photo

Yunchao Wei 魏云超

Lecturer (Assistant Professor) / ARC DECRA Fellow

ReLER | Centre for Artificial Intelligence | University of Technology Sydney

Office: Room 123, Level 10, Building 11, 81 Broadway, Ultimo NSW 2007 (PO Box 123)

Email: Yunchao.Wei AT uts.edu.au | wychao1987 AT gmail.com

  Google Scholar

About Me

I received PhD from Beijing Jiaotong University, advised by Prof. Zhao Yao. Before joining UTS, I was a Postdoc Researcher in Prof. Thomas Huang's Image Formation and Professing (IFP) group at Beckman Institute, UIUC, from 2017 to 2019. I was a Visiting Student from 2013 to 2015 and a Postdoc Researcher from 2016 to 2017 in the Learning and Vision (LV) Research Group at National University of Singapore (NUS), working with Prof. Shuicheng Yan and Prof. Jiashi Feng.



Research Interests

Deep learning and its applications in computer vision, including image classification, object detection, semantic segmentation, etc.


News

  • I'm going to co-organize the workshop on "Real-World Recognition from Low-Quality Images and Videos (RLQ)" in ICCV 2019. More details please refer to [link].
  • I'm going to co-organize the workshop on "Weakly Supervised Learning for Real-World Computer Vision Applications and the 1st Learning from Imperfect Data (LID) Challenge" in CVPR 2019. More details please refer to [link].
  • I'm going to co-organize the workshop on "Augmented Human: Human-centric Understanding and 2D/3D Synthesis, and the third Look Into Person (LIP) Challenge" in CVPR 2019. More details please refer to [link].
  • The slides of VALSE-2019-Workshop and VALSE-2019-Tutorial are avaliable now!
  • Four papers accepted in AAAI 2019 and one paper accepted by PR.
  • One paper accepted in NIPS 2018.
  • Three papers accepted in ECCV 2018.
  • BJTU-UIUC team won the 1st places in all three human parsing tracks in the 2nd LIP Challenge.
          Members: Ting Liu*, Tao Ruan*, Yunchao Wei, Jie Zhao, Shikui Wei, Honghui Shi, Jinjun Xiong, Yao Zhao, Thomas Huang
  • Three papers accepted in CVPR 2018 with one oral and one spotlight. One paper accepted by TMM.
  • NUS-Qihoo-UIUC_DPNs team won the 2nd places in all four video-related tracks in ILSVRC 2017.
          Members: Yunchao Wei, Mengdan Zhang, Honghui Shi, Jianan Li, Yunpeng Chen, Jiashi Feng, Jian Dong, Shuicheng Yan
  • Two papers accepted in ACM MM 2017 and one paper accepted in ICCV 2017.
  • Three papers accepted in CVPR 2017 with one oral and one spotlight.
  • One paper accepted in ICME 2017.

Publications

Technique Reports

Self-Correction for Human Parsing
Peike Li, Yunqiu Xu, Yunchao Wei, Yi Yang
[arxiv][CODE]
Note: Our latest progress on human parsing won the 1st place of the 3rd LIP Challenge in CVPR 2019.

Revisiting Pre-training: An Efficient Training Method for Image Classification
Bowen Cheng, Yunchao Wei, Honghui Shi, Shiyu Chang, Jinjun Xiong, Thomas S. Huang
[arxiv]

SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
Xiaolin Zhang, Yunchao Wei, Yi Yang, Thomas Huang
[arxiv] [CODE]

Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, Jinjun Xiong, Thomas Huang
[arxiv] [CODE]

Towards Real World Human Parsing: Multiple-Human Parsing in the Wild
Jianshu Li, Jian Zhao, Yunchao Wei, Congyan Lang, Yidong Li, Jiashi Feng
[arxiv]

2019

SPGNet: Semantic Prediction Guidance for Scene Parsing
Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, Jinjun Xiong, Thomas Huang, Wen-Mei Hwu, Honghui Shi
IEEE International Conference on Computer Vision (ICCV), 2019
[PDF]

Integral Object Mining via Online Attention Accumulation
Peng-Tao Jiang, Qibin Hou, Yang Cao, Ming-Ming Cheng, Yunchao Wei, Hong-Kai Xiong
IEEE International Conference on Computer Vision (ICCV), 2019
[Project]

CCNet: Criss-Cross Attention for Semantic Segmentation
Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, Wenyu Liu
IEEE International Conference on Computer Vision (ICCV), 2019
[arxiv] [CODE]

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
Yang Fu, Yunchao Wei, Guanshuo Wang, Yuqian Zhou, Honghui Shi, Thomas Huang
IEEE International Conference on Computer Vision (ICCV), 2019 (oral)
[arxiv] [CODE]

Boundary Perception Guidance: A Scribble-Supervised Semantic Segmentation Approach
Bin Wang, Guojun Qi, Sheng Tang, Tianzhu Zhang, Yunchao Wei, Linghui Li, Yongdong Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2019

Geometry-Aware Distillation for Indoor Semantic Segmentation
Jianbo Jiao, Yunchao Wei, Zequn Jie, Honghui Shi, Rynson W.H. Lau, Thomas S. Huang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms
Canyi Lu, Xi Peng, Yunchao Wei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Magic-wall: Visualizing Room Decoration by Enhanced Wall Segmentation
Ting Liu, Yunchao Wei, Yao Zhao, Si Liu, Shikui Wei
IEEE Transactions on Image Processing (TIP), 2019

Concealed Object Detection for Activate Millimeter Wave Image
Ting Liu, Yao Zhao, Yunchao Wei, Yufeng Zhao, Shikui Wei
IEEE Transactions on Industrial Electronics (TIE), 2019

Devil in the Details: Towards Accurate Single and Multiple Human Parsing
Tao Ruan, Ting Liu, Zilong Huang, Yunchao Wei, Shikui Wei, Yao Zhao, Thomas Huang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019
[arxiv] [CODE]
Note: This work achieves the 1st places on all human paring tracks in the 2nd LIP Challenge

Weakly Supervised Scene Parsing with Point-based Distance Metric Learning
Rui Qian, Yunchao Wei, Honghui Shi, Jiachen Li, Jiaying Liu, Thomas Huang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019
[arxiv]

STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification
Yang Fu, Xiaoyang Wang, Yunchao Wei, Thomas Huang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019
[arxiv]

Horizontal Pyramid Matching for Person Re-identification
Yang Fu, Yunchao Wei, Yuqian Zhou, Honghui Shi, Gao Huang, Xinchao Wang, Zhiqiang Yao, Thomas Huang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019
[PDF]

IAN: The Individual Aggregation Network for Person Search
Jimin Xiao, Yanchun Xie, Tammam Tillo, Kaizhu Huang, Yunchao Wei, Jiashi Feng
Pattern Recognition (PR), 2019
[PDF]

2018

Self-Erasing Network for Integral Object Attention
Qibin Hou, Peng-Tao Jiang, Yunchao Wei, Ming-Ming Cheng
Neural Information Processing Systems (NIPS), 2018
[PDF] [Project]

TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
Yunchao Wei, Zhiqiang Shen, Bowen Cheng, Honghui Shi, Jinjun Xiong, Jiashi Feng, Thomas Huang
European Conference on Computer Vision (ECCV), 2018
[PDF]

Self-produced Guidance for Weakly-supervised Object Localization
Xiaolin Zhang, Yunchao Wei, Guoliang Kang, Yi Yang, Thomas Huang
European Conference on Computer Vision (ECCV), 2018
[PDF] [CODE]

Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, Jinjun Xiong, Thomas Huang
European Conference on Computer Vision (ECCV), 2018
[PDF]

Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
Yunchao Wei, Huaxin Xiao, Honghui Shi, Zequn Jie, Jiashi Feng, Thomas Huang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (spotlight)
[PDF] [Project] [Prototxt]

Adversarial Complementary Learning for Weakly Supervised Object Localization
Xiaolin Zhang, *Yunchao Wei, Jiashi Feng, Yi Yang, Thomas Huang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[PDF] [CODE]

Left-Right Comparative Recurrent Model for Stereo Matching
Zequn Jie, Pengfei Wang, Yonggen Ling, Bo Zhao, Yunchao Wei, Jiashi Feng, Wei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (oral)
[PDF]

Deep Salient Object Detection with Dense Connections and Distraction Diagnosis
Huaxin Xiao, Jiashi Feng, Yunchao Wei, Maojun Zhang
IEEE Transactions on Multimedia (TMM), 2018
[PDF] [CODE] Note: This work provides the state-of-the-art solution for saliency object detection.

Transferable Semi-supervised Semantic Segmentation
Huaxin Xiao, Yunchao Wei, Yu Liu, Maojun Zhang, Jiashi Feng
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2018
[PDF]

Proposal-free network for instance-level object segmentation
Xiaodan Liang, Yunchao Wei, Xiaohui Shen, Jianchao Yang, Liang Lin, Shuicheng Yan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
[arxiv]

2017

Multi-stage Object Detection with Group Recursive Learning
Jianan Li, Xiaodan Liang, Jianshu Li, Yunchao Wei, Tingfa Xu, Jiashi Feng, Shuicheng Yan
IEEE Transactions on Multimedia (TMM), 2017

Regional Interactive Image Segmentation Networks
Jun Hao Liew, Yunchao Wei, Wei Xiong, Sim-Heng Ong, Jiashi Feng
IEEE International Conference on Computer Vision (ICCV), 2017

Magic-wall: Visualizing Room Decoration
Ting Liu, Yunchao Wei, Yao Zhao, Si Liu, Shikui Wei
ACM Multimedia (MM), 2017 (oral)

Deep Attribute-preserving Metric Learning for Natural Language Object Retrieval
Jianan Li, Yunchao Wei, Xiaodan Liang, Fang Zhao, Tingfa Xu, Jiashi Feng
ACM Multimedia (MM), 2017

Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
Yunchao Wei, Jiashi Feng, Xiaodan Liang, Ming-Ming Cheng, Yao Zhao, Shuicheng Yan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (oral)
[PDF]

Deep Self-taught Learning for Weakly Supervised Object Detection
Zequn Jie, Yunchao Wei, Xiaojie Jin, Jiashi Feng, Wei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (spotlight)
[PDF]

Perceptual Generative Adversarial Networks for Small Object Detection
Jianan Li, Xiaodan Liang, Yunchao Wei, Tingfa Xu, Jiashi Feng, Shuicheng Yan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
[PDF]

Enhanced Isomorphic Semantic Representation for Cross-media Retrieval
Ting Liu, Yao Zhao, Shikui Wei, Lixin Liao, Yunchao Wei
IEEE International Conference on Multimedia and Expo (ICME), 2017
[PDF] [CODE]

Attentive Contexts for Object Detection
Jianan Li*, Yunchao Wei*, Xiaodan Liang, Jian Dong, Tingfa Xu, Jiashi Feng, Shuicheng Yan
IEEE Transactions on Multimedia (TMM), 2017
[PDF]

STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, Ming-Ming Cheng, Jiashi Feng, Yao Zhao, Shuicheng Yan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017
[PDF] [SUPP] [Project] [Bibtex]

2016

Learning to Segment Human by Watching YouTube
Xiaodan Liang, Yunchao Wei, Yunpeng Chen, Xiaohui Shen, Jianchao Yang, Liang Lin, Shuicheng Yan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016
[PDF]

Reversible Recursive Instance-level Object Segmentation
Xiaodan Liang, Yunchao Wei, Xiaohui Shen, Zequn Jie, Jiashi Feng, Liang Lin, Shuicheng Yan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[PDF]

HCP: A Flexible CNN Framework for Multi-label Image Classification
Yunchao Wei, Wei Xia, Min Lin, Junshi Huang, Bingbing Ni, Jian Dong, Yao Zhao, Shuicheng Yan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016
[PDF] [SUPP] [Project] [Bibtex]

Cross-Modal Retrieval With CNN Visual Features: A New Baseline
Yunchao Wei, Yao Zhao, Canyi Lu, Shikui Wei, Luoqi Liu, Zhenfeng Zhu, Shuicheng Yan
IEEE Transactions on Cybernetics (TCYB), 2016
[PDF] [Project] [Bibtex]

Learning to segment with image-level annotations
Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Zequn Jie, Yanhui Xiao, Yao Zhao, Shuicheng Yan
Pattern Recognition (PR), 2016
[PDF]

Modality-Dependent Cross-Media Retrieval
Yunchao Wei, Yao Zhao, Zhenfeng Zhu, Shikui Wei, Yanhui Xiao, Jiashi Feng, Shuicheng Yan
ACM Transactions on Intelligent Systems and Technology (TIST), 2016
[PDF] [Project] [Bibtex]

Instance-Aware Hashing for Multi-Label Image Retrieval
Hanjiang Lai, Pan Yan, Xiangbo Shu, Yunchao Wei, Shuicheng Yan
IEEE Transactions on Image Processing (TIP), 2016
[PDF]

Object proposal generation with fully convolutional networks
Zequn Jie, Wen Feng Lu, Siavash Sakhavi, Yunchao Wei, Eng Hock Francis Tay, Shuicheng Yan
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016
[PDF]

Deep Learning with S-Shaped Rectified Linear Activation Units
Xiaojie Jin, Chunyan Xu, Jiashi Feng, Yunchao Wei, Junjun Xiong, Shuicheng Yan
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2016
[PDF]

3D video super-resolution using fully convolutional neural networks
Yanchun Xie, Jimin Xiao, Tammam Tillo, Yunchao Wei, Yao Zhao
IEEE International Conference on Multimedia and Expo (ICME), 2016
[PDF]

2015

Kernel Reconstruction ICA for Sparse Representation
Yanhui Xiao, Zhenfeng Zhu, Yao Zhao, Yunchao Wei, Shikui Wei
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2015
[PDF]

Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection
Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, Shuicheng Yan
IEEE International Conference on Computer Vision (ICCV), 2015
[PDF]

Heterogeneous data alignment for cross-media computing
Shikui Wei, Yunchao Wei, Lei Zhang, Zhenfeng Zhu, Yao Zhao
International Conference on Internet Multimedia Computing and Service (ICIMCS), 2015

2014

Topographic NMF for data representation
Yanhui Xiao, Zhenfeng Zhu, Yao Zhao, Yunchao Wei, Shikui Wei, Xuelong Li
IEEE Transactions on Cybernetics (TCYB), 2014
[PDF]

Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Nonconvex Sparsity Optimization
Canyi Lu, Yunchao Wei, Zhouchen Lin, Shuicheng Yan
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2014
[PDF]

Learning a mid-level feature space for cross-media regularization
Yunchao Wei, Yao Zhao, Zhenfeng Zhu, Yanhui Xiao, Shikui Wei:
IEEE International Conference on Multimedia and Expo (ICME), 2014
[PDF]

2013 and Earlier

Class-Driven Non-Negative Matrix Factorization for Image Representation
Yanhui Xiao, Zhenfeng Zhu, Yao Zhao, Yunchao Wei
Journal of Computer Science and Technology (JCST), 2013

Knowledge Transferring for Image Classification
Yunchao Wei, Yao Zhao, Zhenfeng Zhu, Yanhui Xiao
Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2012


Selected Award

  • 2018 The Winner Prizes of All Human Parsing Tasks in the 2nd LIP Challenge
  • 2017 The Runnerup Prizes of All Video Object Detection/Tracking Tasks in ILSVRC
  • 2016 Excellent Doctoral Dissertation Award of CIE
  • 2016 Excellent Doctoral Dissertation Award of Beijing Jiaotong University
  • 2014 National Scholarship
  • 2014 The Winner Prize of Object Detection Task 1a in ILSVRC
  • 2013 Huawei Scholarship

Research Resources