{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tumtraffic-videoqa-a-benchmark-for-unified","title":"TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes","arxiv_id":"2502.02449","date":"2025-02-04","proceeding":null,"authors":["Xingcheng Zhou","Konstantinos Larintzakis","Hao Guo","Walter Zimmer","MingYu Liu","Hu Cao","Jiajie Zhang","Venkatnarayanan Lakshminarasimhan","Leah Strand","Alois C. Knoll"],"abstract":"We present TUMTraffic-VideoQA, a novel dataset and benchmark designed for spatio-temporal video understanding in complex roadside traffic scenarios. The dataset comprises 1,000 videos, featuring 85,000 multiple-choice QA pairs, 2,300 object captioning, and 5,700 object grounding annotations, encompassing diverse real-world conditions such as adverse weather and traffic anomalies. By incorporating tuple-based spatio-temporal object expressions, TUMTraffic-VideoQA unifies three essential tasks-multiple-choice video question answering, referred object captioning, and spatio-temporal object grounding-within a cohesive evaluation framework. We further introduce the TUMTraffic-Qwen baseline model, enhanced with visual token sampling strategies, providing valuable insights into the challenges of fine-grained spatio-temporal reasoning. Extensive experiments demonstrate the dataset's complexity, highlight the limitations of existing models, and position TUMTraffic-VideoQA as a robust foundation for advancing research in intelligent transportation systems. The dataset and benchmark are publicly available to facilitate further exploration.","url_abs":"https://arxiv.org/abs/2502.02449v1","url_pdf":"https://arxiv.org/pdf/2502.02449v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tumtraffic-videoqa-a-benchmark-for-unified","repo_url":"https://github.com/TraffiX-VideoQA/TUMTraffic-VideoQA-Baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"object","task_name":"Object"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"traffic-object-detection","task_name":"Traffic Object Detection"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[{"slug":"tumtraffic-videoqa","name":"TUMTraffic-VideoQA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}