Convolutional Pose Machines
Shih-En Wei, Varun Ramakrishna, Takeo Kanade A et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2016
Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.
Cited by 2,838 works. doi:10.1109/cvpr.2016.511 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- ImageNet classification with deep convolutional neural networks
- Going deeper with convolutions
- Fully convolutional networks for semantic segmentation
- Caffe
- Understanding the difficulty of training deep feedforward neural networks
- Learning long-term dependencies with gradient descent is difficult
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Pictorial Structures for Object Recognition
- Deeply-Supervised Nets