Student at Xiamen University
About Me
I'm currently a graduate student in the Visual Computing and Graphics Lab of Xiamen University, supervised by associate professor Ming Zeng (opens new window). And I'm a research intern at Tencent AI Lab (opens new window).
My research interests lie at Computer Vision and Computer Graphics. I'm particularly interested in the areas of Human Pose Estimation, Text to Speech, and Virtual Human.
News
- [Apr. 2022] Our work on multi-person pose estimation named I^2R-Net is accepted by IJCAI-2022.
- [Jan. 2022] Our work on multi-person pose estimation has been submitted to IJCAI-2022.
- [Feb. 2021] Our work on the text to speech achieves multilingual in English and Chinese.
Some of my paper co-authors
- Ming Zeng (opens new window), Associate Professor at School of Informatics, Xiamen University.
- Jinpeng Lin (opens new window), Researcher at AlibabaGroup.
- Yinglin Zheng (opens new window), Research Intern at Visual Computing Group, Microsoft Research Asia (MSRA).
- Wenjin Deng (opens new window), Research at Visual Computing and Graphics Lab, Xiamen University.
Publications
I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
Yiwei Ding, Wenjin Deng, Yinglin Zheng, Pengfei Liu, Jianmin Bao, Meihong Wang, Xuan Cheng, Ming Zeng, Dong Chen.
CCF A, 2022, The 31st International Joint Conference on Artificial Intelligence (IJCAI-22).
Image-Based Automatic Watermeter Reading under Challenging Environments
Yiwei Ding, Jinpeng Lin, Meihong Wang, Qingyang Wei, Xianwei Wang, Qingqi Hong and Ming Zeng
SCI, 2021, 21(2), 434, Sensors; This work serves China Water.
Other Research Experience
Multi-Language Text to Speech
Duplicate Tacotron2 and improve its approach to multilingual TTS and use the resulting audio as input for virtual humans.
This work serves Xiamen political and legal virtual human.
Patents
CN202110069065.1
An Intelligent System for Fully Automatic Instrument Analysis in Complex Environment Based on Image.
Ming Zeng; Yiwei Ding; Jinpeng Lin.
CN202111117800.8
A speech-driven virtual human pose synthesis method for perceiving the environment.
Ming Zeng; Wenjin Deng; Yiwei Ding; Pengfei Liu.
CN202111117785.7
A speaker emotion perception method integrating multi-dimensional information.
Ming Zeng; Yiwei Ding; Wenjin Deng; Pengfei Liu.
CN202011408727.5
An evaluation and early warning system to enhance mutual trust between doctors and patients and reduce conflicts between doctors and patients.
Yilin Zhao; Ming Zeng; Wenjin Deng; Yiwei Ding, et al
Awards & Honors
- 1nd Prize The 6th Digital Media Technology Competition of Chinese Society for Artificial Intelligence, 2018.
- 2nd Prize The 10th Blue Bridge Cup Competition, 2019.
- 3nd Prize The 12th Computer Design Competition, 2019.
- 3nd Prize The 5th China 'Internet+'Innovation and Entrepreneurship Competition, 2019.
Thanks
Great thanks to my friend Yinglin Zheng (opens new window).