Multi-Granularity Language-Guided Training for Multi-Object Tracking
Fahad Shahbaz Khan
Fahad Shahbaz Khan
Author
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Most existing multi-object tracking methods typically learn visual tracking features via maximizing dis-similarities of different instances and minimizing similarities of the same instance. While such a feature learning scheme achieves promising performance, learning discriminative features solely based on visual information is challenging especially in case of environmental interference such as occlusion, blur and domain variance. In this work, we argue that multi-modal language-driven features provide complementary information to classical visual features, thereby aiding in improving the robustness to such environmental interference. To this end, we propose a new multi-object tracking framework, named LG-MOT, that explicitly leverages language information at different levels of granularity (scene-and instance-level) and combines it with standard visual features to obtain discriminative representations. To develop LG-MOT, we annotate existing MOT datasets with scene-and instance-level language descriptions. We then encode both scene-and instance-level language information into high-dimensional embeddings, which are utilized to guide the visual features during training. At inference, our LG-MOT uses the standard visual features without relying on annotated language descriptions. Extensive experiments on three benchmarks, MOT17, DanceTrack and SportsMOT, reveal the merits of the proposed contributions leading to state-of-the-art performance. On the DanceTrack test set, our LG-MOT achieves an absolute gain of 2.2% in terms of target object association (IDF1 score), compared to the baseline using only visual features. Further, our LG-MOT exhibits strong cross-domain generalizability.
Co-author(s)
Li Yuhao, Cao Jiale, Naseer Muzammal, Zhu Yu, Sun Jinqiu, Zhang Yanning, Khan Fahad Shahbaz
Citation
Y. Li et al., "Multi-Granularity Language-Guided Training for Multi-Object Tracking," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2025.3572810
Source
IEEE Transactions on Circuits and Systems for Video Technology
Conference
Keywords
Multi-object tracking, Language-guided features, Cross-domain generalizability
Subjects
Source
Publisher
IEEE