DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels
arxiv.org·1d
Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thought
arxiv.org·2h
Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence
arxiv.org·1d
Loading...Loading more...