AI Paper Atlas

Research map / Detection and segmentation / Tracking

Delving into Motion-Aware Matching for Monocular 3D Object Tracking

Kuan-Chih Huang, Ming-Hsuan Yang, Yi-Hsuan Tsai

ICCV 2023 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 19 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
use motion representation instead of global representation (feature-space matching) (ablation)MoMA-M3T · nuScenes valAMOTA: 28.8 -> 30.7Improved
match in feature space instead of output space (motion representation) (ablation)MoMA-M3T · nuScenes valAMOTA: 28.7 -> 30.7Improved
add contrastive motion feature learning (ablation)MoMA-M3T · nuScenes valAMOTA: 30.7 -> 31.1Improved
add temporal encoder to motion transformer (ablation)MoMA-M3T · nuScenes valAMOTA: 29.5 -> 31.1Improved
add spatial encoder (ablation)MoMA-M3T · nuScenes valAMOTA: 30.1 -> 31.1Improved
add global positional feature in spatial encoder (ablation)MoMA-M3T · nuScenes valAMOTA: 30.7 -> 31.1Improved
use motion transformer instead of LSTM (ablation)MoMA-M3T · nuScenes valAMOTA: 29.7 -> 31.1Improved
add learnable time positional encoding (ablation)motion transformer · nuScenes valAMOTA: 30.7 -> 31.1Improved
increase number of history frames T from 1 to 6 (ablation)motion transformer · nuScenes valAMOTA: 29.5 -> 31.1Improved
use MoMA-M3T tracker instead of KF3D or LSTM on unseen detectors without retrainingFCOS3D / EPro-PnP detections · nuScenes valAMOTA: 25.8 -> 29.7 (EPro-PnP KF3D)Improved
MoMA-M3T versus Time3D on AMOTPnuScenes test single-camera · nuScenes testAMOTP (m): 1.36 -> 1.479Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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