{"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/fast-online-object-tracking-and-segmentation","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","arxiv_id":"1812.05050","date":"2018-12-12","proceeding":"CVPR 2019 6","authors":["Qiang Wang","Li Zhang","Luca Bertinetto","Weiming Hu","Philip H. S. Torr"],"abstract":"In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask.","url_abs":"https://arxiv.org/abs/1812.05050v2","url_pdf":"https://arxiv.org/pdf/1812.05050v2.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":"fast-online-object-tracking-and-segmentation","repo_url":"https://github.com/ezelikman/anonymal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fast-online-object-tracking-and-segmentation","repo_url":"https://github.com/foolwood/SiamMask","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fast-online-object-tracking-and-segmentation","repo_url":"https://github.com/shallowtoil/DROL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"real-time-visual-tracking","task_name":"Real-Time Visual Tracking"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object 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":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"SiamMask","rank_in_archive_order":70,"of":78,"metrics":{"F-measure (Decay)":"2.1","F-measure (Mean)":"67.8","F-measure (Recall)":"79.8","J&F":"69.75","Jaccard (Decay)":"3.0","Jaccard (Mean)":"71.7","Jaccard (Recall)":"86.8"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"SiamMask","rank_in_archive_order":58,"of":59,"metrics":{"F-measure (Decay)":"22.4","F-measure (Mean)":"45.8","F-measure (Recall)":"45.3","J&F":"43.2","Jaccard (Decay)":"21.9","Jaccard (Mean)":"40.6","Jaccard (Recall)":"44.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"SiamMask","rank_in_archive_order":76,"of":81,"metrics":{"F-measure (Decay)":"20.9","F-measure (Mean)":"58.5","F-measure (Recall)":"67.5","J&F":"56.4","Jaccard (Decay)":"19.3","Jaccard (Mean)":"54.3","Jaccard (Recall)":"62.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"SiamMask","rank_in_archive_order":22,"of":43,"metrics":{"AUC":"35.14","Precision":"46.49"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-vot201718","task":"Visual Object Tracking","dataset":"VOT2017/18","model":"SiamMask","rank_in_archive_order":8,"of":15,"metrics":{"Expected Average Overlap (EAO)":"0.380"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-youtube-vos","task":"Visual Object Tracking","dataset":"YouTube-VOS 2018","model":"SiamMask","rank_in_archive_order":3,"of":9,"metrics":{"F-Measure (Seen)":"58.2","F-Measure (Unseen)":"47.7","Jaccard (Seen)":"54.3","Jaccard (Unseen)":"45.1","O (Average of Measures)":"52.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.05050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05050"}},"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/shallowtoil/DROL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ezelikman/anonymal","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/foolwood/SiamMask","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"ran":1,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"ezelikman/anonymal","repo_kind":"listed","path":"experiments/siammask_base/resnet.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/experiments/siammask_base/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"ed07034dd18cfc8f","entry":"conv2d_dw_group","repo":"ezelikman/anonymal","repo_kind":"listed","path":"models/rpn.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/models/rpn.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":"ed07034dd18cfc8f"}},{"code_sha256_prefix":"3be374ea8fee76b5","entry":"crop_hwc","repo":"ezelikman/anonymal","repo_kind":"listed","path":"datasets/siam_mask_dataset.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/datasets/siam_mask_dataset.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":"3be374ea8fee76b5"}},{"code_sha256_prefix":"3f1957b700e9ed16","entry":"get_cls_loss","repo":"ezelikman/anonymal","repo_kind":"listed","path":"models/siamrpn.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/models/siamrpn.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":"3f1957b700e9ed16"}},{"code_sha256_prefix":"ef70c620a00de25b","entry":"get_cls_loss","repo":"ezelikman/anonymal","repo_kind":"listed","path":"models/siammask.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/models/siammask.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":"ef70c620a00de25b"}},{"code_sha256_prefix":"02b73f913b091c75","entry":"resnet18","repo":"ezelikman/anonymal","repo_kind":"listed","path":"experiments/siammask_sharp/resnet.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/experiments/siammask_sharp/resnet.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":"02b73f913b091c75"}},{"code_sha256_prefix":"82928ae508d22d28","entry":"resnet34","repo":"ezelikman/anonymal","repo_kind":"listed","path":"experiments/siammask_sharp/resnet.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/experiments/siammask_sharp/resnet.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":"82928ae508d22d28"}},{"code_sha256_prefix":"8c846e3850e50c54","entry":"select_cross_entropy_loss","repo":"ezelikman/anonymal","repo_kind":"listed","path":"models/siammask.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/models/siammask.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":"8c846e3850e50c54"}},{"code_sha256_prefix":"2d85fa7671a85da4","entry":"select_cross_entropy_loss","repo":"ezelikman/anonymal","repo_kind":"listed","path":"models/siamrpn.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/models/siamrpn.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":"2d85fa7671a85da4"}},{"code_sha256_prefix":"27f3175caf7f84b6","entry":"weight_l1_loss","repo":"ezelikman/anonymal","repo_kind":"listed","path":"models/siammask.py","file_url":"https://github.com/ezelikman/anonymal/blob/HEAD/models/siammask.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":"27f3175caf7f84b6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}