AI Paper Atlas

Research map / Detection and segmentation / Tracking

Referring Multi-Object Tracking with Diverse Dynamic Expressions

Yani Zhang, Dongming Wu, Wencheng Han, Xingping Dong, Shengcai Liao, Bo Du

TPAMI 2026 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 36 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
add Temporal Enhancement module to TransRMOT baseline (ablation)TransRMOT baseline · Refer-KITTI-V2HOTA: 31.00 -> 34.46Improved
add Track Refinement module (ablation)TempRMOT · Refer-KITTI-V2HOTA: 34.46 -> 35.04Improved
add temporal decoder only (ablation)temporal enhancement module · Refer-KITTI-V2HOTA: 31.00 -> 33.52Improved
add object decoder only (ablation)temporal enhancement module · Refer-KITTI-V2HOTA: 31.00 -> 32.90Improved
add positional embeddings to temporal+object decoders (ablation)temporal enhancement module · Refer-KITTI-V2HOTA: 34.43 -> 35.04Improved
increase training memory length from 3 to 5 (ablation)TempRMOT · Refer-KITTI-V2HOTA: 33.64 -> 34.72Improved
increase inference memory length from 5 to 8 (trained with 5) (ablation)TempRMOT · Refer-KITTI-V2HOTA: 34.72 -> 35.04Improved
use proposed temporal module instead of GRU memory (ablation)TempRMOT · Refer-KITTI-V2HOTA: 31.88 -> 35.04Improved
use proposed temporal module instead of convolution (ablation)TempRMOT · Refer-KITTI-V2AssA: 44.65 -> 53.58Improved
add LLM-generated expressions to human expressions (ablation)TempRMOT · Refer-KITTI-V2HOTA: 27.69 -> 35.04Improved
add LLM-generated expressions on independently written test expressions (ablation)TempRMOT · Independently written expressionsHOTA: 30.09 -> 37.90Improved
train on Refer-KITTI-V2 instead of Refer-KITTI for cross-dataset test (ablation)TempRMOT · GroOT (MOT17 subset)HOTA: 6.75 -> 12.01Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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