segmentation by Instance Flow Assembly","date":"2021-10-20","arxiv_id":"2110.10599","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-guided-segmentation-framework-for","title":"Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation","date":"2021-06-07","arxiv_id":"2106.03330","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-based-energy","title":"A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline","date":"2021-04-09","arxiv_id":"2104.04443","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-video-instance-segmentation-with","title":"Learning Video Instance Segmentation with Recurrent Graph Neural Networks","date":"2020-12-07","arxiv_id":"2012.03911","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-instance-segmentation-tracking-with-a","title":"Video Instance Segmentation Tracking With a Modified VAE Architecture","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classifying-segmenting-and-tracking-object","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","date":"2019-12-10","arxiv_id":"1912.04573","repositories_listed":0,"syntology":null}],"record_sha256":"50322b7a4a229ee0a113554a0ec32e9087de867d40636bee47c86e4e7bc5f4ed","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}