Learning Feature Pyramids for Human Pose Estimation

@article{Yang2017LearningFP,
  title={Learning Feature Pyramids for Human Pose Estimation},
  author={Wei Yang and Shuang Li and Wanli Ouyang and Hongsheng Li and Xiaogang Wang},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1290-1299}
}
Articulated human pose estimation is a fundamental yet challenging task in computer vision. [] Key Method Given input features, the PRMs learn convolutional filters on various scales of input features, which are obtained with different subsampling ratios in a multibranch network. Moreover, we observe that it is inappropriate to adopt existing methods to initialize the weights of multi-branch networks, which achieve superior performance than plain networks in many tasks recently.

Figures and Tables from this paper

Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization
TLDR
This work introduces a spatio-temporal network for robust 3D human pose estimation and proposes a confidence-based inference stage optimization to adaptively enforce 3D pose projection to match 2D pose estimation to further improve final pose prediction accuracy.
Learning Joint Structure for Human Pose Estimation
TLDR
This work designs a Structural Pose Network to take full advantage of joint structure for human pose estimation under unconstrained environment and proposes a novel structure-consistency constraint, which can maintain the structural consistency between the joints and body parts via estimating whether the joints are located in their corresponding parts.
Learning to Refine Human Pose Estimation
TLDR
A pose refinement network (PoseRefiner) is introduced which takes as input both the image and a given pose estimate and learns to directly predict a refined pose by jointly reasoning about the input-output space.
Cascade Feature Aggregation for Human Pose Estimation
TLDR
A novel Cascade Feature Aggregation (CFA) method, which cascades several hourglass networks for robust human pose estimation, which outperforms the state-of-the-art and achieves the best performance on the state of theart benchmark MPII.
Multi-Scale Supervised Network for Human Pose Estimation
TLDR
A robust pose estimation method based on the recent deep conv-deconv modules with two improvements: (1) multi -scale supervision of body keypoints, and (2) a global regression to improve structural consistency of keypoints.
SPCNet: Spatial Preserve and Content-aware Network for Human Pose Estimation
TLDR
A novel Spatial Preserve and Content-aware Network (SPCNet), which includes two effective modules: Dilated Hourglass Module (DHM) and Selective Information Module (SIM) and considerably improves the performance.
Improving Human Pose Estimation With Self-Attention Generative Adversarial Networks
TLDR
This paper proposes to apply Self-Attention GAN to further improve the performance of human pose estimation with attention mechanism in the framework of GAN, which outperforms other state-of-the-art methods on two standard benchmark datasets MPII and LSP.
Human Pose Estimation Using Convolutional Neural Networks
TLDR
This thesis proposes a simple yet effective method for human pose estimation, which applies a preprocessing step to the monocular images, tasked with generating the depth maps, in a cascaded manner.
Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
TLDR
This paper investigates different architectures and methodologies to address issues addressing standard issues normally faced in practical applications, and proposes to work with depth images, whose structure contains sufficient information about body landmarks while being simpler than textured color images and thus potentially requiring less complex CNNs for processing.
Stacked Mixed-Scale Networks for Human Pose Estimation
TLDR
A novel model is proposed, named Mixed-Scale Dense Block, that exploits dilation convolution layers and dense concatenation connections to maximise the information flow through the block and captures the feature representation in different scales more effectively and efficiently.
...
...

References

SHOWING 1-10 OF 71 REFERENCES
End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation
TLDR
This paper proposes a novel end-to-end framework for human pose estimation that combines DCNNs with the expressive deformable mixture of parts, and explicitly incorporate domain prior knowledge into the framework, which greatly regularizes the learning process and enables the flexibility of the framework for loopy models or tree-structured models.
Structured Feature Learning for Pose Estimation
TLDR
A bi-directional tree structured model is proposed, so that the feature channels at a body joint can well receive information from other joints, and the proposed framework improves feature learning substantially.
Human Pose Estimation with Iterative Error Feedback
TLDR
A framework that expands the expressive power of hierarchical feature extractors to encompass both input and output spaces, by introducing top-down feedback, and shows excellent performance on the task of articulated pose estimation in the challenging MPII and LSP benchmarks.
An Efficient Convolutional Network for Human Pose Estimation
TLDR
An efficient deep network architecture is proposed that is trained efficiently with a transparent procedure and exploits the best available ingredients from deep learning with low computational budget and achieves impressive performance on popular benchmarks in human pose estimation.
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
TLDR
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models.
Efficient object localization using Convolutional Networks
TLDR
A novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image to achieve improved accuracy in human joint location estimation is introduced.
Human Pose Estimation via Convolutional Part Heatmap Regression
TLDR
A CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for the case of severe part occlusions is proposed, and achieves top performance on the MPII and LSP data sets.
Multi-context Attention for Human Pose Estimation
TLDR
This paper proposes to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation and designs novel Hourglass Residual Units (HRUs) to increase the receptive field of the network.
Towards Accurate Multi-person Pose Estimation in the Wild
TLDR
This work proposes a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task by using a novel form of keypoint-based Non-Maximum-Suppression (NMS), instead of the cruder box-level NMS, and by introducing a novel aggregation procedure to obtain highly localized keypoint predictions.
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
TLDR
An approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other is proposed.
...
...