Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

arXiv:2311.18259v3 Announce Type: replace
Abstract: We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel …

arxiv cs.ai cs.cv human person perspectives skilled type understanding