InterAct-Video: Reasoning-Rich Video QA for Urban Traffic
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912557444366336 |
|---|---|
| author | Vishal, Joseph Raj Basina, Divesh Patil, Rutuja Gowda, Manas Srinivas Naik, Katha Yang, Yezhou Chakravarthi, Bharatesh |
| author_facet | Vishal, Joseph Raj Basina, Divesh Patil, Rutuja Gowda, Manas Srinivas Naik, Katha Yang, Yezhou Chakravarthi, Bharatesh |
| contents | Traffic monitoring is crucial for urban mobility, road safety, and intelligent transportation systems (ITS). Deep learning has advanced video-based traffic monitoring through video question answering (VideoQA) models, enabling structured insight extraction from traffic videos. However, existing VideoQA models struggle with the complexity of real-world traffic scenes, where multiple concurrent events unfold across spatiotemporal dimensions. To address these challenges, this paper introduces \textbf{InterAct VideoQA}, a curated dataset designed to benchmark and enhance VideoQA models for traffic monitoring tasks. The InterAct VideoQA dataset comprises 8 hours of real-world traffic footage collected from diverse intersections, segmented into 10-second video clips, with over 25,000 question-answer (QA) pairs covering spatiotemporal dynamics, vehicle interactions, incident detection, and other critical traffic attributes. State-of-the-art VideoQA models are evaluated on InterAct VideoQA, exposing challenges in reasoning over fine-grained spatiotemporal dependencies within complex traffic scenarios. Additionally, fine-tuning these models on InterAct VideoQA yields notable performance improvements, demonstrating the necessity of domain-specific datasets for VideoQA. InterAct VideoQA is publicly available as a benchmark dataset to facilitate future research in real-world deployable VideoQA models for intelligent transportation systems. GitHub Repo: https://github.com/joe-rabbit/InterAct_VideoQA |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InterAct-Video: Reasoning-Rich Video QA for Urban Traffic Vishal, Joseph Raj Basina, Divesh Patil, Rutuja Gowda, Manas Srinivas Naik, Katha Yang, Yezhou Chakravarthi, Bharatesh Computer Vision and Pattern Recognition Traffic monitoring is crucial for urban mobility, road safety, and intelligent transportation systems (ITS). Deep learning has advanced video-based traffic monitoring through video question answering (VideoQA) models, enabling structured insight extraction from traffic videos. However, existing VideoQA models struggle with the complexity of real-world traffic scenes, where multiple concurrent events unfold across spatiotemporal dimensions. To address these challenges, this paper introduces \textbf{InterAct VideoQA}, a curated dataset designed to benchmark and enhance VideoQA models for traffic monitoring tasks. The InterAct VideoQA dataset comprises 8 hours of real-world traffic footage collected from diverse intersections, segmented into 10-second video clips, with over 25,000 question-answer (QA) pairs covering spatiotemporal dynamics, vehicle interactions, incident detection, and other critical traffic attributes. State-of-the-art VideoQA models are evaluated on InterAct VideoQA, exposing challenges in reasoning over fine-grained spatiotemporal dependencies within complex traffic scenarios. Additionally, fine-tuning these models on InterAct VideoQA yields notable performance improvements, demonstrating the necessity of domain-specific datasets for VideoQA. InterAct VideoQA is publicly available as a benchmark dataset to facilitate future research in real-world deployable VideoQA models for intelligent transportation systems. GitHub Repo: https://github.com/joe-rabbit/InterAct_VideoQA |
| title | InterAct-Video: Reasoning-Rich Video QA for Urban Traffic |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.14743 |