Author name: Zijia Lu, Jingru Yi, Jue Wang, Yuxiao Chen, Junwen Chen, Xinyu Li, Davide Modolo

arXiv:2604.10527v1 Announce Type: new
Abstract: Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose …