TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident
Keywords: Anomaly Detection, Traffic Accident Understanding, Multimodal Large Language Models, Instructional Dataset
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general visual understanding tasks. However, their potential for high-level, fine-grained comprehension, such as anomaly understanding, remains unexplored. Focusing on traffic accidents, a critical and practical scenario within anomaly understanding, we investigate the advanced capabilities of MLLMs and propose TABot, a multimodal MLLM specialized for accident-related tasks. To facilitate this, we first construct TAU-106K, a large-scale multimodal dataset containing 106K traffic accident videos and images collected from academic benchmarks and public platforms. The dataset is meticulously annotated through a video-to-image annotation pipeline to ensure comprehensive and high-quality labels. Building upon TAU-106K, we train TABot using a two-step approach designed to integrate multi-granularity tasks, including accident recognition, spatial-temporal grounding, and an auxiliary description task to enhance the model's understanding of accident elements. Extensive experiments demonstrate TABot's superior performance in traffic accident understanding, highlighting not only its capabilities in high-level anomaly comprehension but also the robustness of the TAU-106K benchmark. Our code and data will be available at https://github.com/cool-xuan/TABot.
Supplementary Material: zip
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2856
Loading