AI Paper Atlas

Research map / Detection and segmentation / Tracking

Hypergraph-State Collaborative Reasoning for Multi-Object Tracking

Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, Xinchao Wang

CVPR 2026 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 19 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
replace Kalman filter with HyperSSM motion model (ablation)tracking pipeline · DanceTrack valHOTA: 47.0 -> 59.7Improved
replace Kalman filter with HyperSSM motion model (ablation)tracking pipeline · MOT17 val-halfHOTA: 64.5 -> 65.5Improved
add hypergraph collaborative reasoning to SSM (ablation)SSM motion model · DanceTrack valHOTA: 53.7 -> 59.7Improved
add hypergraph collaborative reasoning to SSM (ablation)SSM motion model · MOT17 val-halfHOTA: 63.4 -> 65.5Improved
add hypergraph reasoning to SSM at YOLOX-X (ablation)SSM · MOT17 full trainHOTA: 71.9 -> 74.1Improved
add hypergraph reasoning to SSM at YOLOX-X (ablation)SSM · MOT17 full trainfps: 20.3 -> 17.5Hurt
raise hyperedge threshold theta from 0.5 to 0.8 (ablation)HyperSSM · MOT17 val-halfHOTA: 47.7 -> 65.5Improved
raise hyperedge threshold theta from 0.8 to 0.98 (ablation)HyperSSM · MOT17 val-halfHOTA: 65.5 -> 64.7Hurt
increase number of HyperSSM layers beyond 8 (ablation)HyperSSM · MOT17 and DanceTrackHOTANo clear effect
use 5-frame trajectory segments instead of longer ones (ablation)HyperSSM · MOT17 and DanceTrackHOTAImproved
use larger YOLOX detector (S to X) (ablation)HyperSSM tracker · MOT17 full trainHOTA: 57.3 -> 74.1Improved
HyperSSM vs best prior on DanceTrack testHyperSSM · DanceTrack testHOTA: 65.7 vs 76.2 (DualMOT)Hurt

Earlier methods this paper compares with

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