Peng Xu     徐 鹏

postdoctoral research fellow

About Me

A postdoctoral research fellow in School of Computer Science and Engineering, Nanyang Technological University (NTU). My supervisor is Prof. Xavier Bresson. My current research is broadly in graph neural network, free-hand sketch recognition and retrieval, cross-modal computing, computer vision, deep learning, and machine learning.

In 2019, I received my Ph.D. degree from Pattern Recognition and Intelligent System Laboratory (PRIS) in Beijing University of Posts and Telecommunications (BUPT), supervised by Prof. Jun Guo.

During 2017 to 2018, I was a visiting student in sketchX Lab, Vision Group, in EE&CS in Queen Mary University of London (QMUL), supervised by Prof. Tao Xiang and Dr. Yi-Zhe Song. Dr. Timothy Hospedales from University of Edinburgh also helps me in research.

I was a visiting student in National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China, during March 2016 to June 2017, supervised by Prof. Liang Wang.

News

[August, 2020] Our paper "Fine-Grained Instance-Level Sketch-Based Video Retrieval" is accepted by IEEE TCSVT. [link]

[June, 2020] Our paper "Deep Self-Supervised Representation Learning for Free-Hand Sketch" is accepted by IEEE TCSVT. [link]

[May, 2020] Was invited as an area chair for multi-media track on IEEE TENCON 2020

[March, 2020] Released TorchSketch, the first sketch-oriented open-source deep learning library. [code]

[Jan 8, 2020] Released my paper "Deep Learning for Free-Hand Sketch: A Survey" on arXiv. [paper], [code]

[Dec 24, 2019] Released our paper "Multi-Graph Transformer for Free-Hand Sketch Recognition" on arXiv. [paper], [code]

[May 31, 2019] Ranked in 8th place in EPIC-Kitchens Action Recognition Challenges @CVPR2019.

[May 29, 2019] Passed thesis defense with an average score of 92.4/100.

[May 14, 2019] Released an unofficial PyToch implementation for MobileNetV3 with pretrained model on ImageNet. [code]. See [link] for media coverage.

[04/2019] Released an unofficial PyToch implementation for SiamRPN++ tracker (CVPR2019). [code]. See [link], [link], [link], [link] for media coverage.

[04/2018] Passed Juniper JNCIA-Junos exam, in London!

[02/2018] One paper has been accepted as poster by CVPR 2018 !

[12/2017] Be a Research Associate (visiting PhD student) in sketchX Lab, Vision Group, in EE&CS in Queen Mary University of London (QMUL) !

Contact Information

Address:    SCSE, Block N4, Nanyang Avenue, Singapore.       No.10 Xitucheng Road, Haidian District, Beijing, China.        Mile End Road, E1 4NS, London, UK.

Email:    peng.xu [AT] ntu.edu.sg       peng.xu@bupt.edu.cn        p.xu@qmul.ac.uk

Links:    [My Google Scholar profile]     [My Github profile]

Selected Publications

Preprint Papers

Peng Xu, et al., "Deep Learning for Free-Hand Sketch: A Survey and A Toolbox", arXiv:2001.02600, 2020. (under review) [paper] [code]

Peng Xu, et al., “On Learning Semantic Representations for Million-Scale Free-Hand Sketches”, arXiv:2007.04101, 2020. [paper]

Peng Xu, et al., “Multi-Graph Transformer for Free-Hand Sketch Recognition”, arXiv:1912.11258, 2019. (under review) [paper] [code]

Conference Papers

Y. Xie*, P. Xu*, and Z. Ma. “Deep zero-shot learning for scene sketch”, in ICIP, 2019. (Oral) (* equal contributor) [paper]

P. Xu, Y. Huang, T. Yuan, K. Pang, Y.-Z. Song, T. Xiang, T. Hospedales, Z. Ma, J. Guo, “Sketch-Mate: Deep Hashing for Million-Scale Human Sketch Retrieval”, in CVPR, 2018. [paper]

P. Xu, Q. Yin, Y. Qi, Y.-Z. Song, Z. Ma, L. Wang, J. Guo, “Instance-level Coupled Subspace Learning for Fine-grained Sketch-based Image Retrieval”, in ECCV workshops, 2016. (Oral) [code]

P. Xu, K. Li, Z. Ma, Y.-Z. Song, L.Wang, and J. Guo. “Crossmodal subspace learning for sketch-based image retrieval: A comparative study”, in Proceedings of 5th IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC), 2016. (Best Paper Award)

Journal Papers

Peng Xu, et al., “Fine-Grained Instance-Level Sketch-Based Video Retrieval”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020. [paper]

P. Xu, Z. Song, Q. Yin, Y. Song, L. Wang, “Deep Self-Supervised Representation Learning for Free-Hand Sketch”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020. [paper] [code]

J. Feng, P. Xu, S. Pu, K. Zhao, H. Zhang, “Robust Visual Tracking by Embedding Combination and Weighted-Gradient Optimization”, Pattern Recognition (PR), 2020.

P. Xu, Q. Yin, Y. Huang, Y.-Z. Song, Z. Ma, L. Wang, J. Guo, T. Xiang, W.B. Kleijn, “Cross-modal Subspace Learning for Subcategory-level and Instance-level Sketch-based Image Retrieval”, Neurocomputing, 2018. [paper]

Academic Experience

Research Assistant (Open Project of NLPR) National Laboratory of Pattern Recognition, Chinese Academy of Sciences. March 2016 - June 2017, Beijing, China

Internship Experience

iQIYI, Inc. Software Engineer Intern January 2014 - September 2014 Beijing, China

Academic Service

Review for CVPR, ICCV, AAAI, TNNLS, CVIU, ACCV, WACV, ICME, etc.

Teaching

ECS797P - Machine Learning for Visual Data Analysis , Spring, 2018, in QMUL.

Selected Computer Certifications

Junos (JNCIA-Junos) (April 2018)

TCP/IP Protocols Cisco-CCNA (August 2010)

Linux Redhat-RHCE (February 2011)