AI Paper Atlas

Research map / Detection and segmentation / Tracking

Uncertainty-aware Unsupervised Multi-Object Tracking

Kai Liu, Sheng Jin, Zhihang Fu, Ze Chen, Rongxin Jiang, Jieping Ye

ICCV 2023 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 29 citations (OpenAlex)

Read the paper

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
add uncertainty-aware tracklet labeling (UTL) to long-term-association baseline (ablation)U2MOT baseline · MOT17 val (half split)HOTA: 63.43 -> 63.84Improved
add vanilla long-term similarity association for pseudo identities (LTD) (ablation)U2MOT baseline · MOT17 val (half split)HOTA: 63.40 -> 63.43No clear effect
add tracklet-guided augmentation (TGA) on top of UTL (ablation)U2MOT · MOT17 val (half split)HOTA: 63.84 -> 64.08Improved
use uncertainty-based source and target anchor selection in TGA instead of random (ablation)TGA · MOT17 val (half split)HOTA: 63.93 -> 64.08Improved
choose high-uncertainty target anchor instead of random (ablation)TGA · MOT17 val (half split)HOTA: 63.93 -> 64.01Improved
add TGA with fully random anchor selection (ablation)U2MOT with UTL · MOT17 val (half split)HOTA: 63.84 -> 63.93Improved
use unsupervised U2MOT instead of identity-supervised trainingU2MOT · MOT17 val (half split)HOTA: 63.96 -> 64.08Improved
apply UTL association at inference to existing trackersFairMOT · MOT17 val (half split)HOTA: 62.03 -> 64.01Improved
apply UTL association at inference to existing trackersDeepSORT · MOT17 val (half split)HOTA: 58.48 -> 59.75Improved
apply UTL association at inferenceByteTrack · MOT17 val (half split)IDS: 207 -> 212Hurt
replace pre-trained UniTrack ReID with jointly trained ReID headByteTrack on VisDrone-MOT · VisDrone-MOT test-devIDF1: 68.3 -> 69.0Improved
use U2MOT on crowded MOT20 versus ByteTrackU2MOT · MOT20 testIDS: 1223 -> 1379Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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