AI Paper Atlas

Research map / Detection and segmentation / Tracking

PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking

Seungjae Kim, SeungJoon Lee, MyeongAh Cho

AAAI 2026 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 4 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 Motion Pattern Module (ablation)PlugTrack (DiffMOT) · DanceTrack valHOTA: 59.2 -> 60.2Improved
add Prediction Discrepancy Module to MPM (ablation)PlugTrack (DiffMOT) · DanceTrack valHOTA: 60.2 -> 60.4Improved
add all three CME modules (ablation)PlugTrack (DiffMOT) · DanceTrack valHOTA: 59.2 -> 60.8Improved
use alpha range [0.3, 0.7] instead of [0.1, 0.9] (ablation)PlugTrack MCAS · DanceTrack valHOTA: 59.8 -> 60.7 (DiffMOT)Improved
use narrow alpha range [0.4, 0.6] (ablation)PlugTrack (DiffMOT) · DanceTrack valHOTA: 60.7 -> 59.5Hurt
add PlugTrack fusion to TrackSSMTrackSSM · DanceTrack testHOTA: 57.7 -> 59.2Improved
add PlugTrack fusion to DiffMOTDiffMOT · DanceTrack testHOTA: 62.3 -> 63.3Improved
add PlugTrack fusion to DiffMOTDiffMOT · DanceTrack testMOTA: 92.8 -> 92.4Hurt
add PlugTrack fusion to DiffMOTDiffMOT · MOT17 testHOTA: 64.0 -> 64.2No clear effect
add PlugTrack fusion to TrackSSM under domain transferTrackSSM · DanceTrack to MOT20HOTA: 47.7 -> 54.2Improved
add PlugTrack fusionTrackSSM · inference speedFPS: 37.2 -> 34.2Hurt

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