AI Paper Atlas

Research map / Detection and segmentation / Tracking

Referring Multi-Object Tracking

Dongming Wu, Wencheng Han, Tiancai Wang, Xingping Dong, Xiangyu Zhang, Jianbing Shen

CVPR 2023 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 104 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 TransRMOT instead of the strongest reported baseline, TrackFormerRefer-KITTI tracking · Refer-KITTIHOTA: 33.26 -> 35.54Improved
add the cross-modal fusion module (ablation)TransRMOT · Refer-KITTIHOTA: 17.01 -> 35.54Improved
use early fusion instead of concatenating visual and linguistic features (ablation)TransRMOT · Refer-KITTIHOTA: 28.61 -> 35.54Improved
use early fusion instead of language as decoder query (ablation)TransRMOT · Refer-KITTIHOTA: 33.29 -> 35.54Improved
add track queries for cross-frame association (ablation)TransRMOT · Refer-KITTIHOTAImproved
use track queries instead of SORT association (ablation)TransRMOT · Refer-KITTIHOTA: 31.63 -> 35.54Improved
use track queries instead of ByteTrack association (ablation)TransRMOT · Refer-KITTIHOTA: 32.12 -> 35.54Improved
replace RoBERTa with FastText or GloVe (ablation)TransRMOT · Refer-KITTIHOTA: 32.39, 32.45 vs 35.54Hurt
replace RoBERTa with BERT or Distill-BERT (ablation)TransRMOT · Refer-KITTIHOTA: 35.28, 33.56 vs 35.54No clear effect
vary the referring threshold from 0.2 to 0.5 (ablation)TransRMOT · Refer-KITTIHOTA: 35.10, 35.07, 35.54, 34.73No clear effect
increase the referring threshold to 0.6 or 0.7 (ablation)TransRMOT · Refer-KITTIHOTA: 35.54 -> 31.09; 31.63Hurt
train with 50% or 75% of expressions instead of all expressions (ablation)TransRMOT · Refer-KITTIHOTA: 35.54 -> 35.19; 35.48No clear effect

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