Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915598911406080 |
|---|---|
| author | Yang, Yi Xu, Yiming Kaiser, Timo Cheng, Hao Rosenhahn, Bodo Yang, Michael Ying |
| author_facet | Yang, Yi Xu, Yiming Kaiser, Timo Cheng, Hao Rosenhahn, Bodo Yang, Michael Ying |
| contents | In this report, we present our solution to the MOT25-Spatiotemporal Action Grounding (MOT25-StAG) Challenge. The aim of this challenge is to accurately localize and track multiple objects that match specific and free-form language queries, using video data of complex real-world scenes as input. We model the underlying task as a video retrieval problem and present a two-stage, zero-shot approach, combining the advantages of the SOTA tracking model FastTracker and Multi-modal Large Language Model LLaVA-Video. On the MOT25-StAG test set, our method achieves m-HIoU and HOTA scores of 20.68 and 10.73 respectively, which won second place in the challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03332 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge Yang, Yi Xu, Yiming Kaiser, Timo Cheng, Hao Rosenhahn, Bodo Yang, Michael Ying Computer Vision and Pattern Recognition In this report, we present our solution to the MOT25-Spatiotemporal Action Grounding (MOT25-StAG) Challenge. The aim of this challenge is to accurately localize and track multiple objects that match specific and free-form language queries, using video data of complex real-world scenes as input. We model the underlying task as a video retrieval problem and present a two-stage, zero-shot approach, combining the advantages of the SOTA tracking model FastTracker and Multi-modal Large Language Model LLaVA-Video. On the MOT25-StAG test set, our method achieves m-HIoU and HOTA scores of 20.68 and 10.73 respectively, which won second place in the challenge. |
| title | Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.03332 |