Yi   Li

Senior Researcher, Computer Vision, NICTA     (old page)
yi dot li at nicta dot com dot au
L1-31, Tower A, 7 London Circuit, Canberra, ACT 2601
office: +61 2 6267 6236

Adjunct Lecturer, CECS, ANU
yi dot li at cecs dot anu dot edu dot au

Research Interests

Computer Vision, Machine Learning, Human Pose Analysis, Cognitive Robotics, and Bionic Vision.


Dr. Yi Li received his Ph.D from the ECE Dept. at the University of Maryland at College Park. He joined NICTA as a Researcher since 2011 in the Visual Processing for Bionic Eye (VIBE) project, and was promoted to Senior Researcher in 2013. He was the recipient Future Faculty Fellow at Maryland from 2008-2010, received the Best Student paper of ICHFR, and the second price in the Semantic Robot Vision Challenge (SRVC). His recent areas of interest include human pose estimation and deep learning for computer vision.

He was the session chair for CVPR 2014, co-chair for the DeepVision: Deep Learning for Computer Vision workshop in conjunction with CVPR 2014 and 2015, area chair of the WACV 2015, and served in the TPC of a number of conferences and workshops such as ACM Multimedia 2015 and DICTA 2015. He was invited to give talks in the University of Tokyo, NIST, AT&T Labs, and ACCV 2014 workshop. His work on deep learning and robotics was recently interviewed by Compass (UK), SBS and Channel 9 (AU) and TheAustralian (AU), and was reported by Washington Post, Fox News, USA Today, Discovery Channel, as well as other major US media.


'Semantic Vectorization: From Bitmaps to Intelligent Representations' (A$ 370,100) from the Australian Research Council, with Fatih Porikli and Mehrtash Harandi.

Organization Activities

Deep Vision 2: Deep learning for Computer Vision Workshop, in conjunction with CVPR 2015 with Yann Lecun, Jose Alvarez, and Fatih Porikli

Deep Vision: Deep learning for Computer Vision Workshop, in conjunction with CVPR 2014 with Yann Lecun, Jose Alvarez, and Fatih Porikli

Session Chair: CVPR 2014, ICPR 2012

Area Chair, WACV 2015

TPC: DICTA 2014, Deep Learning on Visual Data

Selected Publications

Deep Learning
F. Wang, L. Kang, and Y. Li, Sketch-based 3D Shape Retrieval using Convolutional Neural Net, CVPR 2015, (oral) (pdf, project/code)
Y. Yang, C. Fermuller, Y. Li, and Y. Aloimonos Grasp Type Revisited: A Modern Perspective on A Classical Feature for Vision, CVPR, 2015. (pdf)
Y. Yang, Y. Li, C. Fermuller, and Y. Aloimonos, Robot Learning Manipulation Action Plans by 'Watching' Unconstrained Videos From the World Wide, AAAI 2015, (oral). (pdf)
H. Li, Y. Li, and F. Porikli, DeepTrack: Learning Discriminative Feature Representations by Convolutional Neural Networks for Visual Tracking, BMVC 2014 (code)
L. Kang, Y. Peng, Y. Li, and D. Doermann, CNN for No-Reference Image Quality Assessment, CVPR 2014 (oral, pdf)
Q. Ke and Y. Li, Is Rotation a Nuisance in Shape Recognition?, CVPR 2014 (code/project, pdf)
L. Kang, P. Ye, Y. Li, and D. Doermann, A Deep Learning Approach to Document Image Quality Assessment, ICIP 2014
L. Kang, J. Kumar, P. Ye, Y. Li, and D.Doermann, Convolutional Neural Networks for Document Image Classification, ICPR 2014
Visual tracking
H. Zhu and Y. Li, Fast Inference of Contaminated Data for Real Time Object Tracking, ACCV 2014
Human Pose Estimation
F. Wang and Y. Li, Beyond Physical Connections: Tree Models in Human Pose Estimation, CVPR 2013, (oral) (oral) (pdf, project, code, relabeled LSP)
F. Wang and Y. Li, Learning Visual Symbols for Parsing Human Poses in Images, IJCAI 2013, (oral) (oral) (pdf)
A. Ausilio, L. Badino, Y. Li, S. Tokay, L. Craighero, et al., Leadership in Orchestra Emerges from the Causal Relationships of Movement Kinematics, PLoS ONE 7(5): e35757, 2012 (pdf)
Y. Li, C. Fermuller, Y. Aloimonos, and H. Ji, Learning shift-invariant sparse representation of actions, CVPR 2010 (pdf)
Recognizing texts in images
L. Kang, Y. Li, and D. Doermann, Orientation Robust Textline Detection in Natural Images, CVPR 2014 (pdf)
Y. Li, Y. Zheng, D. Doerman, and S. Jaeger, Script-Independent Text Line Segmentation in Freestyle Handwritten Documents, IEEE Trans. Pattern Anal. Machine Intell., vol. 30, no. 8, pp. 1313-1329, August, 2008 (pdf, code)
G. Zhu, X. Yu, Y. Li, and D. Doermann, Language Identification for Handwritten Document Images Using A Shape Codebook, Pattern Recognition, 2008 (pdf)
Y. Li, Z. Wang, and H. Zeng, Correlation Filter: An Accurate Approach to Detect and Locate Low Contrast Character Strings In Complex Table Environment, IEEE Trans. Pattern Anal. Machine Intell., vol. 26, no. 12, pp. 1639-1644, December, 2004
Image deblurring
F. Wang, T. Li, and Y. Li, Dual Deblurring Leveraged by Image Matching, ICIP 2013 (oral)
F. Wang and Y. Li, Robust Kernel Estimation for Single Image Blind Deconvolution, ICPR 2012 (oral) (pdf)
Object Recognition
Y. Li, K. Bitsakos, C. Fermuller, and Y. Aloimonos, Real-Time Shape Retrieval for Robotics Using Skip Tri-Grams, IROS 2009 (oral) (pdf)
G. Zhu, X. Yu, Y. Li and D. Doermann, Learning Visual Shape Lexicon for Document Image Content Recognition, ECCV 2008 (pdf)
Y. Li and D. Jacobs, Efficiently Determining Silhouette Consistency, CVPR 2007 (pdf)
X. Yu, Y. Li, C. Fermuller, and D. Doermann, Object Detection Using A Shape Codebook, BMVC 2007 (oral)
Bionic Eye
F. Wang and Y. Li, A Filtering process for human detection in Bionic Eye, EMBC 2013 (oral)
X. Tang and Yi Li, Lightness illusion: A new look from Compressive Sensing perspective, ICIP 2012
Y. Li, C. McCarthy, and N. Barnes, On Just Noticeable Di erence for Bionic Eye, EMBC 2012
N. Barnes, P. Lieby, H. Dennet, J. Walker, C. McCarthy, N. Liu, and Y. Li Investigating the role of single-viewpoint depth data in visually-guided mobility, Vision Science 2011


I am actively seeking motivated graduate students and visiting students around the world. NICTA is able to provide a full or top-up scholarship for PhD students and support visitors in various forms. Please send me your resume if you are interested in collaborating with me (though your formal application must through ANU admission office if you plan to pursue a graduate degree).

Chinese Scholarship Council (CSC) students: Australian National University and the China Scholarship Council (CSC) have a collaborative arrangement to provide research opportunities to select high quality research students from China. CSC scholarship recipients will be able to enrol in the ANU PhD program for up to four years full-time study. NICTA also welcomes the CSC visitors to collaborate in many projects.

PhD Students
Song Wang (with N. Barnes), Fang Wang, and K. Park (with S. Gould)
Master Students
Ashley Stacey (with N. Barnes), Andrew (with Dr. J. Zhang and Dr. J. Steel, NICTA)
Summer Scholar
Tianxing Li and Xinke Tang (RMIT)


ANU Computer Vision, ENGN 4528/6528 (2012)   syllabus   notes
NICTA Computer Vision Short Course (2011, 2012)

Locations of visitors to this page