Zhiyuan Shi

I am a Machine Learning/Computer Vision Researcher at Onfido. Previously I was a postdoctoral associate at Imperial College London, working with Tae-Kyun Kim. I completed my PhD in Computer Science at Queen Mary, University of London in 2016 (advised by Tao Xiang, Timothy Hospedales and Shaogang Gong). Before that I graduated from BUPT with a Bachelor of Science in Electronic Engineering. I am interested in computer vision (action recognition, object localisation, attribute learning) and machine learning (deep learning, probabilistic graphical models, weakly supervised learning).


zhiyuan.shi 'AT' onfido.com / Google Scholar / LinkedIn

Zhiyuan Shi


Publications

Kinematic-Layout-aware Random Forests for Depth-based Action Recognition
Seungryul Baek, Zhiyuan Shi, Masato Kawade, Tae-Kyun Kim
British Machine Vision Conference (BMVC)
London, UK, September 2017.

arXiv | PDF | Bibtex

Learning and Refining of Privileged Information-based RNNs for Action Recognition from Depth Sequences
Zhiyuan Shi, Tae-Kyun Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hawaii, USA, July 2017.

arXiv | PDF | Bibtex | Video

Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes
Zhiyuan Shi, Yongxin Yang, Timothy M. Hospedales and Tao Xiang
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI)
2017


arXiv | PDF | Bibtex | SUP

Transferring a Semantic Representation for Person Re-Identification and Search
Zhiyuan Shi, Timothy M. Hospedales and Tao Xiang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Boston, USA, June 2015.

arXiv | PDF | Bibtex | CMC curve | SUP

Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images
Zhiyuan Shi, Timothy M. Hospedales and Tao Xiang
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI)
2015


arXiv | PDF | Bibtex | SUP

Weakly Supervised Learning of Objects, Attributes and their Associations
Zhiyuan Shi, Yongxin Yang, Timothy M. Hospedales and Tao Xiang
European Conference on Computer Vision (ECCV)
Zurich, Switzerland, September 2014.

arXiv | PDF | Bibtex | Video

Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation
Zhiyuan Shi, Timothy M. Hospedales and Tao Xiang
International Conference on Computer Vision (ICCV)
Sydney, Australia, ICCV 2013.

arXiv | PDF | Bibtex | SUP | Video

Transfer Learning by Ranking for Weakly Supervised Object Annotation
Zhiyuan Shi, Parthipan Siva and Tao Xiang
British Machine Vision Conference (BMVC)
Surrey, UK, September 2012.

arXiv | PDF | Bibtex


Jon Barron and Li Zhang have an awesome website =)