AI Paper Atlas

Research map / Detection and segmentation / Tracking

Towards Real-Time Multi-Object Tracking

Zhongdao Wang, Liang Zheng, Yixuan Liu, Yali Li, Shengjin Wang

ECCV 2020 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 1,276 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
train embedding with cross-entropy instead of triplet loss (ablation)JDE · Embedding validationTPR@FAR=0.1: 44.3 -> 88.2Improved
train embedding with cross-entropy instead of triplet loss (ablation)JDE · Caltech val / MOT-15 trainMOTA: 59.5 -> 64.3Improved
use triplet upper bound instead of plain triplet loss (ablation)JDE · Embedding validationTPR@FAR=0.1: 42.2 -> 44.3Improved
use uncertainty weighting instead of approximate-optimal searched weights (ablation)JDE · Caltech val / MOT-15 trainMOTA: 64.3 -> 65.8Improved
use uncertainty weighting instead of uniform loss weights (ablation)JDE · Caltech val (detection AP)AP: 6.8 -> 83.0Improved
use uncertainty weighting instead of uniform loss weights (ablation)JDE · Caltech val / MOT-15 trainMOTA: 36.9 -> 65.8Improved
use MGDA-UB weighting instead of uncertainty weighting (ablation)JDE · Caltech val / MOT-15 trainMOTA: 65.8 -> 38.3Hurt
use loss normalization instead of uncertainty weighting (ablation)JDE · Caltech val / MOT-15 trainMOTA: 65.8 -> 57.9Hurt
use JDE online association instead of SORT cascade matching (ablation)JDE · MOT-15 (low density)MOTA: 66.9 -> 67.5Improved
use JDE online association instead of SORT cascade matching (ablation)JDE · CVPR19-01 (high density)FPS: 26.4 -> 33.9Improved
use JDE online association instead of SORT (ablation)JDE · MOT-15 (low density)IDF-1: 55.8 -> 67.6Improved
reduce input resolution from 1088x608 to 864x408JDE · MOT-16 testMOTA: 64.4 -> 62.1Hurt

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