"Luck is what happens when preparation meets opportunity."


  Yongcheng Jing

    MSc student in Computer Science

    Zhejiang University

    E-mail: ycjing AT zju DOT edu DOT cn

Short Bio [CV]

I am currently a graduate student at the Microsoft Visual Perception Laboratory (VIPA) of Zhejiang University (ZJU) and Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies (AZFT). I am fortunately advised by Prof. Mingli Song and Prof. Yizhou Yu.

I am also very fortunate to collaborate with Prof. Yezhou Yang and Prof. Dacheng Tao.

Prior to Zhejiang University, I received my BEng in Computer Science from the Elite Program at South China University of Technology (SCUT), where I worked on pattern recognition and computer vision under the supervision of Prof. Patrick P. K. Chan. I was awarded the Early Graduate Honor and graduated one year ahead of the expected graduation date in 2016. After that I was admitted as an MS candidate to Zhejiang University, exempt from the Graduate Entrance Exam.

Research Interests

  • Texture Modelling (MS)

  • Vision Algorithms in an Adversarial Environment (BEng)


2016.9 - 2019.3 (expected), MS in Computer Science and Technology, Zhejiang University (Exempt from Graduate Entrance Exam)

2013.9 - 2016.7, BEng in Computer Science and Technology, South China University of Technology (Elite Program of Computer Science, Graduated with Early Graduation Honor)

Selected Publications

[Google Scholar]

Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
Y Jing, Y Liu, Y Yang, Z Feng, Y Yu, D Tao, M Song.
European Conference on Computer Vision (ECCV), 2018.
[arXiv] [Project Page] [Code] [Video] [Supplementary] [Blog (in Chinese)] [Poster] [Bibtex]

The Fast Style Transfer methods have been recently proposed to transfer a photograph to an artistic style in real-time. This task involves controlling the stroke size in the stylized results, which remains an open challenge. In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.

Neural Style Transfer: A Review
Y Jing, Y Yang, Z Feng, J Ye, Y Yu, M Song.
IEEE Transactions on Visualization and Computer Graphics (TVCG), Under Review.
[arXiv] [Project Page] [Supplementary] [Blog (in Chinese)] [Media Coverage] [Bibtex]

Neural Style Transfer is an important computer vision task which is to exploit Convolutional Neural Networks to migrate the semantic content of one image to different styles. This review aims to present and summarize recent progress towards Neural Style Transfer, as well as discussing its various applications and open problems for future research.

Finer-Net: Cascaded Human Parsing with Hierarchical Granularity
J Ye, Z Feng, Y Jing, M Song.
IEEE International Conference on Multimedia and Expo (ICME), 2018. (Oral)

In this paper, we propose a cascaded human parsing architecture with hierarchical granularity from coarse to fine. The proposed framework can be extended according to the demands of concrete segmentation precision. Furthermore, we effectively use the human pose information predicted by convolutional pose machine beforehand to further improve the final results.

Interpretable Partitioned Embedding for Customized Fashion Outfit Composition
Z Feng, Z Yu, Y Yang, Y Jing, J Jiang, M Song.
ACM International Conference on Multimedia Retrieval (ICMR), 2018. (Oral)
[PDF] [Media Coverage]

In this paper, we propose a partitioned embedding network to learn interpretable representations from clothing items. Our proposed network can extract interpretable embeddings of fashion outfit items. Based on the extracted embeddings, we put forward a weakly-supervised fashion outfit composition model which depends solely on a large number of outfits without quality scores. We also propose a customized fashion outfit composition scheme.

Graph-based Color Gamut Mapping Using Neighbor Metric
Z Feng, Y Jing, C Zhang, R Xu, J Lei, M Song.
IEEE International Conference on Multimedia and Expo (ICME), 2017. (Oral)

In this paper, a new Multi-source Shortest Paths Algorithm (MSSPA) is proposed to establish color mapping relationships between out-of-gamut colors and colors in gamut boundary. Experimental results show that our method achieves superior performance on the aspect of keeping accuracy and preserving details compared with HPMinDE and SGCK.


A Review on Adversarial Attacks (June 4, 2018) [Slides]

Deep Image Aesthetics (Jan 17, 2018) [Slides]

Fast Neural Style Transfer (Aug 14, 2017) [Slides]

Recent Advances in Image Reconstruction (July 17, 2017) [Slides]

Generative Adversarial Networks: Recent Advances and Popular Application (Mar 20, 2017) [Slides]

Visualizing Convolutional Neural Networks: Image Reconstruction (Oct 17, 2016) [Slides]

Honors & Awards

National Scholarship (top 2%), Ministry of Education of China, 2018

Graduate of Merit/Triple A Graduate, ZJU, 2018

Award of Honor for Graduates, ZJU, 2018

Outstanding Reviewer for JVCI, 2017

National Scholarship (top 2%), Ministry of Education of China, 2017

Graduate of Merit/Triple A Graduate, ZJU, 2017

Award of Honor for Graduates, ZJU, 2017

Academic Scholarship, ZJU, 2016

Early Graduate Honor (top 5%), SCUT, 2016

“Hong Ping Chang Qing” Academic Scholarship, 2016

Honorable Mention in Interdisciplinary Contest In Modeling (administered by COMAP), 2015

Volunteer Stars Awards, SCUT, 2015

1st and 3rd Class Scholarships, SCUT, 2013 - 2016

The Elite Program of Computer Science (40 best students are chosen from about 1500 freshmen), 2013 - 2016

Academic Activities

Journal Reviewer:

  • Journal of Visual Communication and Image Representation (JVCI)

  • Information Sciences (INS)

  • The Visual Computer (TVC)

  • IET Computer Vision (IET-CVI)

  • Journal of Electronic Imaging (JEI)

Conference Reviewer:

  • Asian Conference on Computer Vision (ACCV)

Working Experience

  • Algorithm Engineer Intern, Taobao AI Team, Alibaba Group