{"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":"/paper/bootstap-bootstrapped-training-for-tracking","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","arxiv_id":"2402.00847","date":"2024-02-01","proceeding":null,"authors":["Carl Doersch","Pauline Luc","Yi Yang","Dilara Gokay","Skanda Koppula","Ankush Gupta","Joseph Heyward","Ignacio Rocco","Ross Goroshin","João Carreira","Andrew Zisserman"],"abstract":"To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes. This can be formalized as Tracking-Any-Point (TAP), which requires the algorithm to track any point on solid surfaces in a video, potentially densely in space and time. Large-scale groundtruth training data for TAP is only available in simulation, which currently has a limited variety of objects and motion. In this work, we demonstrate how large-scale, unlabeled, uncurated real-world data can improve a TAP model with minimal architectural changes, using a selfsupervised student-teacher setup. We demonstrate state-of-the-art performance on the TAP-Vid benchmark surpassing previous results by a wide margin: for example, TAP-Vid-DAVIS performance improves from 61.3% to 67.4%, and TAP-Vid-Kinetics from 57.2% to 62.5%. For visualizations, see our project webpage at https://bootstap.github.io/","url_abs":"https://arxiv.org/abs/2402.00847v2","url_pdf":"https://arxiv.org/pdf/2402.00847v2.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":"bootstap-bootstrapped-training-for-tracking","repo_url":"https://github.com/google-deepmind/tapnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"bootstap-bootstrapped-training-for-tracking","repo_url":"https://github.com/deepmind/tapnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"point-tracking","task_name":"Point Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-tracking-on-tap-vid-davis","task":"Point Tracking","dataset":"TAP-Vid-DAVIS","model":"BootsTAPIR","rank_in_archive_order":2,"of":3,"metrics":{"Average Jaccard":"66.2","Average PCK":"78.1","Occlusion Accuracy":"91"},"uses_additional_data":false},{"leaderboard":"/sota/point-tracking-on-tap-vid-kinetics","task":"Point Tracking","dataset":"TAP-Vid-Kinetics","model":"BootsTAPIR","rank_in_archive_order":1,"of":2,"metrics":{"Average Jaccard":"61.4","Average PCK":"74.2","Occlusion Accuracy":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/point-tracking-on-tap-vid-rgb-stacking","task":"Point Tracking","dataset":"TAP-Vid-RGB-Stacking","model":"BootsTAPIR","rank_in_archive_order":1,"of":2,"metrics":{"Average Jaccard":"72.4","Average PCK":"83.1","Occlusion Accuracy":"91.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.00847","atlas_url":"https://app.syntology.ai/?focus=2402.00847","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2402.00847"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.00847\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.00847"},"call":"get_concepts_for_paper(arxiv_id=\"2402.00847\")"}],"by_repo":[{"repo":"google-deepmind/tapnet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2501.12392"],"harvested_for_calls":[{"arxiv_id":"2501.12392","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2501.12392"},"call":"get_harvested_code_for_paper(arxiv_id=\"2501.12392\")"}]},{"repo":"deepmind/tapnet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2211.03726"],"harvested_for_calls":[{"arxiv_id":"2211.03726","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.03726"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.03726\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d9be768d6249ea647dee5b90f47f9d5e46ab2b5c2aa03830d1b997f406560ac4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}