Jingdong Wang 王井东

Senior Researcher
Microsoft Research Asia
Beijing, China
Email_1: jingdw at microsoft dot com
Email_2: welleast at outlook dot com

CV    Google Scholar    DBLP    ORCID

Biography

Jingdong Wang is a Senior Researcher at Visual Computing Group, Microsoft Research Asia. His areas of interest include efficient CNN architecture design, human pose estimation, semantic segmentation, image classification, object detection, large-scale indexing, and salient object detection. He has been serving/served as an Associate Editor of IEEE TPAMI, IEEE TMM and IEEE TCSVT, and an area chair (or SPC) of some prestigious conferences in vision, multimedia, and AI, such as CVPR, ICCV, ECCV, ACM MM, IJCAI, and AAAI. He is an ACM Distinguished Member and a Fellow of IAPR. CV

Recent news

13. Three papers are accepted by CVPR 2019.
12. High-resolution networks (HRNet). A repalcement of classification networks for computer vision problems. Deep high-resolution representation learning for human pose estimation. Accepted to CVPR 2019. pdf   projects   code. 2/25/2019. Others applications: object detection, semantic segmentation, facial landmark detection, and image classification. pdf and code. 4/11/2019
11. Fast neighborhood graph-based approximate nearest neighbor search: code. It has been employed in many products: Bing Ads, Bing image search, Bing web search, XiaoIce etc. 12/29/2018.
10. Invited as an area chair of ICCV 2019, IJCAI 2019.
9. Elected as an ACM Distinguished Member, 11/2018.
8. Gave a keynote talk about approximate nearest neighbor search on 9/29/2018 at JD.com.  slides
7. Second place entry, COCO keypoints detection challenge ECCV 2018.
6. Appointed as AE of TPAMI, 09/2018.
5. Elected as Fellow of IAPR 2018.
4. One paper is accepted by ECCV 2018.
3. Two papers are accepted by ACM MM 2018.
2. Three papers are accepted by CVPR 2018.
1. Appointed as AE of TCSVT, 01/2018.

Codes and datasets

1. High-resolution representation learning (HRNet). A repalcement of classification networks for computer vision problems. Deep high-resolution representation learning for human pose estimation (CVPR 2019):  pdf  code | HRNetV2 for object detection, semantic segmentation, facial landmark detection, and image classification:  pdf   code
2. Small convolutional neural networks. Interleaved group convolutions. IGCV1 (ICCV 2017):  pdf  code | IGCV2 (CVPR 2018, spotlight):  pdf | IGCV3 (BMVC 2018):  pdf  code
3. Hashing and quantization. A survey on learning to hash (TPAMI):  pdf v2  html v2  tex v2  pdf v1 | Composite quantization (TPAMI, ICML 2014):  pdf  code
4. Large-scale indexing for similarity search. Neighborhood graph search (ACM MM 2012):  pdf | Neighborhood graph construction (CVPR 2012):  pdf | Trinary-projection trees (TPAMI, CVPR 2010):  pdf | code
5. Salient object detection. Discriminative Regional Feature Integration (IJCV, CVPR 2013):  pdf (CVPR)  pdf (IJCV)  c++ code  matlab code  MSRA-B  project | Local context (BMVC 2011):  pdf  code | Learning to detect a salient object (TPAMI):  pdf  MSRA10K

Recent publications

More by topic     More by date
[12]  Deep high-resolution representation learning for human pose estimation. Ke Sun, Bin Xiao, Dong Liu and Jingdong Wang. CVPR 2019.  [pdf] [code]
[11]  Part-Aligned Bilinear Representations for Person Re-identification. Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei, and Kyoung Mu Lee. ECCV 2018.  [pdf] [code]
[10]  IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks. Ke Sun, Mingjie Li, Dong Liu, and Jingdong Wang BMVC 2018.  [pdf] [code]
[9]  Composite Quantization. Jingdong Wang, and Ting Zhang. TPAMI 2018.  [pdf] [code]
[8]  Deep Convolutional Neural Networks with Merge-and-Run Mappings. Liming Zhao, Mingjie Li, Depu Meng, Xi Li, Zhaoxiang Zhang, Yueting Zhuang, Zhuowen Tu, and Jingdong Wang. IJCAI 2018.  [pdf] [code]
[7]  IGCV2: Interleaved Structured Sparse Convolutional Neural Networks. Guotian Xie, Jingdong Wang, Ting Zhang, Jianhuang Lai, Richang Hong, and Guo-Jun Qi. CVPR 2018.  [pdf] [code]
[6]  IGCV1: Interleaved Group Convolutions. Ting Zhang, Guo-Jun Qi, Bin Xiao, and Jingdong Wang. ICCV 2017.  [pdf]  [code]  [related papers]  [Zhihu]  [blog]
[5]  Deeply-Learned Part-Aligned Representations for Person Re-Identification. Liming Zhao, Xi Li, Yueting Zhuang, and Jingdong Wang. ICCV 2017.  [pdf] [code]
[4]  Human Pose Estimation using Global and Local Normalization. Ke Sun, Cuiling Lan, Junliang Xing, Dong Liu, Wenjun Zeng, and Jingdong Wang. ICCV 2017.  [pdf]
[3]  Ensemble Diffusion for Retrieval. Song Bai, Zhichao Zhou, Jingdong Wang, Xiang Bai, Longin Jan Latecki, and Qi Tian. ICCV 2017.  [pdf]
[2]  A Survey on Learning to Hash. Jingdong Wang, Ting Zhang, Jingkuan Song, Nicu Sebe, and Heng Tao Shen. TPAMI, Accepted 2017.  [pdf v2]  [[pdf v1]]
[1]  Deeply-Fused Nets. Jingdong Wang, Zhen Wei, and Ting Zhang. arXiv.  [pdf] [code]

HTML Hit Counters