{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/video-instance-segmentation","title":"Video Instance Segmentation","arxiv_id":"1905.04804","date":"2019-05-12","proceeding":"ICCV 2019 10","authors":["Linjie Yang","Yuchen Fan","Ning Xu"],"abstract":"In this paper we present a new computer vision task, named video instance segmentation. The goal of this new task 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. To facilitate research on this new task, we propose a large-scale benchmark called YouTube-VIS, which consists of 2883 high-resolution YouTube videos, a 40-category label set and 131k high-quality instance masks. In addition, we propose a novel algorithm called MaskTrack R-CNN for this task. Our new method introduces a new tracking branch to Mask R-CNN to jointly perform the detection, segmentation and tracking tasks simultaneously. Finally, we evaluate the proposed method and several strong baselines on our new dataset. Experimental results clearly demonstrate the advantages of the proposed algorithm and reveal insight for future improvement. We believe the video instance segmentation task will motivate the community along the line of research for video understanding.","url_abs":"https://arxiv.org/abs/1905.04804v4","url_pdf":"https://arxiv.org/pdf/1905.04804v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"video-instance-segmentation","repo_url":"https://github.com/Epiphqny/VisTR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"video-instance-segmentation","repo_url":"https://github.com/youtubevos/MaskTrackRCNN","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"video-instance-segmentation","repo_url":"https://github.com/JonathonLuiten/HOTA-metrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"video-instance-segmentation","repo_url":"https://github.com/JonathonLuiten/TrackEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"video-instance-segmentation","repo_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"video-instance-segmentation","repo_url":"https://github.com/bbednarski9/MaskTrackRCNN_DeepSort","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"youtubevis","name":"YouTube-VIS 2019","full_name":""},{"slug":"youtube-vis-2021-validation","name":"YouTube-VIS 2021","full_name":"Video Instance Segmentation on YouTube-VIS 2021 validation"},{"slug":"youtube-vis-2022-validation","name":"Youtube-VIS 2022 Validation","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"MaskTrack R-CNN (ResNet-50, single-scale training and test)","rank_in_archive_order":41,"of":44,"metrics":{"AP50":"51.1","AP75":"32.6","AR1":"31","AR10":"35.5","mask AP":"30.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.04804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04804"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bbednarski9/MaskTrackRCNN_DeepSort","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JonathonLuiten/HOTA-metrics","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Epiphqny/VisTR","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youtubevos/MaskTrackRCNN","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JonathonLuiten/TrackEval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"listed":{"samples":10,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"0ce058e665602da2","entry":"init_config","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/utils.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ce058e665602da2"}},{"code_sha256_prefix":"1bc1d9b92dfee6c1","entry":"single_frame","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1bc1d9b92dfee6c1"}},{"code_sha256_prefix":"5ef3f617efb9ddc4","entry":"update_config","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/utils.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ef3f617efb9ddc4"}},{"code_sha256_prefix":"e4a9dbe96206f1e6","entry":"create_coco_mask","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/baselines/baseline_utils.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/baselines/baseline_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a9dbe96206f1e6"}},{"code_sha256_prefix":"06d2be4ac9d0e95b","entry":"geometric_mean","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/plotting.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/plotting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06d2be4ac9d0e95b"}},{"code_sha256_prefix":"00c662d6d9709fe4","entry":"jaccard","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/plotting.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/plotting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00c662d6d9709fe4"}},{"code_sha256_prefix":"e9f7b2829ca9731b","entry":"load_multiple_tracker_summaries","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/plotting.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/plotting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9f7b2829ca9731b"}},{"code_sha256_prefix":"3aceddbf375bf009","entry":"load_seq","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/baselines/baseline_utils.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/baselines/baseline_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3aceddbf375bf009"}},{"code_sha256_prefix":"407ecabd804b59d8","entry":"threshold","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/baselines/baseline_utils.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/baselines/baseline_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"407ecabd804b59d8"}},{"code_sha256_prefix":"df1bd31f4da1bed6","entry":"time","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/_timing.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/_timing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df1bd31f4da1bed6"}},{"code_sha256_prefix":"9792bf1150d36891","entry":"validate_metrics_list","repo":"TranThienDat-Nguyen/VisionEvaluation","repo_kind":"listed","path":"trackeval/utils.py","file_url":"https://github.com/TranThienDat-Nguyen/VisionEvaluation/blob/HEAD/trackeval/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9792bf1150d36891"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}