2016 · 286 citations · 32 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningFeature DescriptionKernel MethodsPose EstimationRepresentation LearningBody Pose EstimationConvolutionConvolution KernelsDeep Feature LearningFeature LearningHuman Pose EstimationPost-processing
In this paper, we propose a structured feature learning framework to reason the correlations among body joints at the feature level in human pose estimation. Different from existing approaches of modeling structures on score maps or predicted labels, feature maps preserve substantially richer descriptions of body joints. The relationships between feature maps of joints are captured with the introduced geometrical transform kernels, which can be easily implemented with a convolution layer. Features and their relationships are jointly learned in an end-to-end learning system. A bi-directional tree structured model is proposed, so that the feature channels at a body joint can well receive information from other joints. The proposed framework improves feature learning substantially. With very simple post processing, it reaches the best mean PCP on the LSP and FLIC datasets. Compared with the baseline of learning features at each joint separately with ConvNet, the mean PCP has been improved by 18% on FLIC. The code is released to the public.
32
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
Histograms of Oriented Gradients for Human Detection
Navneet Dalal, Bill Triggs · 2005 · 31.9K citations · Full text
DeepPose: Human Pose Estimation via Deep Neural Networks
Alexander Toshev, Christian Szegedy · 2014 · 3.3K citations · Full text