|
Download README.md from GAASH-Lab/QTrack: direct link, hf CLI and curl.
- Browser
- Download file 2.87 kB
-
https://huggingface.co/GAASH-Lab/QTrack/resolve/main/README.md
- Command line
-
hf download hf://GAASH-Lab/QTrack/README.md
-
curl -L -o README.md https://huggingface.co/GAASH-Lab/QTrack/resolve/main/README.md
2.87 kB
| license: mit | |
| pipeline_tag: video-text-to-text | |
| tags: | |
| - multi-object-tracking | |
| - video-understanding | |
| - vision-language-model | |
| - spatiotemporal-reasoning | |
| # QTrack: Query-Driven Reasoning for Multi-modal MOT | |
| [**QTrack**](https://huggingface.co/papers/2603.13759) is an end-to-end vision-language model designed for query-driven multi-object tracking (MOT). Unlike traditional MOT which tracks all objects in a scene, QTrack selectively localizes and tracks specific targets based on natural language instructions while maintaining temporal coherence and identity consistency. | |
| - **Paper:** [QTrack: Query-Driven Reasoning for Multi-modal MOT](https://huggingface.co/papers/2603.13759) | |
| - **Project Page:** [https://gaash-lab.github.io/QTrack/](https://gaash-lab.github.io/QTrack/) | |
| - **Repository:** [https://github.com/gaash-lab/QTrack](https://github.com/gaash-lab/QTrack) | |
| ## Description | |
| Multi-object tracking has traditionally focused on estimating trajectories of all objects. QTrack introduces a **query-driven tracking paradigm** that formulates tracking as a spatiotemporal reasoning problem conditioned on natural language queries. | |
| ### Key Contributions | |
| - **RMOT26 Benchmark**: A large-scale benchmark with grounded queries and sequence-level splits to enable robust evaluation of generalization. | |
| - **QTrack Model**: An end-to-end vision-language model that integrates multimodal reasoning with tracking-oriented localization. | |
| - **Temporal Perception-Aware Policy Optimization (TPA-PO)**: A structured reward strategy to encourage motion-aware reasoning. | |
| ## Benchmark Results | |
| QTrack achieves state-of-the-art performance on the [RMOT26](https://huggingface.co/datasets/GAASH-Lab/RMOT26) benchmark. | |
| | Model | Params | MCP↑ | MOTP↑ | CLE (px)↓ | NDE↓ | | |
| |:-----:|:------:|:----:|:-----:|:---------:|:----:| | |
| | GPT-5.2 | - | 0.25 | 0.61 | 94.2 | 0.55 | | |
| | Qwen3-VL-Instruct | 8B | 0.25 | 0.64 | 96.0 | 0.97 | | |
| | Gemma 3 | 27B | 0.24 | 0.56 | 58.4 | 0.88 | | |
| | InternVL | 8B | 0.21 | 0.66 | 117.44 | 0.64 | | |
| | **QTrack (Ours)** | **3B** | **0.30** | **0.75** | **44.61** | **0.39** | | |
| ## Installation | |
| To set up the environment and use the model, please follow the instructions in the [official repository](https://github.com/gaash-lab/QTrack): | |
| ```bash | |
| # Create conda environment | |
| conda create -n qtrack python=3.12 | |
| conda activate qtrack | |
| # Install QTrack and dependencies | |
| git clone https://github.com/gaash-lab/QTrack.git | |
| cd QTrack | |
| pip install -r requirements.txt | |
| pip install -e . | |
| ``` | |
| ## Citation | |
| If you find QTrack useful for your research, please cite: | |
| ```bibtex | |
| @article{ashraf2026qtrack, | |
| title={QTrack: Query-Driven Reasoning for Multi-modal MOT}, | |
| author={Ashraf, Tajamul and Tariq, Tavaheed and Yadav, Sonia and Ul Riyaz, Abrar and Tak, Wasif and Abdar, Moloud and Bashir, Janibul}, | |
| journal={arXiv preprint arXiv:2603.13759}, | |
| year={2026} | |
| } | |
| ``` |