Jingli Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jingli Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Anran Zhao
Wuhan University
1 shared publication - Hongren Cheng
Sports Big-Data Research Center, Wuhan Sports University, Wuhan 430079, China
1 shared publication - Hongtao Zeng
School of Physical Education, Huazhong University of Science and Technology, Wuhan 430074, China
1 shared publication - Liangshan Dong
School of Physical Education, China University of Geoscience, Wuhan, China
1 shared publication
Latest Publications
- Open Access
DSPose: Dual-Space-Driven Keypoint Topology Modeling for Human Pose Estimation
Human pose estimation is the basis of many downstream tasks, such as motor intervention, behavior understanding, and human–computer interaction. The existing human pose estimation methods rely too much on the similarity of keypoints at the image feature level, which is vulnerable to three problems: object occlusion, keypoints ghost, and neighbor pose interference. We propose a dual-space-driven topology model for the human pose estimation task. Firstly, the model extracts relatively accurate keypoints features through a Transformer-based feature extraction method. Then, the correlation of keypoints in the physical space is introduced to alleviate the error localization problem caused by excessive dependence on the feature-level representation of the model. Finally, through the graph convolutional neural network, the spatial correlation of keypoints and the feature correlation are effectively fused to obtain more accurate human pose estimation results. The experimental results on real datasets also further verify the effectiveness of our proposed model.
Open AccessDSPose: Dual-Space-Driven Keypoint Topology Modeling for Human Pose Estimation
Human pose estimation is the basis of many downstream tasks, such as motor intervention, behavior understanding, and human–computer interaction. The existing human pose estimation methods rely too much on the similarity of keypoints at the image feature level, which is vulnerable to three problems: object occlusion, keypoints ghost, and neighbor pose interference. We propose a dual-space-driven topology model for the human pose estimation task. Firstly, the model extracts relatively accurate keypoints features through a Transformer-based feature extraction method. Then, the correlation of keypoints in the physical space is introduced to alleviate the error localization problem caused by excessive dependence on the feature-level representation of the model. Finally, through the graph convolutional neural network, the spatial correlation of keypoints and the feature correlation are effectively fused to obtain more accurate human pose estimation results. The experimental results on real datasets also further verify the effectiveness of our proposed model.