Kaiyue Pang

Ph.D Candidate, SketchX Research Lab


Email: kaiyue.pang@qmul.ac.uk

About Me:

My recent research interest shifted to generative models for human sketch understanding and generation, especially on how such understanding can be transferred into commercial applications.

I am a second year Ph.D candidate at SketchX Research Lab , Queen Mary University of London. My supervisors are Dr. Yi-Zhe Song and Prof. Tao Xiang. Before that, I received the first-class B.S. degree from the Sino-UK Joint Programme held between Beijing University of Posts and Telecommunications and Queen Mary University of London. I'm honoured to deliver the valedictory speech to the class of 2016.


News:

Publications:

Jifei Song, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, " Learning to Sketch with Shortcut Cycle Consistency " IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo, " SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval " IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, " Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval " British Machine Vision Conference (BMVC), 2017.

Ke Li, Kaiyue Pang, Yi-Zhe Song, Timothy M. Hospedales, Tao Xiang, Honggang Zhang, " Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval " IEEE Transactions on Image Processing (TIP), Sep 2017, in press.

Ke Li, Kaiyue Pang, Yi-Zhe Song, Timothy M. Hospedales, Honggang Zhang, Yichuan Hu, " Fine-Grained Sketch-Based Image Retrieval: The Role of Part-Aware Attributes " IEEE Winter Conference on Applications of Computer Vision (WACV), 2016. (Oral)