Saved in:
Bibliographic Details
Main Authors: Ashraf, Tajamul, Tariq, Tavaheed, Yadav, Sonia, Riyaz, Abrar Ul, Tak, Wasif, Abdar, Moloud, Bashir, Janibul
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911515097956352
author Ashraf, Tajamul
Tariq, Tavaheed
Yadav, Sonia
Riyaz, Abrar Ul
Tak, Wasif
Abdar, Moloud
Bashir, Janibul
author_facet Ashraf, Tajamul
Tariq, Tavaheed
Yadav, Sonia
Riyaz, Abrar Ul
Tak, Wasif
Abdar, Moloud
Bashir, Janibul
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2603_13759
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle QTrack: Query-Driven Reasoning for Multi-modal MOT
Ashraf, Tajamul
Tariq, Tavaheed
Yadav, Sonia
Riyaz, Abrar Ul
Tak, Wasif
Abdar, Moloud
Bashir, Janibul
Computer Vision and Pattern Recognition
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
title QTrack: Query-Driven Reasoning for Multi-modal MOT
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13759