Metraipolis › archive › dc_ec78322255b4
TAQ-MOTR: Tracking-Aware Detection Query Formation for End-to-End Multiple Object Tracking — arXiv:2611.05205
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05205
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:57:26.355Z
- SHA-256 of the archived text
f614321d2aeadec04e9b3b8b1139ea5028d458883bf43b49d88a01809850a394- Stable URL of this page
https://metraipolis.com/documento/dc_ec78322255b4
How to cite
TAQ-MOTR: Tracking-Aware Detection Query Formation for End-to-End Multiple Object Tracking — arXiv:2611.05205 — arXiv (en), https://arxiv.org/abs/2611.05205 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec78322255b4 (Metraipolis archive dc_ec78322255b4, sha256 f614321d2aeadec04e9b3b8b1139ea5028d458883bf43b49d88a01809850a394)
BibTeX
@misc{dcec78322255b4,
title = {TAQ-MOTR: Tracking-Aware Detection Query Formation for End-to-End Multiple Object Tracking — arXiv:2611.05205},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05205},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec78322255b4; sha256 f614321d2aeadec04e9b3b8b1139ea5028d458883bf43b49d88a01809850a394},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05205. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tracking-by-propagation (TBP) methods perform end-to-end multi-object tracking by propagating track queries across frames, jointly handling detection and identity association without heuristic post-processing while naturally modeling temporal information. However, as detection and association are tightly coupled, detection queries in TBP are expected to discover currently untracked objects and provide complementary current-frame evidence for challenging tracks whose queries and identities are retained. Existing methods largely inherit detection-query formation from single-frame detection and construct such queries before the decoder with little awareness of trajectory states. Consequently, currently untracked objects may be missed, while challenging tracked objects with reduced visibility under occlusion may lack complementary evidence, causing association failures or duplicate responses. To address these issues, we propose TAQ-MOTR, a tracking-aware detection query formation framework that employs a pre-decoder Hybrid Query Generator (HQG) to fuse current-frame image features, track memory, and learnable memory. By conditioning detection queries on trajectory states, TAQ-MOTR adapts them to \rev{the discovery of currently untracked objects and tracked-object complementation We further introduce a training-only auxiliary detection branch whose one-to-one label assignment is decoupled from that of the main tracking branch, providing additional detection supervision to strengthen the shared HQG and decoder for the discovery of currently untracked objects. TAQ-MOTR improves performance on DanceTrack, SportsMOT, and BFT, achieving 72.0 HOTA, 63.1 AssA, and 76.6 IDF1 on the DanceTrack test set. Code is available at this https URL
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.05205 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:33:47.224Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).