{"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/do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","arxiv_id":"2107.02156","date":"2021-07-05","proceeding":"NeurIPS 2021 12","authors":["Zhongdao Wang","Hengshuang Zhao","Ya-Li Li","Shengjin Wang","Philip H. S. Torr","Luca Bertinetto"],"abstract":"Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of different experimental setups. As a consequence, the literature has fragmented too, and now novel approaches proposed by the community are usually specialised to fit only one specific setup. To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. UniTrack consists of a single and task-agnostic appearance model, which can be learned in a supervised or self-supervised fashion, and multiple ``heads'' that address individual tasks and do not require training. We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered. The framework also allows us to analyse appearance models obtained with the most recent self-supervised methods, thus extending their evaluation and comparison to a larger variety of important problems.","url_abs":"https://arxiv.org/abs/2107.02156v2","url_pdf":"https://arxiv.org/pdf/2107.02156v2.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":"do-different-tracking-tasks-require-different","repo_url":"https://github.com/Zhongdao/UniTrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multi-object-tracking-and-segmentation","task_name":"Multi-Object Tracking and Segmentation"},{"task_slug":"multiple-people-tracking","task_name":"Multiple People Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"online-multi-object-tracking","task_name":"Online Multi-Object Tracking"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"pose-prediction","task_name":"Pose Prediction"},{"task_slug":"pose-tracking","task_name":"Pose Tracking"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-mot16","task":"Multi-Object Tracking","dataset":"MOT16","model":"UniTrack","rank_in_archive_order":6,"of":24,"metrics":{"IDF1":"71.8","IDs":"683","MOTA":"74.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mots20","task":"Multi-Object Tracking","dataset":"MOTS20","model":"UniTrack","rank_in_archive_order":2,"of":6,"metrics":{"IDF1":"67.2","IDs":"622","sMOTSA":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-j-hmdb","task":"Pose Estimation","dataset":"J-HMDB","model":"UniTrack_i18","rank_in_archive_order":5,"of":5,"metrics":{"Mean PCK@0.1":"58.3","Mean PCK@0.2":"80.5"},"uses_additional_data":false},{"leaderboard":"/sota/pose-tracking-on-posetrack2018","task":"Pose Tracking","dataset":"PoseTrack2018","model":"UniTrack","rank_in_archive_order":2,"of":5,"metrics":{"IDF1":"73.2","IDs":"6760","MOTA":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"UniTrack","rank_in_archive_order":42,"of":44,"metrics":{"mask AP":"30.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017","task":"Video Object Segmentation","dataset":"DAVIS 2017","model":"UniTrack","rank_in_archive_order":4,"of":5,"metrics":{"mIoU":"58.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-2015","task":"Visual Object Tracking","dataset":"OTB-2015","model":"UniTrack_DCF","rank_in_archive_order":16,"of":18,"metrics":{"AUC":"0.618"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}},"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/Zhongdao/UniTrack","reach":null}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":11},"by_repo_kind":{"official":{"samples":17,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"6bed795c8790b42f","entry":"From3D","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"6bed795c8790b42f"}},{"code_sha256_prefix":"6cb64253bc2483ab","entry":"HighResolutionModule","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"6cb64253bc2483ab"}},{"code_sha256_prefix":"24f302b7add67f84","entry":"RandomFeatGenerator","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24f302b7add67f84"}},{"code_sha256_prefix":"5fb6217486f7e99c","entry":"ResNet","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fb6217486f7e99c"}},{"code_sha256_prefix":"8a5d9f9460c91bb5","entry":"_resnet","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a5d9f9460c91bb5"}},{"code_sha256_prefix":"93ff6b09d3e38b8e","entry":"dets2obs","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"demo/mot_demo.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/demo/mot_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93ff6b09d3e38b8e"}},{"code_sha256_prefix":"fe69a6b9983c5ce3","entry":"HighResolutionNet","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"fe69a6b9983c5ce3"}},{"code_sha256_prefix":"ec2a972e12e2c2f6","entry":"get_cls_net","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"ec2a972e12e2c2f6"}},{"code_sha256_prefix":"bb753455f7400311","entry":"load_tc_model","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"bb753455f7400311"}},{"code_sha256_prefix":"407da3ab43d8ba3f","entry":"load_uvc_model","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"407da3ab43d8ba3f"}},{"code_sha256_prefix":"d3b2fda956486d2c","entry":"make_encoder","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"d3b2fda956486d2c"}},{"code_sha256_prefix":"c0367497ab1f7faa","entry":"partial_load","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"c0367497ab1f7faa"}},{"code_sha256_prefix":"33b995998b62c580","entry":"resnet101","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"33b995998b62c580"}},{"code_sha256_prefix":"08e568179967e865","entry":"resnet18","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"08e568179967e865"}},{"code_sha256_prefix":"92b061ec78263602","entry":"resnet50","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"92b061ec78263602"}},{"code_sha256_prefix":"bf216e79a1ef8b76","entry":"resnext101_32x8d","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"bf216e79a1ef8b76"}},{"code_sha256_prefix":"8cc2e400c38e8730","entry":"resnext50_32x4d","repo":"Zhongdao/UniTrack","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Zhongdao/UniTrack/blob/HEAD/model/model.py","link_basis":"first_harvest_node","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":"8cc2e400c38e8730"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}