{"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/track-anything-segment-anything-meets-videos","title":"Track Anything: Segment Anything Meets Videos","arxiv_id":"2304.11968","date":"2023-04-24","proceeding":null,"authors":["Jinyu Yang","Mingqi Gao","Zhe Li","Shang Gao","Fangjing Wang","Feng Zheng"],"abstract":"Recently, the Segment Anything Model (SAM) gains lots of attention rapidly due to its impressive segmentation performance on images. Regarding its strong ability on image segmentation and high interactivity with different prompts, we found that it performs poorly on consistent segmentation in videos. Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos. To be detailed, given a video sequence, only with very little human participation, i.e., several clicks, people can track anything they are interested in, and get satisfactory results in one-pass inference. Without additional training, such an interactive design performs impressively on video object tracking and segmentation. All resources are available on {https://github.com/gaomingqi/Track-Anything}. We hope this work can facilitate related research.","url_abs":"https://arxiv.org/abs/2304.11968v2","url_pdf":"https://arxiv.org/pdf/2304.11968v2.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":"track-anything-segment-anything-meets-videos","repo_url":"https://github.com/gaomingqi/track-anything","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.11968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11968"}},"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/gaomingqi/track-anything","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":8,"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":"db0ab43be2a00330","entry":"aggregate","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/aggregate.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/aggregate.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db0ab43be2a00330"}},{"code_sha256_prefix":"3903fb53c9bc4ae2","entry":"dice_loss","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/losses.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/losses.py","link_basis":"plan_row","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":"3903fb53c9bc4ae2"}},{"code_sha256_prefix":"dc5d821a03594011","entry":"do_softmax","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/memory_util.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/memory_util.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":"dc5d821a03594011"}},{"code_sha256_prefix":"2bd3aa89f60c3cec","entry":"downsample_groups","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/group_modules.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/group_modules.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":"2bd3aa89f60c3cec"}},{"code_sha256_prefix":"65507ac25f300c43","entry":"get_similarity","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/memory_util.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/memory_util.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":"65507ac25f300c43"}},{"code_sha256_prefix":"797931db27caacdb","entry":"upsample_groups","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/group_modules.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/group_modules.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":"797931db27caacdb"}},{"code_sha256_prefix":"72678d2f039afdfe","entry":"get_affinity","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/memory_util.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/memory_util.py","link_basis":"plan_row","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":"72678d2f039afdfe"}},{"code_sha256_prefix":"8fd49daab6c49086","entry":"interpolate_groups","repo":"gaomingqi/track-anything","repo_kind":"official","path":"tracker/model/group_modules.py","file_url":"https://github.com/gaomingqi/track-anything/blob/HEAD/tracker/model/group_modules.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":"8fd49daab6c49086"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}