AI Paper Atlas

Research map / Detection and segmentation / CNN features

TAPTR: Tracking Any Point with Transformers as Detection

Hongyang Li, Hao Zhang, Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Lei Zhang

ECCV 2024 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 26 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
lower the positional-encoding temperature in point self-attention (ablation)TAPTR · TAP-Vid-DAVISAJ: 61.9 -> 63.0Improved
add self attention among point queries (ablation)TAPTR · TAP-Vid-DAVISAJ: 58.4 -> 60.9Improved
add transformer encoder to image features (ablation)TAPTR · TAP-Vid-DAVISAJ: 60.9 -> 61.9Improved
add temporal attention and window feature updating (ablation)TAPTR · TAP-Vid-DAVISAJ: 51.6 -> 58.4Improved
add cost volume aggregation in decoder (ablation)TAPTR · TAP-Vid-DAVISAJ: 46.8 -> 51.6Improved
add cross attention to supplement cost volume (ablation)TAPTR · TAP-Vid-DAVISAJ: 50.0 -> 51.6Improved
use residual content-feature updating instead of DETR-style updating (ablation)TAPTR · TAP-Vid-DAVISAJ: 45.1 -> 46.8Improved
random drop of feature updating in training and gapped feature padding at inference, versus always updating (ablation)TAPTR · TAP-Vid-RGB-StackingAJ: 23.1 -> 60.8Improved
update cost volume once per window instead of every decoder iteration (ablation)TAPTR · TAP-Vid-RGB-StackingAJ: 58.0 -> 60.8Improved
update cost volume per window versus never updating (ablation)TAPTR · TAP-Vid-DAVISAJ: 63.0 -> 63.0No clear effect
supervise all decoder layers instead of last only (ablation)TAPTR · TAP-Vid-DAVISAJ: 55.4 -> 63.0Improved
increase decoder layers from 2 to 6 (ablation)TAPTR · TAP-Vid-DAVISAJ: 58.2 -> 63.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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