Dual Path Networks for Multi-Person Human Pose Estimation
arXiv:1710.10192
Abstract
The task of multi-person human pose estimation in natural scenes is quite challenging. Existing methods include both top-down and bottom-up approaches. The main advantage of bottom-up methods is its excellent tradeoff between estimation accuracy and computational cost. We follow this path and aim to design smaller, faster, and more accurate neural networks for the regression of keypoints and limb association vectors. These two regression tasks are naturally dependent on each other. In this work, we propose a dual-path network specially designed for multi-person human pose estimation, and compare our performance with the openpose network in aspects of model size, forward speed, and estimation accuracy.
ICCV 2017 Workshop on PoseTrack Challenge. Challenge results available at: https://posetrack.net/workshops/iccv2017/posetrack-challenge-results.html
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Deep Residual Learning for Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Densely Connected Convolutional Networks
- Going Deeper with Convolutions
- Rethinking the Inception Architecture for Computer Vision
- Stacked Hourglass Networks for Human Pose Estimation
- Aggregated Residual Transformations for Deep Neural Networks
- Convolutional Pose Machines
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- Towards Accurate Multi-person Pose Estimation in the Wild
- RMPE: Regional Multi-person Pose Estimation
- Joint Multi-Person Pose Estimation and Semantic Part Segmentation