Weilin Huang
Chief Scientist
Malong Technologies
Email: whuang[at]malong.com; whuang[at]robots.ox.ac.uk
Our Research Team is hiring!

About me

I am Chief Scientist of Malong Technologies (since July 2017), leading Algorithm and Research Team. Before that, I was working as a researcher at Visual Geometry Group, University of Oxford (2015-2017), with Prof. Alison Noble and Prof. Andrew Zisserman on Medical Image/Video Analysis. I was an Assistant Professor at Chinese Academy of Sciences (2013-2015), working closely with Dr. Yu Qiao at Chinese Academy of Sciences, and Prof. Xiaoou Tang at the Chinese University of Hongkong. I was a Research Intern at Adobe Research, working with Dr. Jue Wang, Dr. Zhe Lin, and Dr. Jianchao Yang. My research interests are in computer vision and deep learning, including scene text detection and recognition, medical image analysis, object detection and image classification.

I got my PhD degree from the University of Manchester, UK, under the supervision of Dr. Hujun Yin in 2013. I received my B.Sc degree from Shandong Unviersity, China.
 

News

  • 29th July, 2019: Four papers (with one Oral) are accepted by ICCV 2019, and one paper (Oral) is accepted by MICCAI 2019.
  • 12th July, 2018: Two papers are accepted by ECCV, 2018.
  • 26th July, 2017: Our team at Malong got the 1st place on the WebVision Challenge at CVPR 2017. [ Result ]
  • 17th July, 2017: One paper is accepted by ICCV 2017 as a spotlight paper.
  • 26th June, 2017: One paper is accapted by MICCAI-17 for oral presentation.
  • 17th November, 2016: Codes and models for our ECCV work on text detection are released.
  • 13rd July, 2016: One paper is accapted by ECCV, 2016.
  • 10th Dec, 2015: Our SIAT_MMLAB team got the 2nd place on Scene Classification at ILSVRC (ImageNet) 2015. [ Result ]

Publications [Google Scholar]

Cross-Batch Memory for Embedding Learning (Best Paper Nomination)
Xun Wang, Haozhi Zhang, Weilin Huang, and Matthew R. Scott
Technical report, arXiv:1912.06798, December, 2020. [PDF]
IEEE Computer Vision and Pattern Recognition (CVPR), 2020. (Oral)
[ PDF] [ Codes/Models]
Deformable Siamese Attention Networks for Visual Object Tracking
Yuechen Yu, Yilei Xiong, Weilin Huang, and Matthew R. Scott
IEEE Computer Vision and Pattern Recognition (CVPR), 2020.
[ PDF] [ Codes/Models]

Representation Sharing for Fast Object Detector Search and Beyond
Yujie Zhong, Zelu Deng, Sheng Guo, Matthew R. Scott, and Weilin Huang
European Conference on Computer Vision (ECCV), 2020.
[ PDF]
V4D: 4D Covolutional Neural Networks for Video-level Representations
Shiwen Zhang, Sheng Guo, Weilin Huang, Matthew R. Scott, and Limin Wang
The 8th International Conference on Learning Representations (ICLR), 2020.
[ PDF] [ Codes/Models]
Knowledge Integration Networks for Action Recognition
Shiwen Zhang, Sheng Guo, Limin Wang, Weilin Huang, and Matthew R. Scott
The 34th AAAI Conference on Artificial Intelligence (AAAI-20), 2020.
[ PDF]
iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
Chenfan Zhuang, Xintong Han, Weilin Huang, and Matthew R. Scott
The 34th AAAI Conference on Artificial Intelligence (AAAI-20), 2020.
[ PDF]
Channel Interaction Networks for Fine-Grained Image Categorization
Yu Gao, Xintong Han, Xun Wang, Weilin Huang, and Matthew R. Scott
The 34th AAAI Conference on Artificial Intelligence (AAAI-20), 2020.
[ PDF]
FiNet:Compatible and Diverse Fashion Image Inpainting
Xintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott, and Larry S. Davis
Technical report, arXiv:1902.01096, February, 2019. [PDF]
IEEE International Conference on Computer Vision (ICCV), 2019. (Oral)

Convolutional Character Networks
Linjie Xing, Zhi Tian, Weilin Huang, and Matthew R. Scott
IEEE International Conference on Computer Vision (ICCV), 2019.
[ PDF] [ Codes/Models]
ClothFlow: A Flow-Based Model for Clothed Person Generation
Xintong Han, Xiaojun Hu, Weilin Huang, and Matthew R. Scott
IEEE International Conference on Computer Vision (ICCV), 2019.
[ PDF]
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
Weifeng Ge, Sheng Guo, Weilin Huang, and Matthew R. Scott
IEEE International Conference on Computer Vision (ICCV), 2019.
[ PDF]
The iMaterialist Fashion Attribute Dataset
Sheng Guo, Weilin Huang, Xiao Zhang, Prasanna Srikhanta, Yin Cui, Yuan Li, Hartwig Adam, Matthew R Scott, Serge Belongie.
Computer Vision for Fashion, Art, and Design Workshop, IEEE International Conference on Computer Vision (ICCV), 2019. (Best Paper Award)
[ PDF] [ Codes/Models]
Dual-Stream Pyramid Registration Network
Xiaojun Hu, Miao Kang, Weilin Huang, Matthew R. Scott, Roland Wiest, and Mauricio Reyes
Technical report, arXiv:1909.11966, September, 2019. [PDF]
The 20th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019. (Oral)

Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning
Xun Wang, Xintong Han, Weilin Huang, Dengke Dong, and Matthew R. Scott
Technical report, arXiv:1808.01097, April, 2019. [PDF]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[ PDF] [ Codes/Models]
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R. Scott, and Dinglong Huang
Technical report, arXiv:1808.01097, August, 2018. [PDF]
European Conference on Computer Vision (ECCV), 2018.
[ PDF] [ Codes/Models]
Deep Metric Learning with Hierarchical Triplet Loss
Weifeng Ge, Weilin Huang, Dengke Dong, and Matthew R. Scott
European Conference on Computer Vision (ECCV), 2018.
[PDF]
An End-to-End TextSpotter with Explicit Alignment and Attention
Tong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, and Changming Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[PDF] [Codes/Models]
Single Shot Text Detector with Regional Attention
Pan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, and Xiaolin Li
IEEE International Conference on Computer Vision (ICCV), 2017. (Spotlight)
[PDF] [Online Demo] [Codes/Models]
Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video
Weilin Huang, Christopher P. Bridge, J. Alison Noble, and Andrew Zisserman
Technical report, arXiv:1707.00665, July, 2017. [PDF]
The 20th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI-17), 2017. (Oral)
Detecting Text in Natural Image with Connectionist Text Proposal Network
Zhi Tian, Weilin Huang, Tong He, Pan He and Yu Qiao
European Conference on Computer Vision (ECCV), 2016.
[PDF] [Online Demo] [Codes/Models(Caffe)] [Codes/Models(TensorFlow)]
Reading Scene Text in Deep Convolutional Sequences
Pan he*, Weilin Huang*, Yu Qiao, Chen Change Loy and Xiaoou Tang
Technical report, arXiv:1506.04395, June, 2015. [PDF]
The 30th AAAI Conference on Artificial Intelligence (AAAI-16), 2016. (Oral) [PDF] (* indicates equal contribution)
Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
Limin Wang, Sheng Guo, Weilin Huang, Yuanjun Xiong and Yu Qiao
Technical report, arXiv:1610.01119, October, 2016.
IEEE Trans. on Image Processing (TIP), vol. 26, pp.2055 - 2068, 2017.
[PDF] [Codes/Models]
Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
Tong He, Weilin Huang, Yu Qiao and Jian Yao
Technical report, arXiv:1603.09423, March, 2016. [PDF]
Text-Attentional Convolutional Neural Networks for Scene Text Detection
Tong He, Weilin Huang, Yu Qiao and Jian Yao
Technical report, arXiv:1510.03283, October, 2015. [PDF]
IEEE Trans. on Image Processing (TIP), vol.25, pp.2529-2541, 2016. [PDF]
Locally-Supervised Deep Hybrid Model for Scene Recognition
Sheng Guo, Weilin Huang, Limin Wang and Yu Qiao
Technical report, arXiv:1601.07576, 2015. [PDF]
IEEE Trans. on Image Processing (TIP), vol. 26, pp.808 - 820, 2017.
Local Multi-Grouped Binary Descriptor with Ring-based Pooling Configuration and Optimization
Yongqiang Gao, Weilin Huang and Yu Qiao
IEEE Trans. on Image Processing (TIP), vol.24, pp.4820-4833, 2015. [PDF]
Robust Scene Text Detection with Convolution Neural Network Induced MSER Tree
Weilin Huang, Yu Qiao and Xiaoou Tang
European Conference on Computer Vision (ECCV), 2014. [PDF]
Text Localization in Natural Images using Stroke Feature Transform and Text Covariance Descriptors
Weilin Huang, Zhe Lin, Jianchao Yang and Jue Wang
IEEE International Conference on Computer Vision (ICCV), 2013. [PDF]
Robust Face Recognition with Structural Binary Gradient Patterns
Weilin Huang and Yujun Yin
Technical report, arXiv:1506.00481, 2015. [PDF]
Pattern Recognition (PR), vol.68, pp.126-140, 2017. [PDF]
On Nonlinear Dimensionality Reduction for Face Recognition
Weilin Huang and Hujun Yin
Image and Vision Computing (IVC), vol.30, pp.355-366, 2012. [PDF]
Adaptive Nonlinear Manifolds and Their Applications to Pattern Recognition
Hujun Yin and Weilin Huang
Information Sciences (IS), vol.180, pp.2649–2662, 2010. [PDF]
A Dissimilarity Kernel with Local Features for Robust Facial Recognition
Weilin Huang and Hujun Yin
IEEE International Conference on Image Processing (ICIP), 2010. [PDF]

Journal Reviewers/Conference Program Committee (PC)

PC Member/Reviewer of CVPR (2017, 2018, 2019), ICCV (2017, 2019), ECCV (2016, 2018), MICCAI (2018, 2019), AAAI(2016-2019), IJCAI (2016, 2019)
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal of Computer Vision (IJCV)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Circuits and Systems for Video Technology
IEEE Transactions on Multimedia
IEEE Transactions on Systems, Man, and Cybernetics (SMC), Part B
Others:Pattern Recognition, Computer Vision and Image Understanding, Neurocomputing, IEEE Transactions on Cybernetics, IEEE Signal Processing Letter, Computer Vision and Image Understanding, Pattern Recognition Letters

Patents

[1] "METHODS AND APPARATUS FOR RECOGNIZING TEXT IN AN IMAGE", International Patent: PCT/CN2015/081308.
with Xiaoou Tang, Yu Qiao, Chen Change Loy and Pan He.
[2] "SCENE TEXT DETECTION SYSTEM AND METHOD" International Patent: PCT/CN2014/000830<.
with Xiaoou Tang and Yu Qiao.
[3] "TEXT DETECTION IN NATURAL IMAGES" US Patent:33121US01.
with Jue Wang, Zhe Lin and Jianchao Yang.

Last Updated on 19 August, 2016