QTrack: Query-Driven Reasoning for Multi-modal MOT
This work addresses the need for selective, language-guided tracking in multi-object tracking, enabling more efficient and user-focused applications in video analysis.
The paper tackles the problem of multi-object tracking by introducing a query-driven paradigm that localizes and tracks only user-specified targets based on natural language queries, achieving state-of-the-art results on a new benchmark with improved generalization and temporal coherence.
Multi-object tracking (MOT) has traditionally focused on estimating trajectories of all objects in a video, without selectively reasoning about user-specified targets under semantic instructions. In this work, we introduce a query-driven tracking paradigm that formulates tracking as a spatiotemporal reasoning problem conditioned on natural language queries. Given a reference frame, a video sequence, and a textual query, the goal is to localize and track only the target(s) specified in the query while maintaining temporal coherence and identity consistency. To support this setting, we construct RMOT26, a large-scale benchmark with grounded queries and sequence-level splits to prevent identity leakage and enable robust evaluation of generalization. We further present QTrack, an end-to-end vision-language model that integrates multimodal reasoning with tracking-oriented localization. Additionally, we introduce a Temporal Perception-Aware Policy Optimization strategy with structured rewards to encourage motion-aware reasoning. Extensive experiments demonstrate the effectiveness of our approach for reasoning-centric, language-guided tracking. Code and data are available at https://github.com/gaash-lab/QTrack