Papers › BootsTAP: Bootstrapped Training for Tracking-Any-Point

BootsTAP: Bootstrapped Training for Tracking-Any-Point

1 Feb 2024arXiv:2402.00847archive 2025-07-28

Carl Doersch, Pauline Luc, Yi Yang, Dilara Gokay, Skanda Koppula, Ankush Gupta, Joseph Heyward, Ignacio Rocco, Ross Goroshin, João Carreira, Andrew Zisserman

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/

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

google-deepmind/tapnet officialmentioned in papermentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning segmentation from point trajectories (arXiv:2501.12392; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. report
deepmind/tapnet mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TAP-Vid: A Benchmark for Tracking Any Point in a Video (arXiv:2211.03726; that paper's own run record: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Point Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Tracking TAP-Vid-DAVIS BootsTAPIR Average Jaccard 66.2 #2 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS BootsTAPIR Average PCK 78.1 #2 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS BootsTAPIR Occlusion Accuracy 91 #2 of 3 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics BootsTAPIR Average Jaccard 61.4 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics BootsTAPIR Average PCK 74.2 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics BootsTAPIR Occlusion Accuracy 89.7 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-RGB-Stacking BootsTAPIR Average Jaccard 72.4 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-RGB-Stacking BootsTAPIR Average PCK 83.1 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-RGB-Stacking BootsTAPIR Occlusion Accuracy 91.2 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections