Fenghai Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fenghai Li has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Jian Cao
School of Computer, Beijing Technology and Business University, Beijing, China
2 shared publicationsShanshan Li
School of Computer, Beijing Technology and Business University, Beijing, China
2 shared publicationsYifan Chen
Canvard College, Beijing Technology and Business University, Beijing, China
2 shared publicationsHaisheng Li
School of Computer, Beijing Technology and Business University, 100048, China
1 shared publication- Haisheng Li
Beijing Technology and Business University, Beijing, China
1 shared publication Qiang Cai
School of Computer, Beijing Technology and Business University, 100048, China
1 shared publication
Latest Publications
- Open Access
Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization
In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this challenge, we convert the input from pixel space to 3D normalized rays. This conversion makes our approach robust to camera intrinsic parameter changes. To deal with the in-the-wild camera extrinsic parameter variations, Ray3D explicitly takes the camera extrinsic parameters as an input and jointly models the distribution between the 3D pose rays and camera extrinsic parameters. This novel network design is the key to the outstanding generalizability of Ray3D approach. To have a comprehensive understanding of how the camera intrinsic and extrinsic parameter variations affect the accuracy of absolute 3D key-point localization, we conduct in-depth systematic experiments on three single person 3D benchmarks as well as one synthetic benchmark. These experiments demonstrate that our method significantly outperforms existing state-of-the-art models. Our code and the synthetic dataset are available at https://github.com/YxZhxn/Ray3D .
Open AccessRay3D: ray-based 3D human pose estimation for monocular absolute 3D localization
In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this challenge, we convert the input from pixel space to 3D normalized rays. This conversion makes our approach robust to camera intrinsic parameter changes. To deal with the in-the-wild camera extrinsic parameter variations, Ray3D explicitly takes the camera extrinsic parameters as an input and jointly models the distribution between the 3D pose rays and camera extrinsic parameters. This novel network design is the key to the outstanding generalizability of Ray3D approach. To have a comprehensive understanding of how the camera intrinsic and extrinsic parameter variations affect the accuracy of absolute 3D key-point localization, we conduct in-depth systematic experiments on three single person 3D benchmarks as well as one synthetic benchmark. These experiments demonstrate that our method significantly outperforms existing state-of-the-art models. Our code and the synthetic dataset are available at https://github.com/YxZhxn/Ray3D .
- 5 August 2021
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (5) , 5185-5196
Attentive frequency learning network for super-resolution
- 5 August 2021
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (5) , 5185-5196
Attentive frequency learning network for super-resolution
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Label Rectification Learning through Kernel Extreme Learning Machine
Along with the strong representation of the convolutional neural network (CNN), image classification tasks have achieved considerable progress. However, majority of works focus on designing complicated and redundant architectures for extracting informative features to improve classification performance. In this study, we concentrate on rectifying the incomplete outputs of CNN. To be concrete, we propose an innovative image classification method based on Label Rectification Learning (LRL) through kernel extreme learning machine (KELM). It mainly consists of two steps: (1) preclassification, extracting incomplete labels through a pretrained CNN, and (2) label rectification, rectifying the generated incomplete labels by the KELM to obtain the rectified labels. Experiments conducted on publicly available datasets demonstrate the effectiveness of our method. Notably, our method is extensible which can be easily integrated with off‐the‐shelf networks for improving performance.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessLabel Rectification Learning through Kernel Extreme Learning Machine
Along with the strong representation of the convolutional neural network (CNN), image classification tasks have achieved considerable progress. However, majority of works focus on designing complicated and redundant architectures for extracting informative features to improve classification performance. In this study, we concentrate on rectifying the incomplete outputs of CNN. To be concrete, we propose an innovative image classification method based on Label Rectification Learning (LRL) through kernel extreme learning machine (KELM). It mainly consists of two steps: (1) preclassification, extracting incomplete labels through a pretrained CNN, and (2) label rectification, rectifying the generated incomplete labels by the KELM to obtain the rectified labels. Experiments conducted on publicly available datasets demonstrate the effectiveness of our method. Notably, our method is extensible which can be easily integrated with off‐the‐shelf networks for improving performance.