Wenhai Wang (王文海)
Department of Computer Science and Technology, Nanjing University (NJU)
Address: 163 Xianlin Avenue, Qixia District, Nanjing, China
Email: wangwenhai362 [at] {163.com, smail.nju.edu.cn}

About Me ([GitHub] [Google Scholar] [CV])

I am a PhD candidate at Department of Computer Science and Technology, Nanjing University (NJU). My academic supervisor is Prof. Tong Lu. I received the bachelor's degree from School of Computer Science and Engineering, Nanjing University of Science and Technology (NUST) in 2016.

I work very close with my friends Enze Xie and Xiang Li. My recent works are mainly on scene text detection/recognition, deep neural networks exploration, object detection and instance segmentation.

I am looking for a postdoctoral position or a full-time job. Please feel free to contact me through the email.


  • 2020-09-02: Code of PAN is released at here.
  • 2020-07-03: Four papers are accepted by ECCV 2020.
  • 2020-03-10: One paper is accepted by CVPR 2020.
  • 2019-07-23: One paper is accepted by ICCV 2019.
  • 2019-03-15: Two papers are accepted by CVPR 2019.
  • 2018-06-16: One paper is accepted by IJCAI 2018.


  • Oct. 2019 - Mar. 2020, research assistant at the University of Hong Kong (HKU), hosted by Dr. Ping Luo
  • Aug. 2019 - Mar. 2020, research intern at SenseTime Group Limited, hosted by Xuebo Liu and Ding Liang
  • Jun. 2018 - Dec. 2018, research intern at Momenta, hosted by Xiang Li

Selected Publications [Full List]

AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
Wenhai Wang, Xuebo Liu, Xiaozhong Ji, Enze Xie, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen, Ping Luo
in ECCV, 2020
[Paper] [Dataset] [BibTex]
We introduce linguistic information to eliminate the ambiguity in text detection.
Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
Wenhai Wang*, Enze Xie*, Xiaoge Song, Yuhang Zang, Wenjia Wang, Tong Lu, Gang Yu, Chunhua Shen
in ICCV, 2019
[Paper] [Poster] [Code] [BibTex]
We propose an efficient method for arbitrary-shaped text detection.
Shape Robust Text Detection with Progressive Scale Expansion Network
Wenhai Wang*, Enze Xie*, Xiang Li, Wenbo Hou, Tong Lu, Gang Yu, Shuai Shao
in CVPR, 2019
[Paper] [Poster] [Code] [BibTex]
We proposed a segmentation-based text detector that can precisely detect text instances with arbitrary shapes.
Mixed Link Networks
Wenhai Wang*, Xiang Li*, Jian Yang, Tong Lu
in IJCAI, 2018
[Paper] [Poster] [Code] [BibTex]
We proposed an parameter-efficient convolutional neural networks for image classification.
Selective Kernel Networks
Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang
in CVPR, 2019
[Paper] [Code] [BibTex]
We proposed a dynamic selection mechanism in convolutional neural networks.
PolarMask: Single Shot Instance Segmentation with Polar Representation
Enze Xie*, Peize Sun*, Xiaoge Song*, Wenhai Wang, Chunhua Shen, Ping Luo
in CVPR, 2020 (oral presentation)
[Paper] [Code] [BibTex]
We introduced a Polar Representation to reformulate the instance segmentation problem.


  • ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text, Task1, 1st Place.
  • ICDAR2019 Robust Reading Challenge on Large-scale Street View Text with Partial Labeling, Task1, 2nd Place.
  • AI Challenger 2018 Autonomous Driving Perception Task, 2nd Place
  • ACM-ICPC Asia Regional Contest, Silver Medal

Review Services

Journal Reviewer
IEEE Transactions on Multimedia (T-MM)
Conference Reviewer
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020
Asian Conference on Computer Vision (ACCV), 2020
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021