AI Paper Atlas

Research map / Detection and segmentation / Tracking

SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes

Yutao Cui, Chenkai Zeng, Xiaoyu Zhao, Yichun Yang, Gangshan Wu, Limin Wang

ICCV 2023 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 245 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 MixFormer-based appearance association to ByteTrackByteTrack · SportsMOT testHOTA: 64.1 -> 65.7Improved
add MixFormer-based appearance association to OC-SORTOC-SORT · SportsMOT testHOTA: 73.7 -> 74.1Improved
drop Kalman filter motion prediction, use plain IoU (ablation)ByteTrack on SportsMOT · SportsMOT testHOTA: 64.1 -> 71.5Improved
fuse MixSort appearance cue with IoU (ablation)ByteTrack IoU association · SportsMOT testHOTA: 71.5 -> 73.8Improved
fuse appearance and motion instead of pure motion (ablation)MixSort-OC · SportsMOT footballHOTA: 71.9 -> 73.2Improved
fuse appearance and motion instead of pure motion (ablation)MixSort-OC · SportsMOT basketballHOTA: 65.9 -> 66.2Improved
use pure appearance association instead of pure motion (ablation)MixSort-OC · SportsMOT basketballHOTA: 65.9 -> 26.9Hurt
add MixSort to ByteTrack on DanceTrackByteTrack · DanceTrack valHOTA: 47.1 -> 46.7Hurt
replace DeepSORT-style ReID with MixSort appearance model (ablation)ByteTrack+ReID · SportsMOT testHOTA: 64.8 -> 65.7Improved
add a ReID appearance model to ByteTrack (ablation)ByteTrack · SportsMOT testHOTA: 64.1 -> 64.8Improved
apply MixSort to ByteTrack on MOT17ByteTrack · MOT17 test (private)HOTA: 63.1 -> 64.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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