Human Pose Estimation via Parse Graph of Body Structure
Keywords: Human Pose Estimation, Parse Graph, Context Relations, Hierarchical Structure, Hierarchical Decompositions
TL;DR: We design a hierarchical network to model the context relations and hierarchical structure in the parsing graph by convolutional neural networks
Abstract: When observing a person's body, humans can extract the structured representation of the body called a parse graph, which includes the hierarchical decompositions from the entire body to parts and primitives and the context relations by horizontal links between the body parts. This ability helps humans better locate body structures at different levels. In order for the model to have this ability for human pose estimation (HPE), We design a hierarchical network to model the context relations and hierarchical structure in the parsing graph by convolutional neural networks. It overcomes the problem that most methods ignore context relations in the inference of hierarchical structure for HPE. Our network contains bottom-up and top-down stages. In the bottom-up stage, the structural features of the hierarchy are captured from primitives to parts and the entire body. Then in the top-down stage, with the context information of each body part, the structural features of the body parts are refined separately rather than together from the entire body to parts and primitives. Experiments show that our model enhances the reasonableness of predictions and achieves superior results on the COCO keypoint detection and MPII human pose datasets.
Primary Area: representation learning for computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 809
Loading