Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
arXiv:1406.2984
Abstract
This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.
Cited by in corpus (19)
- GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
- Learning Deep Structured Models
- Human Pose Estimation with Spatial Contextual Information
- Deep High-Resolution Representation Learning for Human Pose Estimation
- Improved training of binary networks for human pose estimation and image recognition
- Person-in-WiFi: Fine-grained Person Perception using WiFi
- Pose from Action: Unsupervised Learning of Pose Features based on Motion
- Exploiting Offset-guided Network for Pose Estimation and Tracking
- Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image
- Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models
- Global Context for Convolutional Pose Machines
- Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation
- Believe It or Not, We Know What You Are Looking at!
- Scaling Matters in Deep Structured-Prediction Models
- Deep Markov Random Field for Image Modeling
- In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations
- PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
- Pose estimator and tracker using temporal flow maps for limbs
- Semi- and Weakly-supervised Human Pose Estimation