2017 · 258 citations · 57 references
ComputingComputer ScienceComputer VisionMachine LearningSensor FusionDeep LearningMulti-view GeometryPose EstimationScene ReconstructionScene UnderstandingVisual Odometry2D Pose Estimation3D Pose EstimationArticulated Pose EstimationBody Pose EstimationHuman Pose Estimation
Most recent approaches to monocular 3D human pose estimation rely on Deep Learning. They typically involve regressing from an image to either 3D joint coordinates directly or 2D joint locations from which 3D coordinates are inferred. Both approaches have their strengths and weaknesses and we therefore propose a novel architecture designed to deliver the best of both worlds by performing both simultaneously and fusing the information along the way. At the heart of our framework is a trainable fusion scheme that learns how to fuse the information optimally instead of being hand-designed. This yields significant improvements upon the state-of-the-art on standard 3D human pose estimation benchmarks.
57
DeepPose: Human Pose Estimation via Deep Neural Networks
Alexander Toshev, Christian Szegedy · 2014 · 3.3K citations · Full text
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler et al. · 2014 · 2.8K citations
Shih-En Wei, Varun Ramakrishna, Takeo Kanade et al. · 2016 · 2.8K citations
Recognizing action at a distance
Alexei A. Efros, Berg, Mori · 2003 · 1.2K citations