Li, Wanqing

Overview

Wanqing Li received his B.Sc and M.Sc from Zhejiang University and PhD from The University of Western Australia, Australia. He joined Motorola Lab in Sydney (98-03) as a Senior Researcher and later a Principal Researcher. He received Motorola CTO’s Award in 2003 for his significant technical contribution to video-based motion analysis. He was a visiting researcher at Microsoft Research US in 2008, 2010 and 2013. He is currently an Associate Professor and Director of Advanced Multimedia Research Lab (AMRL) of University of Wollongong, Australia.
His research areas are machine learning, 3D computer vision and 3D multimedia signal processing and security, including 3D reconstruction, human motion analysis, human-computer interactions, detection of objects and events, immersive and free-viewpoint video, medical image processing and their applications to aged care and health monitoring. He is one of the earliest researchers and advocates of understanding human activities from 3D data, one of the most popular research topics now in computer vision and machine learning. His research results have expounded in one book and 180+ publications at prestigious journals and prominent conferences, such as TIP, IJCV, TNNLS, TCSVT, TMM, CVPR, ICCV, AAAI, IJCAI, ACM MM and ICME.

Research Areas

Research Overview

He mainly applies statistics and mathematics to spatial-temporal data analytics and his research interest spread across machine learning, pattern recognition, computer vision, neural networks, multimedia, image processing, video surveillance and their application to health. He pioneered in 2010 and nurtured in the subsequent years the research of understanding human activities from 3D data, one of the most popular research topics now in computer vision and machine learning. His research results have expounded in one book and 180+ publications at prestigious journals and prominent conferences, such as TIP, IJCV, TNNLS, TCSVT, TMM, CVPR, ICCV, AAAI and ACM MM. His publications have been cited in Google Scholar ~5500, his H-Index is 36 (all) and 33 (since 2015) in Google Scholar, 30 in Scopus. The highest citations of a single paper is 1250+ in Google Scholar.

Current Main Research Activities:
- Machine Learning - Statistical learning, deep learning
- 3D Computer Vision - Human activity understanding, human detection, gait recognition, 3D sensing and reconstruction from RGB-D data
- 3D Multimedia Signal Processing and Understanding – scene analysis and event detection
- Free Viewpoint Video (FVV) – Acquisition, processing, understanding and compression
- Medical Image Processing and Understanding – Image reconstruction for low-dose X-ray and fast MR imaging, segmentation of medical images

Available as Research Supervisor

Selected Publications

Journal Article

Year	Title
2020	A Review of Dynamic Maps for 3D Human Motion Recognition Using ConvNets and Its Improvement Published In Neural Processing Letters
2020	A hybrid network for large-scale action recognition from RGB and depth modalities Published In Sensors (Switzerland)
2020	Beyond Covariance: SICE and Kernel Based Visual Feature Representation Published In International Journal of Computer Vision
2020	Densely Connected Deep Extreme Learning Machine Algorithm Published In Cognitive Computation
2020	SAR-NAS: Skeleton-based action recognition via neural architecture searching Published In Journal of Visual Communication and Image Representation
2020	Sharkeye: Real-Time Autonomous Personal Shark Alerting via Aerial Surveillance Published In Drones
2019	A fully trainable network with RNN-based pooling Published In Neurocomputing
2019	ConvNets-based action recognition from skeleton motion maps Published In Multimedia Tools and Applications
2019	Jointly Learning Visual Poses and Pose Lexicon for Semantic Action Recognition Published In IEEE Transactions on Circuits and Systems for Video Technology
2019	Learning attentive dynamic maps (ADMs) for Understanding Human Actions Published In Journal of Visual Communication and Image Representation
2019	Multiview-Based 3-D Action Recognition Using Deep Networks Published In IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews
2019	Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective Published In ACM Computing Surveys
2019	Unsupervised domain adaptation: A multi-task learning-based method Published In Knowledge-Based Systems
2018	A Fusion Framework for Camouflaged Moving Foreground Detection in the Wavelet Domain Published In IEEE Transactions on Image Processing
2018	A large scale RGB-D dataset for action recognition Published In Lecture Notes in Computer Science
2018	A singular K-space model for fast reconstruction of magnetic resonance images from undersampled data Published In Medical and Biological Engineering and Computing
2018	Action recognition based on joint trajectory maps with convolutional neural networks Published In Knowledge-Based Systems
2018	Depth Pooling Based Large-Scale 3-D Action Recognition with Convolutional Neural Networks Published In IEEE Transactions on Multimedia
2018	Online human action recognition based on incremental learning of weighted covariance descriptors Published In Information Sciences
2018	RGB-D-based human motion recognition with deep learning: A survey Published In Computer Vision and Image Understanding
2018	Robust unsupervised feature selection via dual self-representation and manifold regularization Published In Knowledge-Based Systems
2018	Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks Published In IEEE Transactions on Circuits and Systems for Video Technology
2018	Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition Published In IEEE Access
2017	An effective edge-preserving smoothing method for image manipulation Published In Digital Signal Processing
2017	Detection and Separation of Smoke from Single Image Frames Published In IEEE Transactions on Image Processing
2017	Detection of ground parrot vocalisation: A multiple instance learning approach Published In Journal of the Acoustical Society of America
2017	Fast single image super-resolution using estimated low-frequency k-space data in MRI Published In Magnetic Resonance Imaging
2017	Joint Distance Maps Based Action Recognition with Convolutional Neural Networks Published In IEEE Signal Processing Letters
2017	Optimization of camera arrangement using correspondence field to improve depth estimation Published In IEEE Transactions on Image Processing
2017	Salient object detection via weighted low rank matrix recovery Published In IEEE Signal Processing Letters
2017	Semantic action recognition by learning a pose lexicon Published In Pattern Recognition
2016	A Spectral and Spatial Approach of Coarse-to-Fine Blurred Image Region Detection Published In IEEE Signal Processing Letters
2016	Action Recognition From Depth Maps Using Deep Convolutional Neural Networks Published In IEEE Transactions on Human-Machine Systems
2016	Efficient 2D viewpoint combination for human action recognition Published In Pattern Analysis and Applications
2016	Enhancing project-based learning through student and industry engagement in a video-augmented 3-D virtual trade fair Published In IEEE Transactions on Education
2016	Human detection from images and videos: a survey Published In Pattern Recognition
2016	Learning Discriminative Stein Kernel for SPD Matrices and Its Applications Published In IEEE Transactions on Neural Networks and Learning Systems
2016	Planogram compliance checking based on detection of recurring patterns Published In IEEE MultiMedia Magazine
2016	RGB-D-based action recognition datasets: a survey Published In Pattern Recognition
2015	Dietary assessment on a mobile phone using image processing and pattern recognition techniques: Algorithm design and system prototyping Published In Nutrients
2015	Estimation of signal distortion using effective sampling density for light field-based free viewpoint video Published In IEEE Transactions on Multimedia
2015	Functional brain network classification with compact representation of SICE matrices Published In IEEE Transactions on Biomedical Engineering
2015	Semantic and spatial content fusion for scene recognition Published In Cognitive Systems Monographs
2014	Food image classification using local appearance and global structural information Published In Neurocomputing
2014	Introduction to the special issue on visual understanding and applications with RGB-D cameras Published In Journal of Visual Communication and Image Representation
2014	Smoke detection in video: an image separation approach Published In International Journal of Computer Vision
2013	A novel shape-based non-redundant local binary pattern descriptor for object detection Published In Pattern Recognition
2013	Inter-occlusion reasoning for human detection based on variational mean field Published In Neurocomputing
2013	Measuring the degree of face familiarity based on extended NMF Published In ACM Transactions on Applied Perception
2012	Image reconstruction from sparse projections using S-transform Published In Journal of Mathematical Imaging and Vision
2012	Local representation of faces through extended NMF Published In Electronics Letters
2012	MRI reconstruction from 2D truncated k-space Published In Journal of Magnetic Resonance Imaging
2012	Removal of truncation artefacts in magnetic resonance images by recovering missing spectral data Published In Journal of Magnetic Resonance
2011	Local intensity distribution descriptor for object detection Published In Electronics Letters
2011	Object detection by admissible region search Published In Lecture Notes in Computer Science
2011	Research of unsupervised posture modeling and action recognition based on spatial-temporal interesting points Published In Chinese Journal of Electronics
2011	Semi-supervised maximum a posteriori probability segmentation of brain tissues from dual-echo magnetic resonance scans using incomplete training data Published In IET Image Processing
2010	An improved template matching method for object detection Published In Lecture Notes in Computer Science
2010	Reconstruction from limited-angle projections based on spectrum analysis Published In IEEE Transactions on Image Processing
2010	Video scene segmentation using time constraint dominant-set clustering Published In Lecture Notes in Computer Science
2008	A real-time facial expression recognition system for online games Published In International Journal of Computer Games Technology
2008	An efficient iterative algorithm for image thresholding Published In Pattern Recognition Letters
2008	Expandable data-driven graphical modeling of human actions based on salient postures Published In IEEE Transactions on Circuits and Systems for Video Technology
2008	The HCM for perceptual image segmentation Published In Neurocomputing
2007	A Prototype of Intelligent Video Surveillance Cameras Published In International Journal of Information and Systems Sciences

Book

Year	Title
2010	Illumination invariant face detection using classifier fusion Publisher Europe

Chapter

Year	Title
2015	mHealth diet and nutrition guidance Published In mHealth Multidisciplinary Verticals Publisher Boca Raton, United States
2014	Exploring compact representation of SICE matrices for functional brain network classification Published In Machine Learning in Medical Imaging 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings Publisher Switzerland
2010	Human action recognition with expandable graphical models Published In Machine Learning for Human Motion Analysis: Theory and Practice

Conference Paper

Year	Title
2019	DVONet: Unsupervised Monocular Depth Estimation and Visual Odometry Published In 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
2019	Light weight stereo matching via deep extraction and integration of low and high level information Published In IEEE International Conference on Multimedia and Expo (ICME) 2019
2019	Self-attention guided deep features for action recognition Published In IEEE International Conference on Multimedia and Expo (ICME) 2019
2018	Foreground detection in camouflaged scenes Published In International Conference on Image Processing, ICIP 2017
2018	Importance Weighted Adversarial Nets for Partia Domain Adaptation Published In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
2018	Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN Published In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
2018	Large-scale multimodal gesture recognition using heterogeneous networks Published In 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
2018	Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks Published In 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
2018	Smartphone-sensors Based Activity Recognition Using IndRNN Published In UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers
2017	Investigation of different skeleton features for CNN-based 3D action recognition Published In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
2017	Joint geometrical and statistical alignment for visual domain adaptation Published In 30th IEEE Conference on Computer Vision and Pattern Recognitio, (CVPR 2017)
2017	Skeleton-based action recognition using LSTM and CNN Published In IEEE International Conference on Multimedia and Expo Workshops (ICMEW)
2017	Weakly structured information aggregation for upper-body posture assessment using ConvNets Published In IEEE International Conference on Multimedia and Expo (ICME)
2016	Action recognition based on joint trajectory maps using convolutional neural networks Published In Proceedings of the 2016 ACM on Multimedia Conference
2016	Facilitating student and staff engagement across multiple offshore campuses for transnational education using an immersive video augmented learning platform Published In IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)
2016	Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks Published In Proceedings - 23rd International Conference on Pattern Recognition (ICPR)
2016	Large-scale Isolated Gesture Recognition using Convolutional Neural Networks Published In Proceedings - 23rd International Conference on Pattern Recognition (ICPR)
2016	Learning a pose lexicon for semantic action recognition Published In 2016 IEEE International Conference on Multimedia and Expo (ICME)
2016	Learning structured dictionary based on inter-class similarity and representative margins Published In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2015	Beyond covariance: feature representation with nonlinear kernel matrices Published In Proceedings of the IEEE International Conference on Computer Vision
2015	ConvNets-based action recognition from depth maps through virtual cameras and pseudocoloring Published In Proceedings of the 23rd ACM international conference on Multimedia
2015	Creating Simplified 3D Models with High Quality Textures Published In 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
2015	Optimization of the number of rays in interpolation for light field based free viewpoint systems Published In Proceedings - IEEE International Conference on Multimedia and Expo
2015	Single image smoke detection Published In Lecture Notes in Computer Science: Computer Vision - ACCV 2014: 12th Asian Conference on Computer Vision Singapore
2014	Discriminative key pose extraction using extended LC-KSVD for action recognition Published In 2014 International Conference on digital Image Computing: Techniques and Applications, DICTA 2014
2014	Image reconstruction from limited-angle projections using sparsifying operators Published In 2014 IEEE 12th International Conference on Signal Processing Proceedings, ICSP
2014	Mining mid-level features for action recognition based on effective skeleton representation Published In 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014
2013	A fast approximate AIB algorithm for distributional word clustering Published In IEEE Conference on Computer Vision and Pattern Recognition
2013	A method for calculating the minimum number of cameras in a light field based free viewpoint video system Published In IEEE International Conference on Multimedia and Expo
2013	Accelerating the divisive information-theoretic clustering of visual words Published In 2013 International Conference on Digital Image Computing: Techniques and Applications
2013	Image color correction in DCT domain Published In Third International Conference on Consumer Electronics
2013	Incorporating local and global information using a novel distance function for scene recognition Published In IEEE Workshop on Robot Vision, WORV
2013	Non-uniform sampling of plenoptic signal based on the scene complexity variations for a free viewpoint video system Published In 20th IEEE International Conference on Image Processing (ICIP 2013)
2013	Pathological gait detection of Parkinson's disease using sparse representation Published In 2013 International Conference on Digital Image Computing: Techniques and Applications
2013	Scene-adaptive configuration of two cameras using the correspondence field function Published In IEEE International Conference on Multimedia and Expo
2012	A novel video-based smoke detection method using image separation Published In ICME 2012: IEEE International Conference on Multimedia and Expo
2012	Measuring face familiarity and its application to face recognition Published In 2012 IEEE Workshop on the Applications of Computer Vision, WACV 2012
2011	A quantitative approach for comparison and evaluation of light field rendering techniques Published In 2011 ICME: IEEE International Conference on Multimedia and Expo
2011	Age estimation based on extended non-negative matrix factorization Published In 13rd IEEE International Workshop on Multimedia Signal Processing, MMSP 2011
2011	Detecting humans under occlusion using variational mean field method Published In 18th IEEE International Conference on Image Processing, ICIP 2011
2011	Human detection with contour-based local motion binary patterns Published In 18th IEEE International Conference on Image Processing, ICIP 2011
2011	Objective evaluation of light field rendering methods using effective sampling density Published In 13rd IEEE International Workshop on Multimedia Signal Processing, MMSP 2011
2011	Ranking social emotions by learning listwise preference Published In First Asian Conference on Digital Object Identifier
2011	Smoke detection in videos using non-redundant local binary pattern-based features Published In 13rd IEEE International Workshop on Multimedia Signal Processing, MMSP 2011
2011	Viewpoint invariants from three-dimensional data: the role of reflection in human activity understanding Published In 2011 IEEE Computer Vision and Pattern Recognition Workshops, CVPRW 2011
2010	Action recognition based on a bag of 3D points Published In IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
2010	Event recognition based on top-down motion attention Published In International Conference on Pattern Recognition
2010	Finding distinctive facial areas for face recognition Published In International Conference on Control, Automation, Robotics and Vision
2010	Head pose estimation based on extended non-negative matrix factorization Published In 25th International Conference of Image and Vision Computing New Zealand, IVCNZ 2010
2010	Human detection using local shape and non-redundant binary patterns Published In International Conference on Control, Automation, Robotics and Vision
2010	Object detection using non-redundant local Binary Patterns Published In Proceedings of 2010 IEEE 17th International Conference on Image Processing
2010	On the combination of local texture and global structure for food classification Published In International Symposium on Multimedia
2009	A novel template matching method for human detection Published In International Conference on Image Processing
2009	A part-based template matching method for multi-view human detection Published In International Conference Image and Vision Computing New Zealand
2009	Face detection using generalised integral image features Published In International Conference on Image Processing
2009	Face recognition from single sample based on human face perception Published In International Conference Image and Vision Computing New Zealand
2009	Greedy approximation of kernel PCA by minimizing the mapping error Published In 2009 Digital Image Computing: Techniques and Applications
2009	Human detection based on weighted template matching Published In IEEE International Conference on Multimedia and Expo
2009	Kernel PCA of HOG features for posture detection Published In International Conference: Image and Vision Computing New Zealand
2009	Recognition of semantic basketball events based on optical flow patterns Published In Advances in Visual Computing. 5th International Symposium ISVC 2009 Proceedings, Part II
2008	Graphical modeling and decoding of human actions Published In International Workshop on Multimedia Signal Processing
2008	Illumination invariant face detection using classifier fusion Published In Pacific-Rim Conference on Multimedia: Advances in Multimedia Information Processing
2008	Key-frame extraction using dominant-set clustering Published In International Conference on Multimedia & Expo
2007	A maximum likelihood watermark decoding scheme Published In IEEE International Conference on Multimedia and Expo
2007	Emotional states control for on-line game avatars Published In Conference on Applications, Technologies, Architectures, and Protocols for Computer CommunicationsNetGames '07 Proceedings of the 6th ACM SIGCOMM workshop on Network and system support for games
2007	Face to face communications in multiplayer online games: a real-time system Published In Human-Computer Interaction International Conference
2007	Human motion simulation and action corpus Published In Digital human modeling: Lecture Notes in Computer Science
2007	Perceived similarity and visual descriptions in content-based image retrieval Published In The IEEE International Symposium on Multimedia
2007	Real-time facial feature point extraction Published In Pacific-Rim Conference on Multimedia

Investigator On

Year	Title
2018	"Sharkeye" -- Real-Time Smart App Alerting through Aerial Surveillance Awarded by: NSW Government Department of Industry Funding Scheme: Annual Competitive Grants Program

Available as Research Supervisor

Advisees

Graduate Advising Relationship

Degree	Research Title	Advisee
Doctor of Philosophy (Integrated)	Surgical pathway discovery, conformance, and enhancement- appendectomy as an archetype
Doctor of Philosophy	Computer Vision and Machine Learning in Disaster Management and Monitoring Process	Iqbal, Umair
Master of Philosophy - EIS	Comparative Study of Deep Neural Network Architectures for Non-Rigid Retinal Image Registration	Tian, Chuanhui
Master of Philosophy - EIS	Analysis of 3D Reconstruction Based on 2D Image with Weak Supervision or no Supervision Training	Jiang, Zhe
Doctor of Philosophy	Object Detection in Images and Videos	Yohanes, Banu
Master of Philosophy - EIS	Deep architectures for object detection	Guerrero Gallegos, Jose Luis
Doctor of Philosophy	Improve Assessing methods in Physical Rehabilitation Exercises using Deep-Learning based Human Motion Analysis	Gunasekara, Shanaka
Doctor of Philosophy	Light Field Acquisition for Free-viewpoint Video.	FU, Shichao

Reviewer Of

IEEE Transactions on Circuits and Systems (Journal)
IEEE Transactions on Electronic Devices (Journal)
IEEE Transactions on Neural Networks and Learning Systems (Journal)

Education And Training

Ph.D. in Electronic Engineering 1997
M.Sc. in Computer Science, Zhejiang University (Xiqi Campus) 1987
B.Sc. in Physics and Electronics, Zhejiang University (Xiqi Campus) 1983

Teaching Overview

Dr Li was a Lecturer from 1987 to 1990 and Associate Professor from 1991 to 1992, both with the Department of Computer Science and Technology, Zhejiang University of China. From 1992 to 1993, he was a visiting Research Fellow with the Computer Science Department, Murdoch University, Australia. From 1997 to 1998, he worked as an Information Technology Officer with the Bureau of Meteorology, Australia. He joined Motorola Australian Research Centre in 1998 as a Senior Research Engineer and later a Principal Research Engineer. Since 2004, he has been a Senior Lecturer with the School of Information Technology and Computer Science, University of Wollongong.

Dr. Li is a co-founder of the Centre for Multimedia Signal Processing and Content Management at University of Wollongong. He has 17 years combined industrial and academic research experience in multimedia. He has initiated, led and contributed to a number of successful R&D projects funded by government and industry. He received Motorola CTO's Award in 2003 due to his significant contribution in the area of video analysis. Dr Li has filed four US patents. He has authored and co-authored over 50 refereed papers in the field of multimedia signal processing. His current research interests are human motion analysis, multimodal biometric cryptosystems, automatic annotation and intelligent retrieval and adaptation of multimedia content and image/video watermarking. Dr. Li regularly serves as a committee member and session chair in international conferences and a reviewer of IEEE Transactions.

Keywords

Machine Learning (Deep Learning) and 3D Computer Vision - Human activity understanding, human detection, gait recognition, 3D sensing and reconstruction from RGB-D data

3D Multimedia Signal Processing and Understanding – scene analysis and event detection

Free Viewpoint Video (FVV) – Acquisition, processing, understanding and compression

Medical Image Processing and Understanding – Image reconstruction for low-dose X-ray and fast MR imaging, segmentation of medical images

Located In Facility

Building 3, Room 101

Fax

+61 2 4221 4170

Orcid Id

http://orcid.org/0000-0002-4427-2687 (confirmed)

Research Areas

Research Overview

He mainly applies statistics and mathematics to spatial-temporal data analytics and his research interest spread across machine learning, pattern recognition, computer vision, neural networks, multimedia, image processing, video surveillance and their application to health. He pioneered in 2010 and nurtured in the subsequent years the research of understanding human activities from 3D data, one of the most popular research topics now in computer vision and machine learning. His research results have expounded in one book and 180+ publications at prestigious journals and prominent conferences, such as TIP, IJCV, TNNLS, TCSVT, TMM, CVPR, ICCV, AAAI and ACM MM. His publications have been cited in Google Scholar ~5500, his H-Index is 36 (all) and 33 (since 2015) in Google Scholar, 30 in Scopus. The highest citations of a single paper is 1250+ in Google Scholar.

Current Main Research Activities:
- Machine Learning - Statistical learning, deep learning
- 3D Computer Vision - Human activity understanding, human detection, gait recognition, 3D sensing and reconstruction from RGB-D data
- 3D Multimedia Signal Processing and Understanding – scene analysis and event detection
- Free Viewpoint Video (FVV) – Acquisition, processing, understanding and compression
- Medical Image Processing and Understanding – Image reconstruction for low-dose X-ray and fast MR imaging, segmentation of medical images

Selected Publications

Journal Article

Year	Title
2020	A Review of Dynamic Maps for 3D Human Motion Recognition Using ConvNets and Its Improvement Published In Neural Processing Letters
2020	A hybrid network for large-scale action recognition from RGB and depth modalities Published In Sensors (Switzerland)
2020	Beyond Covariance: SICE and Kernel Based Visual Feature Representation Published In International Journal of Computer Vision
2020	Densely Connected Deep Extreme Learning Machine Algorithm Published In Cognitive Computation
2020	SAR-NAS: Skeleton-based action recognition via neural architecture searching Published In Journal of Visual Communication and Image Representation
2020	Sharkeye: Real-Time Autonomous Personal Shark Alerting via Aerial Surveillance Published In Drones
2019	A fully trainable network with RNN-based pooling Published In Neurocomputing
2019	ConvNets-based action recognition from skeleton motion maps Published In Multimedia Tools and Applications
2019	Jointly Learning Visual Poses and Pose Lexicon for Semantic Action Recognition Published In IEEE Transactions on Circuits and Systems for Video Technology
2019	Learning attentive dynamic maps (ADMs) for Understanding Human Actions Published In Journal of Visual Communication and Image Representation
2019	Multiview-Based 3-D Action Recognition Using Deep Networks Published In IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews
2019	Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective Published In ACM Computing Surveys
2019	Unsupervised domain adaptation: A multi-task learning-based method Published In Knowledge-Based Systems
2018	A Fusion Framework for Camouflaged Moving Foreground Detection in the Wavelet Domain Published In IEEE Transactions on Image Processing
2018	A large scale RGB-D dataset for action recognition Published In Lecture Notes in Computer Science
2018	A singular K-space model for fast reconstruction of magnetic resonance images from undersampled data Published In Medical and Biological Engineering and Computing
2018	Action recognition based on joint trajectory maps with convolutional neural networks Published In Knowledge-Based Systems
2018	Depth Pooling Based Large-Scale 3-D Action Recognition with Convolutional Neural Networks Published In IEEE Transactions on Multimedia
2018	Online human action recognition based on incremental learning of weighted covariance descriptors Published In Information Sciences
2018	RGB-D-based human motion recognition with deep learning: A survey Published In Computer Vision and Image Understanding
2018	Robust unsupervised feature selection via dual self-representation and manifold regularization Published In Knowledge-Based Systems
2018	Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks Published In IEEE Transactions on Circuits and Systems for Video Technology
2018	Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition Published In IEEE Access
2017	An effective edge-preserving smoothing method for image manipulation Published In Digital Signal Processing
2017	Detection and Separation of Smoke from Single Image Frames Published In IEEE Transactions on Image Processing
2017	Detection of ground parrot vocalisation: A multiple instance learning approach Published In Journal of the Acoustical Society of America
2017	Fast single image super-resolution using estimated low-frequency k-space data in MRI Published In Magnetic Resonance Imaging
2017	Joint Distance Maps Based Action Recognition with Convolutional Neural Networks Published In IEEE Signal Processing Letters
2017	Optimization of camera arrangement using correspondence field to improve depth estimation Published In IEEE Transactions on Image Processing
2017	Salient object detection via weighted low rank matrix recovery Published In IEEE Signal Processing Letters
2017	Semantic action recognition by learning a pose lexicon Published In Pattern Recognition
2016	A Spectral and Spatial Approach of Coarse-to-Fine Blurred Image Region Detection Published In IEEE Signal Processing Letters
2016	Action Recognition From Depth Maps Using Deep Convolutional Neural Networks Published In IEEE Transactions on Human-Machine Systems
2016	Efficient 2D viewpoint combination for human action recognition Published In Pattern Analysis and Applications
2016	Enhancing project-based learning through student and industry engagement in a video-augmented 3-D virtual trade fair Published In IEEE Transactions on Education
2016	Human detection from images and videos: a survey Published In Pattern Recognition
2016	Learning Discriminative Stein Kernel for SPD Matrices and Its Applications Published In IEEE Transactions on Neural Networks and Learning Systems
2016	Planogram compliance checking based on detection of recurring patterns Published In IEEE MultiMedia Magazine
2016	RGB-D-based action recognition datasets: a survey Published In Pattern Recognition
2015	Dietary assessment on a mobile phone using image processing and pattern recognition techniques: Algorithm design and system prototyping Published In Nutrients
2015	Estimation of signal distortion using effective sampling density for light field-based free viewpoint video Published In IEEE Transactions on Multimedia
2015	Functional brain network classification with compact representation of SICE matrices Published In IEEE Transactions on Biomedical Engineering
2015	Semantic and spatial content fusion for scene recognition Published In Cognitive Systems Monographs
2014	Food image classification using local appearance and global structural information Published In Neurocomputing
2014	Introduction to the special issue on visual understanding and applications with RGB-D cameras Published In Journal of Visual Communication and Image Representation
2014	Smoke detection in video: an image separation approach Published In International Journal of Computer Vision
2013	A novel shape-based non-redundant local binary pattern descriptor for object detection Published In Pattern Recognition
2013	Inter-occlusion reasoning for human detection based on variational mean field Published In Neurocomputing
2013	Measuring the degree of face familiarity based on extended NMF Published In ACM Transactions on Applied Perception
2012	Image reconstruction from sparse projections using S-transform Published In Journal of Mathematical Imaging and Vision
2012	Local representation of faces through extended NMF Published In Electronics Letters
2012	MRI reconstruction from 2D truncated k-space Published In Journal of Magnetic Resonance Imaging
2012	Removal of truncation artefacts in magnetic resonance images by recovering missing spectral data Published In Journal of Magnetic Resonance
2011	Local intensity distribution descriptor for object detection Published In Electronics Letters
2011	Object detection by admissible region search Published In Lecture Notes in Computer Science
2011	Research of unsupervised posture modeling and action recognition based on spatial-temporal interesting points Published In Chinese Journal of Electronics
2011	Semi-supervised maximum a posteriori probability segmentation of brain tissues from dual-echo magnetic resonance scans using incomplete training data Published In IET Image Processing
2010	An improved template matching method for object detection Published In Lecture Notes in Computer Science
2010	Reconstruction from limited-angle projections based on spectrum analysis Published In IEEE Transactions on Image Processing
2010	Video scene segmentation using time constraint dominant-set clustering Published In Lecture Notes in Computer Science
2008	A real-time facial expression recognition system for online games Published In International Journal of Computer Games Technology
2008	An efficient iterative algorithm for image thresholding Published In Pattern Recognition Letters
2008	Expandable data-driven graphical modeling of human actions based on salient postures Published In IEEE Transactions on Circuits and Systems for Video Technology
2008	The HCM for perceptual image segmentation Published In Neurocomputing
2007	A Prototype of Intelligent Video Surveillance Cameras Published In International Journal of Information and Systems Sciences

Book

Year	Title
2010	Illumination invariant face detection using classifier fusion Publisher Europe

Chapter

Year	Title
2015	mHealth diet and nutrition guidance Published In mHealth Multidisciplinary Verticals Publisher Boca Raton, United States
2014	Exploring compact representation of SICE matrices for functional brain network classification Published In Machine Learning in Medical Imaging 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings Publisher Switzerland
2010	Human action recognition with expandable graphical models Published In Machine Learning for Human Motion Analysis: Theory and Practice

Conference Paper

Year	Title
2019	DVONet: Unsupervised Monocular Depth Estimation and Visual Odometry Published In 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
2019	Light weight stereo matching via deep extraction and integration of low and high level information Published In IEEE International Conference on Multimedia and Expo (ICME) 2019
2019	Self-attention guided deep features for action recognition Published In IEEE International Conference on Multimedia and Expo (ICME) 2019
2018	Foreground detection in camouflaged scenes Published In International Conference on Image Processing, ICIP 2017
2018	Importance Weighted Adversarial Nets for Partia Domain Adaptation Published In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
2018	Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN Published In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
2018	Large-scale multimodal gesture recognition using heterogeneous networks Published In 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
2018	Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks Published In 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
2018	Smartphone-sensors Based Activity Recognition Using IndRNN Published In UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers
2017	Investigation of different skeleton features for CNN-based 3D action recognition Published In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
2017	Joint geometrical and statistical alignment for visual domain adaptation Published In 30th IEEE Conference on Computer Vision and Pattern Recognitio, (CVPR 2017)
2017	Skeleton-based action recognition using LSTM and CNN Published In IEEE International Conference on Multimedia and Expo Workshops (ICMEW)
2017	Weakly structured information aggregation for upper-body posture assessment using ConvNets Published In IEEE International Conference on Multimedia and Expo (ICME)
2016	Action recognition based on joint trajectory maps using convolutional neural networks Published In Proceedings of the 2016 ACM on Multimedia Conference
2016	Facilitating student and staff engagement across multiple offshore campuses for transnational education using an immersive video augmented learning platform Published In IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)
2016	Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks Published In Proceedings - 23rd International Conference on Pattern Recognition (ICPR)
2016	Large-scale Isolated Gesture Recognition using Convolutional Neural Networks Published In Proceedings - 23rd International Conference on Pattern Recognition (ICPR)
2016	Learning a pose lexicon for semantic action recognition Published In 2016 IEEE International Conference on Multimedia and Expo (ICME)
2016	Learning structured dictionary based on inter-class similarity and representative margins Published In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2015	Beyond covariance: feature representation with nonlinear kernel matrices Published In Proceedings of the IEEE International Conference on Computer Vision
2015	ConvNets-based action recognition from depth maps through virtual cameras and pseudocoloring Published In Proceedings of the 23rd ACM international conference on Multimedia
2015	Creating Simplified 3D Models with High Quality Textures Published In 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
2015	Optimization of the number of rays in interpolation for light field based free viewpoint systems Published In Proceedings - IEEE International Conference on Multimedia and Expo
2015	Single image smoke detection Published In Lecture Notes in Computer Science: Computer Vision - ACCV 2014: 12th Asian Conference on Computer Vision Singapore
2014	Discriminative key pose extraction using extended LC-KSVD for action recognition Published In 2014 International Conference on digital Image Computing: Techniques and Applications, DICTA 2014
2014	Image reconstruction from limited-angle projections using sparsifying operators Published In 2014 IEEE 12th International Conference on Signal Processing Proceedings, ICSP
2014	Mining mid-level features for action recognition based on effective skeleton representation Published In 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014
2013	A fast approximate AIB algorithm for distributional word clustering Published In IEEE Conference on Computer Vision and Pattern Recognition
2013	A method for calculating the minimum number of cameras in a light field based free viewpoint video system Published In IEEE International Conference on Multimedia and Expo
2013	Accelerating the divisive information-theoretic clustering of visual words Published In 2013 International Conference on Digital Image Computing: Techniques and Applications
2013	Image color correction in DCT domain Published In Third International Conference on Consumer Electronics
2013	Incorporating local and global information using a novel distance function for scene recognition Published In IEEE Workshop on Robot Vision, WORV
2013	Non-uniform sampling of plenoptic signal based on the scene complexity variations for a free viewpoint video system Published In 20th IEEE International Conference on Image Processing (ICIP 2013)
2013	Pathological gait detection of Parkinson's disease using sparse representation Published In 2013 International Conference on Digital Image Computing: Techniques and Applications
2013	Scene-adaptive configuration of two cameras using the correspondence field function Published In IEEE International Conference on Multimedia and Expo
2012	A novel video-based smoke detection method using image separation Published In ICME 2012: IEEE International Conference on Multimedia and Expo
2012	Measuring face familiarity and its application to face recognition Published In 2012 IEEE Workshop on the Applications of Computer Vision, WACV 2012
2011	A quantitative approach for comparison and evaluation of light field rendering techniques Published In 2011 ICME: IEEE International Conference on Multimedia and Expo
2011	Age estimation based on extended non-negative matrix factorization Published In 13rd IEEE International Workshop on Multimedia Signal Processing, MMSP 2011
2011	Detecting humans under occlusion using variational mean field method Published In 18th IEEE International Conference on Image Processing, ICIP 2011
2011	Human detection with contour-based local motion binary patterns Published In 18th IEEE International Conference on Image Processing, ICIP 2011
2011	Objective evaluation of light field rendering methods using effective sampling density Published In 13rd IEEE International Workshop on Multimedia Signal Processing, MMSP 2011
2011	Ranking social emotions by learning listwise preference Published In First Asian Conference on Digital Object Identifier
2011	Smoke detection in videos using non-redundant local binary pattern-based features Published In 13rd IEEE International Workshop on Multimedia Signal Processing, MMSP 2011
2011	Viewpoint invariants from three-dimensional data: the role of reflection in human activity understanding Published In 2011 IEEE Computer Vision and Pattern Recognition Workshops, CVPRW 2011
2010	Action recognition based on a bag of 3D points Published In IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
2010	Event recognition based on top-down motion attention Published In International Conference on Pattern Recognition
2010	Finding distinctive facial areas for face recognition Published In International Conference on Control, Automation, Robotics and Vision
2010	Head pose estimation based on extended non-negative matrix factorization Published In 25th International Conference of Image and Vision Computing New Zealand, IVCNZ 2010
2010	Human detection using local shape and non-redundant binary patterns Published In International Conference on Control, Automation, Robotics and Vision
2010	Object detection using non-redundant local Binary Patterns Published In Proceedings of 2010 IEEE 17th International Conference on Image Processing
2010	On the combination of local texture and global structure for food classification Published In International Symposium on Multimedia
2009	A novel template matching method for human detection Published In International Conference on Image Processing
2009	A part-based template matching method for multi-view human detection Published In International Conference Image and Vision Computing New Zealand
2009	Face detection using generalised integral image features Published In International Conference on Image Processing
2009	Face recognition from single sample based on human face perception Published In International Conference Image and Vision Computing New Zealand
2009	Greedy approximation of kernel PCA by minimizing the mapping error Published In 2009 Digital Image Computing: Techniques and Applications
2009	Human detection based on weighted template matching Published In IEEE International Conference on Multimedia and Expo
2009	Kernel PCA of HOG features for posture detection Published In International Conference: Image and Vision Computing New Zealand
2009	Recognition of semantic basketball events based on optical flow patterns Published In Advances in Visual Computing. 5th International Symposium ISVC 2009 Proceedings, Part II
2008	Graphical modeling and decoding of human actions Published In International Workshop on Multimedia Signal Processing
2008	Illumination invariant face detection using classifier fusion Published In Pacific-Rim Conference on Multimedia: Advances in Multimedia Information Processing
2008	Key-frame extraction using dominant-set clustering Published In International Conference on Multimedia & Expo
2007	A maximum likelihood watermark decoding scheme Published In IEEE International Conference on Multimedia and Expo
2007	Emotional states control for on-line game avatars Published In Conference on Applications, Technologies, Architectures, and Protocols for Computer CommunicationsNetGames '07 Proceedings of the 6th ACM SIGCOMM workshop on Network and system support for games
2007	Face to face communications in multiplayer online games: a real-time system Published In Human-Computer Interaction International Conference
2007	Human motion simulation and action corpus Published In Digital human modeling: Lecture Notes in Computer Science
2007	Perceived similarity and visual descriptions in content-based image retrieval Published In The IEEE International Symposium on Multimedia
2007	Real-time facial feature point extraction Published In Pacific-Rim Conference on Multimedia

Investigator On

Year	Title
2018	"Sharkeye" -- Real-Time Smart App Alerting through Aerial Surveillance Awarded by: NSW Government Department of Industry Funding Scheme: Annual Competitive Grants Program

Advisees

Graduate Advising Relationship

Degree	Research Title	Advisee
Doctor of Philosophy (Integrated)	Surgical pathway discovery, conformance, and enhancement- appendectomy as an archetype
Doctor of Philosophy	Computer Vision and Machine Learning in Disaster Management and Monitoring Process	Iqbal, Umair
Master of Philosophy - EIS	Comparative Study of Deep Neural Network Architectures for Non-Rigid Retinal Image Registration	Tian, Chuanhui
Master of Philosophy - EIS	Analysis of 3D Reconstruction Based on 2D Image with Weak Supervision or no Supervision Training	Jiang, Zhe
Doctor of Philosophy	Object Detection in Images and Videos	Yohanes, Banu
Master of Philosophy - EIS	Deep architectures for object detection	Guerrero Gallegos, Jose Luis
Doctor of Philosophy	Improve Assessing methods in Physical Rehabilitation Exercises using Deep-Learning based Human Motion Analysis	Gunasekara, Shanaka
Doctor of Philosophy	Light Field Acquisition for Free-viewpoint Video.	FU, Shichao

Reviewer Of

IEEE Transactions on Circuits and Systems (Journal)
IEEE Transactions on Electronic Devices (Journal)
IEEE Transactions on Neural Networks and Learning Systems (Journal)

Education And Training

Ph.D. in Electronic Engineering 1997
M.Sc. in Computer Science, Zhejiang University (Xiqi Campus) 1987
B.Sc. in Physics and Electronics, Zhejiang University (Xiqi Campus) 1983

Teaching Overview

Dr Li was a Lecturer from 1987 to 1990 and Associate Professor from 1991 to 1992, both with the Department of Computer Science and Technology, Zhejiang University of China. From 1992 to 1993, he was a visiting Research Fellow with the Computer Science Department, Murdoch University, Australia. From 1997 to 1998, he worked as an Information Technology Officer with the Bureau of Meteorology, Australia. He joined Motorola Australian Research Centre in 1998 as a Senior Research Engineer and later a Principal Research Engineer. Since 2004, he has been a Senior Lecturer with the School of Information Technology and Computer Science, University of Wollongong.

Dr. Li is a co-founder of the Centre for Multimedia Signal Processing and Content Management at University of Wollongong. He has 17 years combined industrial and academic research experience in multimedia. He has initiated, led and contributed to a number of successful R&D projects funded by government and industry. He received Motorola CTO's Award in 2003 due to his significant contribution in the area of video analysis. Dr Li has filed four US patents. He has authored and co-authored over 50 refereed papers in the field of multimedia signal processing. His current research interests are human motion analysis, multimodal biometric cryptosystems, automatic annotation and intelligent retrieval and adaptation of multimedia content and image/video watermarking. Dr. Li regularly serves as a committee member and session chair in international conferences and a reviewer of IEEE Transactions.

Keywords

Machine Learning (Deep Learning) and 3D Computer Vision - Human activity understanding, human detection, gait recognition, 3D sensing and reconstruction from RGB-D data

3D Multimedia Signal Processing and Understanding – scene analysis and event detection

Free Viewpoint Video (FVV) – Acquisition, processing, understanding and compression

Medical Image Processing and Understanding – Image reconstruction for low-dose X-ray and fast MR imaging, segmentation of medical images

Located In Facility

Building 3, Room 101

Fax

+61 2 4221 4170

Orcid Id

http://orcid.org/0000-0002-4427-2687 (confirmed)

Overview

Overview

Research Areas

Research Overview

Available as Research Supervisor

Publications

Selected Publications

Journal Article

Book

Chapter

Conference Paper

Funding

Investigator On

Supervision

Available as Research Supervisor

Advisees

Graduate Advising Relationship

Service

Reviewer Of

Background

Education And Training

Teaching Overview

Keywords

Contact

Located In Facility

Fax

Identity

Orcid Id

Overview

Research Areas

Research Overview

Publications

Selected Publications

Journal Article

Book

Chapter

Conference Paper

Funding

Investigator On

Supervision

Advisees

Graduate Advising Relationship

Service

Reviewer Of

Background

Education And Training

Teaching Overview

Keywords

Contact

Located In Facility

Fax

Identity

Orcid Id

Visualisations

Research Areas