PKU-MMD is a new large scale benchmark for continuous multi-modality 3D human action understanding and covers a wide range of complex human activities with well annotated information. PKU-MMD contains 2 phases, for action detection tasks with increasing difficulty. Phase 1 is large-margin action detection task. Phase 2 is small-margin action detection task. Our dataset also provides multi-modality data sources, including RGB, depth, Infrared Radiation and Skeleton. We believe this large-scale dataset will benefit future researches on action detection for the community.
声明：本站所有文章，如无特殊说明或标注，本站所有资源来源于网络，版权均属于原作者所有。如若本站内容侵犯了原著者的合法权益，可联系我们进行处理。
算力导航