AI Paper Atlas

Research map / Detection and segmentation / Tracking

CoTracker: It is Better to Track Together

Nikita Karaev, Ignacio Rocco, Ben Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht

ECCV 2024 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 417 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
track points jointly (add cross-track attention and support points) (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 55.6 -> 62.2Improved
track all target points jointly on Dynamic Replica (ablation)CoTracker · Dynamic Replicadelta_avg^occ: 28.8 -> 37.6Improved
joint tracking effect on visible points (ablation)CoTracker · Dynamic Replicadelta_avg^vis: 62.4 -> 68.9Improved
add unrolled training over sliding windows (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 44.6 -> 62.2Improved
add proxy tokens (64) instead of full self-attention (ablation)CoTracker · scalability on 80 GB GPUmax tracks / time: 9.4k -> 69.2k tracks; 207.3s -> 27.9sImproved
use 64 proxy tokens instead of 0, 32 or 128 (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 0 tokens 61.6; 32: 60.2; 64: 62.2; 128: 60.9Mixed
add local support point grid (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 55.6 -> 60.4Improved
add global and local support grids together (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 55.6 -> 62.2Improved
use training sliding window 8 instead of 4 or 16 (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 4: 56.7; 8: 62.2; 16: 61.1Improved
evaluate with an inference window different from the trained window size (ablation)CoTracker · TAP-Vid-DAVIS FirstAJ: 62.2 -> 54.9 (window 4) / 54.6 (window 16)Hurt
use CoTracker rather than TAPIR on discontinuous Kinetics videosCoTracker · TAP-Vid-Kinetics FirstAJ: 49.6 -> 48.8No clear effect

Later papers that compared with this method

3 later accepted papers report CoTracker as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy