{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:35:17Z","timestamp":1761176117697,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Multi-object tracking (MOT) aims to detect and associate all target instances across consecutive frames. Most existing MOT methods rely on the linear motion assumption of Kalman filter, which is effective for tracking linearly moving targets. However, in sports scenarios, athlete movement is often highly irregular and non-linear, significantly reducing the effectiveness of Kalman filter based approaches. To address this challenge, we propose DDT-Track, a novel tracking algorithm designed specifically for multi-athlete tracking in dynamic sports environments. Unlike traditional methods, DDT-Track abandons Kalman filter entirely. Instead, it leverages deep appearance features and DLIoU for trajectory association without relying on linear motion prediction, and employs the TrackRe-match module to recover lost trajectories caused by occlusions and rapid movements. Our approach effectively addresses the issue of irregular athlete motion and achieves strong tracking performance. DDT-Track attains a HOTA score of 74.5% on our self-constructed benchmark Floorball-MOT, and 78.8% on the public SportsMOT dataset,consistently outperforming previous tracking methods and demonstrating its robustness in complex sports scenarios(Fig. 1).<\/jats:p>","DOI":"10.3233\/faia250804","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:42:39Z","timestamp":1761126159000},"source":"Crossref","is-referenced-by-count":0,"title":["DDT-Track: Optimizing Multi-Object Tracking in Sports Through DLIoU and TrackRematch"],"prefix":"10.3233","author":[{"given":"JunWei","family":"Mu","sequence":"first","affiliation":[{"name":"College of Computer Science, Inner Mongolia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YongMei","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:42:39Z","timestamp":1761126159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250804"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250804","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}