Papers › Local All-Pair Correspondence for Point Tracking

Local All-Pair Correspondence for Point Tracking

22 Jul 2024arXiv:2407.15420archive 2025-07-28

Seokju Cho, Jiahui Huang, Jisu Nam, Honggyu An, Seungryong Kim, Joon-Young Lee

We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely on local 2D correlation maps to establish correspondences from a point in the query image to a local region in the target image, which often struggle with homogeneous regions or repetitive features, leading to matching ambiguities. LocoTrack overcomes this challenge with a novel approach that utilizes all-pair correspondences across regions, i.e., local 4D correlation, to establish precise correspondences, with bidirectional correspondence and matching smoothness significantly enhancing robustness against ambiguities. We also incorporate a lightweight correlation encoder to enhance computational efficiency, and a compact Transformer architecture to integrate long-term temporal information. LocoTrack achieves unmatched accuracy on all TAP-Vid benchmarks and operates at a speed almost 6 times faster than the current state-of-the-art.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.15420")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cvlab-kaist/locotrack officialmentioned on GitHubjaxApache-2.0 report
ku-cvlab/locotrack mentioned in papermentioned on GitHubjaxApache-2.0 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.

Code Syntology ran Syntology

12 samples harvested; 6 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6ran
6unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cvlab-kaist/locotrack. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_tapvid_metrics cvlab-kaist/locotrack/locotrack/evaluation_datasets.py official repository ran Apache-2.0 (permissive) · 8d2089efa5f5af9b · report
get_alibi_slope cvlab-kaist/locotrack/locotrack/locotrack_model.py official repository ran Apache-2.0 (permissive) · e720140bb5365d49 · report
get_relative_positions cvlab-kaist/locotrack/locotrack/locotrack_model.py official repository ran Apache-2.0 (permissive) · aa68b05aa2f84e51 · report
interp cvlab-kaist/locotrack/locotrack/utils/model_utils.py official repository ran Apache-2.0 (permissive) · 39fcbdf93dcb4313 · report
posenc cvlab-kaist/locotrack/locotrack/locotrack_model.py official repository ran Apache-2.0 (permissive) · e392edbfaa7809af · report
prob_loss cvlab-kaist/locotrack/locotrack/utils/model_utils.py official repository ran Apache-2.0 (permissive) · 2db92844cacf356b · report
add_weight_decay cvlab-kaist/locotrack/locotrack/optimizers.py official repository unverified Apache-2.0 (permissive) · 1b97ac62c8bb2152 · report
conv_block cvlab-kaist/locotrack/locotrack/models/cmdtop.py official repository unverified Apache-2.0 (permissive) · a8329e1fb8a56308 · report
huber_loss cvlab-kaist/locotrack/locotrack_pytorch/model_utils.py official repository unverified Apache-2.0 (permissive) · 08fd9996236d683e · report
huber_loss cvlab-kaist/locotrack/locotrack/utils/model_utils.py official repository unverified Apache-2.0 (permissive) · acafb736be892385 · report
latex_table cvlab-kaist/locotrack/locotrack/evaluation_datasets.py official repository unverified Apache-2.0 (permissive) · 17093d41c0b95c30 · report
prob_loss cvlab-kaist/locotrack/locotrack_pytorch/model_utils.py official repository unverified Apache-2.0 (permissive) · d71c81adf1b0a8dc · report

Tasks

AllPoint TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Tracking TAP-Vid-DAVIS LocoTrack-B Average Jaccard 69.4 #1 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS LocoTrack-B Average PCK 81.3 #1 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS LocoTrack-B Occlusion Accuracy 88.6 #1 of 3 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS-First LocoTrack-B Average Jaccard 64.8 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS-First LocoTrack-B Average PCK 77.4 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-DAVIS-First LocoTrack-B Occlusion Accuracy 86.2 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics LocoTrack-B Average Jaccard 59.1 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics LocoTrack-B Average PCK 72.5 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics LocoTrack-B Occlusion Accuracy 85.7 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics-First LocoTrack-B Average Jaccard 52.3 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics-First LocoTrack-B Average PCK 66.4 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-Kinetics-First LocoTrack-B Occlusion Accuracy 82.1 #1 of 2 Archive leaderboard report
Point Tracking TAP-Vid-RGB-Stacking LocoTrack-B Average Jaccard 70.8 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-RGB-Stacking LocoTrack-B Average PCK 83.2 #2 of 2 Archive leaderboard report
Point Tracking TAP-Vid-RGB-Stacking LocoTrack-B Occlusion Accuracy 84.1 #2 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSPEEDSoftmaxTransformer

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