← Search

Dingwen Xiao

2 accepted papers

2025

Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment

NeurIPS 2025poster

360 video captures the complete surrounding scenes with the ultra-large field of view of 360x180. This makes 360 scene understanding tasks, *e.g.*, segmentation and tracking, crucial for appications, such as autonomous driving, robotics. With the recent emergence of foundation models, the community…

Cited by 0SourcecodeScholar