A5006266192- Human Pose and Action Recognition
- Gait Recognition and Analysis
- Video Surveillance and Tracking Methods
- 3D Shape Modeling and Analysis
- Diabetic Foot Ulcer Assessment and Management
- Anomaly Detection Techniques and Applications
- Computer Graphics and Visualization Techniques
- Graph Theory and Algorithms
- Advanced Vision and Imaging
- Image Retrieval and Classification Techniques
- Hand Gesture Recognition Systems
Beijing University of Technology
2021-2025
Abstract Human pose estimation based on monocular video has always been the focus of research in human computer interaction community, which suffers mainly from depth ambiguity and self‐occlusion challenges. While recently proposed learning‐based approaches have demonstrated promising performance, they do not fully explore complementarity features. In this paper, authors propose a novel multi‐feature multi‐level fusion network (MMF‐Net), extracts combines joint features, bone features...
3D human pose estimation (3DHPE) in images aims at estimating joint positions from images. The existing 3DHPE methods usually define the loss function as error measured by Euclidean distance between locations of predicted joints and ground truth joints, which confuses two different kinds errors with obviously characteristics should not be processed equally: caused structures others. However, representations are suitable to distinguish these errors. In order tackle this problem, we propose a...
3D human pose estimation (3DHPE) in images aims at estimating joint positions from images.The state-of-theart for 3DHPE is dominated by deep learning model whose accuracy obviously affected loss functions.The existing methods usually define the function as error measured Euclidean distance between locations of predicted joints and ground truth joints, which confuses two different kinds errors: caused structures others.But fact, characteristics these errors are should not be processed...
<title>Abstract</title> Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D lifting approaches have achieved remarkable improvements. However, HPE is still a challenging problem due inherent depth ambiguities and occlusions. Recently, diffusion models great success in field image generation. Inspired by this, we transform into reverse process, propose dual-branch model that could fully explore global local correlations between joints....
Existing non-rigid shape matching methods mainly involve two disadvantages. (a) Local details and global features of shapes can not be carefully explored. (b) A satisfactory trade-off between the accuracy computational efficiency hardly achieved. To address these issues, we propose a local-global commutative preserving functional map (LGCP) for correspondence. The core LGCP involves an intra-segment geometric submodel submodel, which accomplishes segment-to-segment point-to-point tasks,...