AI Paper Atlas

Research map / Detection and segmentation / Tracking

TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video

Jinyuan Qu, Hongyang Li, Shilong Liu, Tianhe Ren, Zhaoyang Zeng, Lei Zhang

ICLR 2026 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 6 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
replace RNN-like long-temporal modeling with long-temporal attention (ablation)TAPTRv2 · TAP-Vid-Kinetics (ablation)AJ: 44.5 -> 47.8Improved
add visibility-aware reweighting to long-temporal attention (ablation)TAPTRv3 · TAP-Vid-Kinetics (ablation)AJ: 47.8 -> 48.8Improved
remove sliding window (ablation)TAPTRv3 · TAP-Vid-Kinetics (ablation)AJ: 48.8 -> 49.5Improved
supervise only visible points' positions (ablation)TAPTRv3 · TAP-Vid-Kinetics (ablation)AJ: 49.5 -> 51.1Improved
add context-aware cross-attention (CCA) (ablation)TAPTRv3 · TAP-Vid-Kinetics (ablation)AJ: 51.1 -> 52.9Improved
use every-two-point patch similarity instead of element-wise (ablation)CCA · TAP-Vid-Kinetics (ablation)AJ: 51.3 -> 52.9Improved
update spatial context features with VLTA or MLP during tracking (ablation)TAPTRv3 · TAP-Vid-Kinetics (ablation)AJ: 52.9 -> 51.2 (VLTA), 51.7 (MLP)Hurt
use global matching at every frame for decoder initial position (ablation)TAPTRv3 · TAP-Vid-Kinetics (ablation)AJ: 52.9 -> 51.1Hurt
trigger global matching only on scene cuts (ablation)TAPTRv3 · TAP-Vid-Kinetics (full)AJ: 54.9 -> 55.1Improved
trigger global matching on scene cuts (ablation)TAPTRv3 · Kinetics scene-cut subsetAJ: 55.3 -> 55.8Improved
use N=3 (9) context features instead of N=5 (25) or N=1 (ablation)CCA · TAP-Vid-Kinetics (ablation)AJ: N=1 51.3, N=3 52.9, N=5 52.2Mixed
increase VLTA memory size up to all past frames (ablation)TAPTRv3 · TAP-Vid-KineticsAJ: 51.9 (12) -> 54.9 (all past)Improved

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