AI Paper Atlas

Research map / Detection and segmentation / Tracking

End-to-end 3D Tracking with Decoupled Queries

Yanwei Li, Zhiding Yu, Jonah Philion, Anima Anandkumar, Sanja Fidler, Jiaya Jia, Jose Alvarez

ICCV 2023 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 23 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
decouple single query into object query and track query (ablation)DQTrack · nuScenes valAMOTA: 24.5% -> 28.5%Improved
use single query for detection and tracking instead of tracking-by-detection (ablation)SinQuery · nuScenes valAMOTA: 25.7% -> 24.5%Hurt
use DQTrack instead of TBD-Geo with DETR3DDQTrack · nuScenes valAMOTA: 32.6% -> 36.7%; IDS 2564 -> 1120Improved
apply DQTrack across different encoders and decodersDQTrack · nuScenes valAMOTA: more than 3.0% AMOTA gain over TBD-GeoImproved
add embedding interaction (ablation)DQTrack · nuScenes valAMOTA: 27.8% -> 28.5%Improved
fuse appearance and motion features for association (ablation)DQTrack · nuScenes valAMOTA: 26.9% (motion only) -> 28.5%Improved
use transformer decoder embedding instead of raw BEV feature for object embedding (ablation)DQTrack · nuScenes valAMOTA: 26.4% -> 28.5%Improved
add EMA temporal update of track query (alpha 0.5) (ablation)DQTrack · nuScenes valAMOTA: 27.4% -> 28.5%Improved
add track query augmentation with false positives (ablation)DQTrack · nuScenes valAMOTA: 28.1% -> 28.5%Improved
add maximum entropy regularization on unmatched pairs (ablation)DQTrack · nuScenes valAMOTA: 27.9% -> 28.5%Improved
add EMA object embedding update (beta 0.3) (ablation)DQTrack · nuScenes valAMOTA: 26.9% -> 28.5%Improved
train with 3 frames instead of 2 or 4 (ablation)DQTrack · nuScenes valAMOTA: 26.8% (D=2) / 27.0% (D=4) -> 28.5% (D=3)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