微软研究院的最新大作。 We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body jointsfromasingledepthimage,withoutusinganytemporalinformation.Thekeytobothapproachesistheuseofalarge,realistic, an
Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we pro- pose a multitask framework for jointly 2D and 3D pose estimation from still images an
Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DC- NNs). Despite their success on large-scale datasets col- lected in the constrained lab
We introduce new, fine-grained action and emotion recognition tasks defined on non-staged videos, recorded during robot-assisted therapy sessions of children with autism. The tasks present several challenges: a large dataset with long videos, a larg
