Wei Zhang

Senior Researcher
JD Explore Academy, Beijing, China

wzhang.cugmail.com


Bio

Wei Zhang is now a Senior Researcher in JD Explore Academy. He received his Ph.D degree from City University of Hong Kong, Hong Kong, China in 2015. He was a visiting scholar in DVMM group of Columbia University, New York, USA in 2014. His research interests include visual recognition and generation.

Looking for motivated intern students. Drop me an email if interested.


News


Publications

  • Augmentation Pathways Network for Visual Recognition [Paper]
    Yalong Bai, Mohan Zhou, Yuxiang Chen, Wei Zhang, Bowen Zhou, Tao Mei.
    PAMI, 2023

  • Deep person generation: A survey from the perspective of face, pose and cloth synthesis [Paper]
    Tong Sha, Wei Zhang, Tong Shen, Zhoujun Li, Tao Mei.
    ACM Computing Surveys, 2023

  • Boosting Generic Visual-Linguistic Representation with Dynamic Contexts [Paper]
    Guoqing Ma, Yalong Bai, Wei Zhang, Ting Yao, Basem Shihada, Tao Mei.
    IEEE Trans. on Multimedia (TMM), 2023

  • Directional Self-Supervised Learning for Heavy Image Augmentations [Paper] [Project]
    Yalong Bai, Yifan Yang, Wei Zhang, Tao Mei.
    CVPR, 2022

  • Responsive Listening Head Generation: A Benchmark Dataset and Baseline [Paper] [Challenge] [Project]
    Mohan Zhou, Yalong Bai, Wei Zhang, Tiejun Zhao, Tao Mei.
    ECCV, 2022

  • ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones [Paper]
    Shan An, Guangfu Che, Jinghao Guo, Haogang Zhu, Junjie Ye, Fangru Zhou, Zhaoqi Zhu, Dong Wei, Aishan Liu, Wei Zhang.
    ACM Multimedia, 2021

  • Trustworthy AI'21: 1st International Workshop on Trustworthy AI for Multimedia Computing [Project]
    Teddy Furon, Jingen Liu, Yogesh Rawat, Wei Zhang, Qi Zhao.
    ACM Multimedia, 2021

  • ViDA-MAN: Visual Dialog with Digital Humans (best demo paper award) [Paper] [Project]
    Tong Shen, Jiawei Zuo, Fan Shi, Jin Zhang, Liqin Jiang, Meng Chen, Zhengchen Zhang, Wei Zhang, Xiaodong He, Tao Mei.
    ACM Multimedia, 2021

  • Unpaired Person Image Generation with Semantic Parsing Transformation [Paper]
    Sijie Song, Wei Zhang, Jiaying Liu, Zongming Guo, Tao Mei
    PAMI, 2021

  • Exploiting Relationship for Complex-Scene Image Generation [Paper]
    Tianyu Hua, Hongdong Zheng, Yalong Bai, Wei Zhang, Xiao-Ping Zhang, Tao Mei.
    AAAI, 2021

  • Down to the Last Detail: Virtual Try-on with Fine-grained Details [Paper] [Project]
    Jiahang Wang, Tong Sha, Wei Zhang, Zhoujun Li, Tao Mei
    ACM Multimedia, 2020 (oral)

  • SketchMan: Learning to Create Professional Sketches [Paper] [Project]
    Jia Li, Nan Gao, Tong Shen, Wei Zhang, Tao Mei, Hui Ren
    ACM Multimedia, 2020

  • Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation [Paper] [Paper]
    Haoran Wang, Tong Shen, Wei Zhang, Lingyu Duan, Tao Mei
    ECCV, 2020

  • Look-into-Object: Self-supervised Structure Modeling for Object Recognition [Paper] [Project]
    Mohan Zhou, Yalong Bai, Wei Zhang, Tiejun Zhao, and Tao Mei
    CVPR, 2020

  • VrR-VG: Refocusing Visually-Relevant Relationships [Paper] [Project]
    Yuanzhi Liang, Yalong Bai, Wei Zhang, Xueming Qian, Li Zhu, Tao Mei
    ICCV, 2019

  • Sampling Wisely: Deep Image Embedding by Top-k Precision Optimization [Paper] [Project]
    Jing Lu, Chaofan Xu, Wei Zhang, Lingyu Duan, Tao Mei
    ICCV, 2019

  • Unsupervised Person Image Generation with Semantic Parsing Transformation [Paper] [Project]
    Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei
    CVPR, 2019 (oral)

  • Destruction and Construction Learning for Fine-grained Image Recognition [Paper] [Project]
    Yue Chen, Yalong Bai, Wei Zhang, Tao Mei
    CVPR, 2019

  • Everyone is a Cartoonist: Selfie Cartoonization with Attentive Adversarial Networks [Paper]
    Xinyu Li, Wei Zhang, Tong Shen, Tao Mei
    ICME, 2019 (oral)

  • Deep Learning based Multimedia Analytics: A Review [Paper]
    Wei Zhang, Ting Yao, Shiai Zhu, Abdulmotaleb El Saddik
    ACM TOMM, 2018

  • Fake Colorized Image Detection [Paper]
    Yuanfang Guo, Xiaochun Cao, Wei Zhang, Rui Wang
    IEEE Trans. on Information Forensics and Security (TIFS), 2018.

  • Binarized Mode Seeking for Scalable Visual Pattern Discovery [Paper]
    Wei Zhang, Xiaochun Cao, Rui Wang, Yuanfang Guo, Zhineng Chen
    CVPR, 2017

  • Retrieving Objects by Partitioning [Paper]
    Zhiyong Chen, Wei Zhang, Bin Hu, Xiaochun Cao, Si Liu, Dan Meng
    IEEE Trans. on Big Data (TBD), 2017

  • Hyperlink-Aware Object Retrieval [Paper]
    Wei Zhang, Chong-Wah Ngo, Xiaochun Cao
    IEEE Trans. on Image Processing (TIP), 2016

  • MatchDR: Image Correspondence by Leveraging Distance Ratio Constraint [Paper]
    Rui Wang, Dong Liang, Wei Zhang, Xiaochun Cao
    ACM Multimedia, 2016

  • Topological Spatial Verification for Instance Search [Paper]
    Wei Zhang, Chong-Wah Ngo
    IEEE Trans. on Multimedia (TMM), 2015

  • Scalable Visual Instance Mining with Threads of Features [Paper]
    Wei Zhang, Hongzhi Li, Chong-Wah Ngo, Shih-Fu Chang
    ACM Multimedia, 2014 (oral)

  • Visual Typo Correction by Collocative Optimization - A Case Study on Merchandize Images [Paper]
    Xiao-Yong Wei, Zhen-Qun Yang, Chong-Wah Ngo, Wei Zhang
    IEEE Trans. on Image Processing (TIP), 2014

  • Name-Face Association in Web Videos: A Large-Scale Dataset, Baselines, and Open Issues [Paper]
    Zhineng Chen, Chong-Wah Ngo, Wei Zhang, Juan Cao, Yu-Gang Jiang
    Journal of Computer Science and Technology, 2014

  • Searching Visual Instances with Topology Checking and Context Modeling [Paper]
    Wei Zhang, Chong-Wah Ngo
    ICMR, 2013 (oral)

  • VIREO/ECNU @ TRECVID 2013: A Video Dance of Detection, Recounting and Search with Motion Relativity and Concept Learning from Wild [Paper]
    Chong-Wah Ngo, Feng Wang, Wei Zhang, Chun-Chet Tan, Zhan-Hu Sun, Shi-Ai Zhu, Ting Yao
    NIST TRECVID Workshop, 2013

  • VIREO@TRECVID 2012: Searching with Topology, Recounting will Small Concepts, Learning with Free Examples [Paper]
    Wei Zhang, Chun-Chet Tan, Shi-Ai Zhu, Ting Yao, Lei Pang, Chong-Wah Ngo
    NIST TRECVID Workshop, 2012

  • Snap-and-Ask: Answering Multimodal Question by Naming Visual Instance [Paper]
    Wei Zhang, Lei Pang, Chong-Wah Ngo
    ACM Multimedia, 2012 (oral)

  • Video Hyperlinking: Libraries and Tools for Threading and Visualizing Large Video Collection [Paper] [Project]
    Lei Pang, Wei Zhang, Chong-Wah Ngo
    ACM Multimedia, 2012 (OSSC)

  • FashionAsk: Pushing Community Answers to Your Fingertips [Paper] [Video]
    Wei Zhang, Lei Pang, Chong-Wah Ngo
    ACM Multimedia, 2012 (demo)

  • Community as a Connector: Associating Faces with Celebrity Names in Web Videos [Paper]
    Zhineng Chen, Chong-Wah Ngo, Juan Cao, Wei Zhang
    ACM Multimedia, 2012

  • Detecting Image Forgeries using Metrology [Paper]
    Lin Wu, Xiaochun Cao, Wei Zhang, Yang Wang
    Machine Vision and Applications (MVA), 2012

  • VIREO @ TRECVID 2011: Instance Search, Semantic Indexing, Multimedia Event Detection and Known-Item Search [Paper]
    Chong-Wah Ngo, Shi-Ai Zhu, Wei Zhang, Chun-Chet Tan, Ting Yao, Lei Pang, Hung-Khoon Tan
    NIST TRECVID Workshop (TRECVID'11), 2011

  • Detecting and Extracting the Photo Composites using Planar Homography and Graph Cut [Paper]
    Wei Zhang, Xiaochun Cao, Yanling Qu, Yuexian Hou, Handong Zhao, Chenyang Zhang
    IEEE Transactions on Information Forensics and Security (TIFS), 2010

  • Detecting Photographic Composites Using Shadows [Paper]
    Wei Zhang, Xiaochun Cao, Jiawan Zhang, Jigui Zhu, Ping Wang
    ICME, 2009 (oral)

  • Detecting Photographic Composites Using Two-view Geometrical Constraints [Paper]
    Wei Zhang, Xiaochun Cao, Zhiyong Feng, Jiawan Zhang, Ping Wang
    ICME, 2009