Xinhua Cheng 程鑫华

School of Electronic and Computer Engineering
Peking University
Shenzhen, China

Email: chengxinhua@stu.pku.edu.cn

[Google Scholar] [dblp] [Github] [zhihu]

Biography

Xinhua Cheng is a master student of computer applications technology at Peking University, advised by Prof. Jian Zhang. He got a B.E. degree of computer science at Sichuan University. His research interests include computer vision, deep learning and person re-ID.

Education

Master Degree in Computer Applications Technology, 2021.9 - now
Peking University
Summer Workshop of Computer Science, 2019.7 - 2019.8
National University of Singapore
B.E. Degree in Computer Science and Techology (Top-notched Student Program), 2017.9 - 2021.6
Sichuan University

Selected Publications

	EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual and Language Learning Yanmin Wu, Xinhua Cheng, Renrui Zhang, Zesen Cheng, Jian Zhang Arxiv, 2022. [Paper]
	More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification Xinhua Cheng, Mengxi Jia, Qian Wang, Jian Zhang (* indicates equal contribution) ACM International Conference on Multimedia (ACM MM), 2022. [Paper]
	A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition Xinhua Cheng, Mengxi Jia, Qian Wang, Jian Zhang (* indicates equal contribution) IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. [Paper]
	Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification Mengxi Jia, Xinhua Cheng*, Shijian Lu, Jian Zhang ( indicates equal contribution) IEEE Transactions on Multimedia (TMM), 2022. [Paper]
	Matching on Sets: Conquer Occluded Person Re-identification Without Alignment Mengxi Jia, Xinhua Cheng, Yunpeng Zhai, Shijian Lu, Siwei Ma, Yonghong Tian, Jian Zhang AAAI Conference on Artificial Intelligence (AAAI), 2021. [Paper]

Awards

National Scholarship, Ministry of Education, 2020
2nd place in Computer Vision for Wildlife Conservation Challenge, ICCV Workshops, 2019
National Scholarship, Ministry of Education, 2018

	EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual and Language Learning Yanmin Wu, Xinhua Cheng, Renrui Zhang, Zesen Cheng, Jian Zhang Arxiv, 2022. [Paper]
	More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification Xinhua Cheng, Mengxi Jia, Qian Wang, Jian Zhang (* indicates equal contribution) ACM International Conference on Multimedia (ACM MM), 2022. [Paper]
	A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition Xinhua Cheng, Mengxi Jia, Qian Wang, Jian Zhang (* indicates equal contribution) IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. [Paper]
	Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification Mengxi Jia, Xinhua Cheng*, Shijian Lu, Jian Zhang ( indicates equal contribution) IEEE Transactions on Multimedia (TMM), 2022. [Paper]
	Matching on Sets: Conquer Occluded Person Re-identification Without Alignment Mengxi Jia, Xinhua Cheng, Yunpeng Zhai, Shijian Lu, Siwei Ma, Yonghong Tian, Jian Zhang AAAI Conference on Artificial Intelligence (AAAI), 2021. [Paper]