Challenges

❗ The MAPLM-QA v2.0 dataset has been released at this link.

The challenge track is based on the MAPLM-QA benchmark, a subset of the MAPLM dataset designed for visual question answering in traffic scene understanding. Participants will develop innovative methods to accurately answer multi-choice questions about complex traffic scenes using high-resolution panoramic images and 2.5D bird’s-eye view representations. Top-performing teams will be recognized with certificates and honorariums. Detailed information about the challenge can be found in the MAPLM-QA v2.0 dataset.

Please submit your results by filling out this form. This will allow us to update your results on the leaderboard. The deadline of the challenge is Jan 5th.

Citation

If the code, datasets, and research behind this workshop inspire you, please cite our work:

@inproceedings{cao2024maplm,
  title={MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding},
  author={Cao, Xu and Zhou, Tong and Ma, Yunsheng and Ye, Wenqian and Cui, Can and Tang, Kun and Cao, Zhipeng and Liang, Kaizhao and Wang, Ziran and Rehg, James M and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages={21819--21830},
  year={2024}
}