Syed Afaq Shah  from Murdoch University in Perth Australia.
Share

Contact me

Phone

+61 8 9360 2801

Email

Afaq.Shah@murdoch.edu.au

Fellow researchers

    Latest news

    • Research
    • School

    Dr Syed Afaq Shah
    PhD (UWA), MS and BSc Electrical Engineering

    Lecturer in Information Technology

    About me

    Bio: Dr. Syed Afaq Shah is a Lecturer at Murdoch University and Adjunct Lecturer (Department of Computer Science and Software Engineering), the University of Western Australia (UWA), Perth. His research interests include artificial intelligence, computer vision, image processing,  machine learning, pattern recognition, scene understanding, and robotics. Prior to joining Murdoch, he worked as a Lecturer ICT at Central Queensland University. He received his PhD degree from UWA and later worked as a Research Fellow for 2.5 years at UWA. He was holder of the most competitive Australian scholarships, which include Scholarship for International Research Fee (SIRF), Research Training Scheme (RTS) and UWA Top-Up scholarship. Afaq has developed machine learning systems and various feature extraction/matching algorithms for 3D object recognition and reconstruction. Prior to his enrolment at the University of Western Australia, he has worked for seven years as Project Manager and later Deputy Chief Engineer (Information Technology) and Deputy Director Quality Assurance in the aviation industry. His excellent time, staff and project management skills helped him to meet all deadlines and improve various data/document handling procedures in the organization. He also holds Bachelors and Masters degree in electrical engineering. He is Australian Computer Society Certified Professional and a member the IEEE.

     

    Research: Afaq Shah’s main field of research and expertise is “Artificial Intelligence and Image Processing”. He develops advanced machine learning techniques for image/video/data analysis, scene understanding, health (e.g., prediction of cardiovascular and Alzheimer disease), agricultural monitoring, medical/bio-medical applications, environmental sustainability measures, remote sensing, security, surveillance and monitoring. He has significantly contributed in machine learning, 3D feature descriptors, 3D object recognition and reconstruction, image segmentation, biometrics,  2D-3D scene understanding, and classification, human computer interaction, 2D-3D action and gesture recognition, image captioning, and health analytics. He has published over 40 research papers in high impact factor journals including IJCV, IEEE TNNLS, Pattern Recognition and reputable conferences including NeurIPS and ECCV. He has also co-authored a book, “A Guide to Convolutional Neural Networks for Computer Vision”. He has been awarded over $180,000 in different competitive research funding schemes.

    Teaching area

    ICT159 – Foundations of Programming

    ICT365 – Software Development Framework

    ICT582 – Python Programming Principles and Practices (Postgrad Unit)

    I also coordinate off-shore units at Murdoch Dubai and Singapore campuses.

    Research areas

    Artificial Intelligence and Machine Learning
    1. Artificial Intelligence
    2. Deep Learning
    3. Computer Vision
    4. Image Processing/Analysis
    5. Facial Analysis
    6. 3D Scene Understanding for Robot Navigation and Human Computer Interaction
    7. 3D Object Recognition
    8. Object Detection & Segmentation
    9. Health Analytics
    10. Digital AgriTech
    11. Pattern Recognition
    12. Robotics and Autonomous Systems
    13. Data Science
    14. Image Captioning

    Current projects

    Machine Learning for scene understanding
    1. Object detection and segmentation
    2. Image Captioning
    3. Image set classification for object recognition
    4. 3D Scene Understanding
    5. 3D reconstruction
    6. Defence against adversarial attacks on deep learning
    Health Analytics
    1. Machine learning approaches for prediction of cardiovascular diseases
    2. Human organ segmentation
    3. Diagnosis of Alzheimer disease
    4. Prediction and diagnosis of rheumatoid arthritis
    5. Medical Image Analysis
    6. Predictive modelling for 3D face rejuvenation
    Robotics
    1. Autonomous Navigation
    2. Object Grasping
    3. Human-robot interaction
    4. Robotic Empathy
    5. Localisation
    Biometrics
    1. Image set classification for face recognition
    2. Action and gesture recognition
    Digital AgriTech and Livestock
    1. Classification of barley crop
    2. Detection of dirt on cattle skin for better hygiene and cleaning
    3. Meat quality prediction and fat segmentation

    Awards and grants

    Updated Info: https://sites.google.com/view/afaqshah/research-grants

    1. ACU Early Career Conference Grant, 2020 – GBP2000
    2. Conference Travel Funding, 2019 – $2000
    3. NeurIPS Travel Award, 2018 – US$1500
    4. The National Heart Foundation Grant, 2018 – $150,000
    5. UWA Research Collaboration Award, 2017 – $27845
    6. UWA Start Something Research Impact Grant, 2016 – $5000
    Other Grants:

    - NVIDIA Titan-V GPU grant – 2018
    - NVIDIA Tesla K40 GPU grant – 2016

    Events and speaking engagements

    • Delivered a course on “Deep Learning for Computer Vision” at the International Summer School on Deep Learning (DeepLearn2017) in July 2017 – Bilbao, Spain.  
    • Special Session (Deep learning for computer vision) Organizer at ICCMIT 2019 conference.
    • Invited Speaker, Global Summit and Expo on Multimedia and Applications 2016.
    • Real time Object Recognition using RGB-D Video Data. University of Western Australia, 2013.
    • Local Surface Descriptors for 3D Object Recognition. University of Western Australia, 2013.
    • Keypoint Detection with Application to 3D Object Recognition. University of Western Australia, 2013.

    Professional and community service

    PSIVT 2019 Workshop Organiser

    • Organised and chaired an International Workshop on Deep Learning for Video and Image Analysis in conjunction with PSIVT 2019.

    Conference Special Session Organisation

    • Special Session Organizer: International Conference on Communication, Management and Information Technology (ICCMIT) 2019 in Vienna, Austria.

    Program Committee Member

    • Advanced Concepts for Intelligent Vision Systems (ACIVS) 2017 and 2018
    • International Conference on Multimedia and Network Information Systems (MISSI) 2018

    Doctoral and masters supervisions

    Prospective PhD Students. Please email your 2-page CV including details about your qualification, CGPAs, published papers and IELTS/TOEFL score. We have places for PhD students and postdocs in the research areas of computer vision, machine learning, data science and image processing. A typical PhD scholarship covers the tuition fees and provides a living allowance.

    PhD Students

    • Ms Katherine Mata (Murdoch)
    • Ms Naeha Sharif (UWA)
    • Mr Xianfeng Han (visiting CSC scholar from Tianjin University, China) – Completed 2019

    Research Master Training/Master by Research

    • Sharjeel Tahir (Murdoch University) – Project: Deep Learning based Robotic Vision System  – In progress
    • Nima Mirnateghi (Murdoch University) - Project: Defence against Adversarial Attacks on Deep Learning Systems – In progress
    • Weifeng Deng (Project: Deep Learning Models for Prediction of Social Communities using Image Data)  – Completed 2018
    • Ms Huiying Hu  (Project: Deep Learning for 3D Face Recognition using Pointclouds) – Completed 2017

    Publications

    Updated List of Publications: https://sites.google.com/view/afaqshah/publications

    Google Scholar profile: https://scholar.google.com.au/citations?user=jO8lwTYAAAAJ&hl=en

    Book

       S Khan, H Rahmani, Syed Afaq Ali Shah, M Bennamoun.A Guide  to Convolutional Neural Networks for Computer Vision“,  Synthesis Lectures on Computer Vision, Morgan & Claypool Publishers2018[Book]

      Book Chapter

    1. N. Sharif, U. Nadeem, Syed Afaq Ali Shah, M. Bennamoun, W Lui, “ Vision to Language: Methods, Metrics and Datasets”, Machine Learning Paradigms (Learning and Analytics in Intelligent Systems book series), 2020.   
    2. U. Nadeem, Syed Afaq Ali Shah, F. Sohel, R. Togneri, and M. Bennamoun, “Deep learning for scene understanding,” Handbook of Deep Learning Applications, (Eds) Valentina Balas, Sanjiban Sekhar Roy, Dharmendra Sharma and Pijush Samui, Springer, 2018.

       PhD Thesis

       Syed Afaq Ali Shah, Surface Representations and Automatic Feature Learning for 3D Object Recognition” 2016[PDF]
       
       Papers on arXiv
    1. D Ayris, K Horbury, B Williams, M Blackney, C S H See, Syed Afaq Ali Shah, “Deep Learning Models for Early Detection and Prediction of the spread of Novel Coronavirus (COVID-19)“, arXiv 2020. [PDF]
    2. L Zhang, J Li, P Li, X Lu, P Shen, G Zhu, Syed Afaq Ali Shah, M Bennamoun, K Qian, BW Schuller, “MeDaS: An open-source platform as service to help break the walls between medicine and informatics“, arXiv 2020. [PDF]
    3. U Nadeem, Syed Afaq Ali Shah, M Bennamoun, F Sohel, R Togneri, “Image Set Classification for Low Resolution Surveillance“, arXiv 2018. [PDF]
    4. Syed Afaq Ali Shah, U Nadeem, M Bennamoun, F Sohel, R Togneri, “Efficient Image Set Classification using Linear regression based Image reconstruction“, arXiv 2017. [PDF]
       Journal Papers
    1. L Zhang, J Li, G Lu, P Shen, M Bennamoun, Syed Afaq Ali Shah, Q Miao, G Zhu, P Li, and X Lu, ”Analysis and Variants of Broad Learning SystemsIEEE Transactions on Systems, Man and Cybernetics: Systems 2020.
    2. G Zhu, L Zhang, H Li, P Shen, Syed  Afaq Ali Shah, M Bennamoun, “Topology-learnable Graph Convolution for Skeleton-based Action Recognition”. Pattern Recognition Letter 2020.
    3. H Li, L Zhang, X Zhang, M Zhang, G Zhu, P Shen, P Li, M Bennamoun, Syed Afaq Ali Shah, ”Color Vision Deficiency Datasets & Recoloring Evaluation using GANs”, Multimedia Tools and Applications 2020
    4. L Zhang, J Zhang, P Shen, P Li, X Lu, H Zhang, Syed Afaq Ali ShahM Bennamoun, “Block Level Skip Connections across Cascaded V-Net for Multi-organ SegmentationIEEE Transactions on Medical Imaging (TMI) 2020
    5. Y Chen, F Sohel, Syed Afaq Ali Shah, S Ding, “Deep Boltzmann machine for corrosion classification using eddy current pulsed thermography”, Optik 2020
    6. N Sharif, L While, M Bennamoun, W Lui, Syed Afaq Ali Shah,”LCEval: Learned Composite Metric for Caption Evaluation“, International Journal of Computer Vision (IJCV) 2019. 
    7. G Zhu, L Zhang, L Yang, L Mei, Syed Afaq Ali Shah, M Bennamoun, P Shen, “Redundancy and Attention in Convolutional LSTM for Gesture RecognitionIEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2019
    8. Syed Afaq Ali Shah, M Bennamoun, M Molton, “Machine Learning Approaches for Prediction of Facial Rejuvenation using Real and Synthetic Data“, IEEE Access 2019[PDF
    9. G Zhu, L Zhang, P Shen, J Song, Syed Afaq Ali Shah, M Bennamoun, “Continuous Gesture Segmentation and Recognition using 3DCNN and Convolutional LSTM”, IEEE Transactions on Multimedia (TMM) 2018
    10. L Zhang, L Wang, X Zhang, P Shen, M Bennamoun, G Zhu, Syed Afaq Ali Shah, J Suang, “Semantic Scene Completion with Dense CRF from a Single Depth Image”Neurocomputing 2018
    11. L Zhang, H Li, P Shen, G Zhu, J Song, Syed Afaq Ali Shah, M Bennamoun, L Zhang, “Improving semantic image segmentation with a probabilistic superpixel-based dense conditional random field”IEEE Access 2018. [Impact Factor: 3.244] - [PDF]
    12. Syed Afaq Ali Shah, M Bennamoun, F Boussaid, “Evolutionary Feature Learning for 3D Object recognition“, IEEE Access 2017. [Impact Factor: 3.244] - [PDF]
    13. L Zhang, Q Xu, GM Zhu, J Song, X Zhang, P Shen, W Wei, Syed Afaq Ali Shah, M Bennamoun, ”An Improved Colour-to-Grey Method Using Image Segmentation and the Colour Difference Model for Colour Vision Deficiency“, IET Image Processing 2017. [Impact Factor: 1.044 
    14. L Zhang, Y Feng, P Shen, G Zhu, J Song, Syed Afaq Ali Shah, M Bennamoun, ”Efficient Finger Grained Incremental Processing with MapReduce For  Big Data“, Future Generation Computer Systems (FGCS) 2017. [Impact Factor: 3.997]  
    15. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “Keypoint-based Surface Representation for 3D Modeling and 3D Object recognition“, Pattern Recognition 2016. [Impact Factor: 4.582]
    16. M MoltonSyed Afaq Ali Shah, Mohammed Bennamoun, “Improving the Face of Cosmetic Medicine – An Automatic Three-Dimensional Analysis System for Facial Rejuvenation“, Journal of Aesthetic and Reconstructive Surgery 2016. [PDF]
    17. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “A Novel Feature Representation for Automatic 3D Object Recognition in Cluttered Scenes“, Neurocomputing 2015. [Impact Factor: 3.317]
    18. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “Iterative Deep Learning for Image Set based Face and Object Recognition“, Neurocomputing 2015. [Impact Factor: 3.317]
    19. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “A Novel 3D Vorticity based approach for automatic registration of low resolution range images“, Pattern Recognition 2015. [Impact Factor: 4.582, Ranked: A*] [PDF]

       Conference Papers

    1. N Sharif, M Bennamoun, W Liu, Syed Afaq Ali Shah, WEmbSim: A Simple yet Effective Metric for Image Captioning DICTA 2020 (Accepted).
    2. N Sharif, M Bennamoun, W Liu, Syed Afaq Ali Shah, “SubICap: Towards Subword-informed Image Captioning”, WACV 2021 (Accepted).
    3. N Sharif, M Bennamoun, W Liu, Syed Afaq Ali Shah, WEmbSim: A Simple yet Effective Metric for Image CaptioningWiCV (ECCV) 2020 (Accepted).
    4. Syed Afaq Ali Shah, M Bougre, N Akhtar, M Bennamoun, L Zhang”Efficient Detection of Pixel-Level Adversarial Attacks“,  IEEE International Conference on Image Processing (ICIP) 2020 (Accepted).
    5. L Zhang, X Wang, H Li, G Zhu, P Shen, P Li, X Lu, Syed Afaq Ali Shah, M Bennamoun,”Structure-Feature based Graph Self-adapting Pooling”, The Web Conference, WWW 2020.
    6. L Zhang, Y Liu, H Xiao, L Yang, G Zhu, Syed Afaq Ali Shah, M Bennamoun, P Shen,”Efficient Scene Text Detection with Textual Attention Tower”, 45th International Conference on Acoustics, Speech, and Signal Processing ICASSP 2020.  
    7. Syed Afaq Ali Shah, “Spatial Hierarchical Analysis Deep Neural Network for RGB-D Object Recognition“,  The 9th Pacific-Rim Symposium on Image and Video Technology (PSIVT) 2019.
    8. L Zhang, S Zhang, P Shen, G Zhu, Syed Afaq Ali Shah and M Bennamoun, “Relationship Detection Based on Object Semantic Inference and Attention Mechanisms“,  ACM International Conference on Multimedia Retrieval (ICMR) 2019.
    9. Syed Afaq Ali Shah, M Bennamoun, M Molton, “A Fully Automatic Framework for Prediction of 3D Facial Rejuvenation“,  Image and Vision Computing New Zealand (IVCNZ) 2018. 
    10. Syed Afaq Ali Shah, M Bennamoun, M Molton, “A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation“,  Image and Vision Computing New Zealand (IVCNZ) 2018. 
    11. G Zhu, L Zhang, L Mei, P Shen, Syed Afaq Ali Shah, M Bennamoun,”Attention in Convolutional LSTM for Gesture Recognition“, Thirty-second Conference on Neural Information Processing Systems (NIPS) 2018.
    12. N Sharif, L While, M Bennamoun, Syed Afaq Ali Shah,”NNEval: Neural Network based Evaluation Metric for Image Captioning“, European Conference on Computer Vision (ECCV) 2018. 
    13. S Ejaz, G Dwivedi, F Sanfilippo. F Sohel, M Bennamoun, Syed Afaq Ali Shah, “Developing and testing a new machine learning method to identify patients with heart failure who are at risk of 30-day readmission or mortality“, 66th Annual Scientific Meeting of the Cardiac Society of Australia and New Zealand (CSANZ) 2018.
    14. N Sharif, L While, M Bennamoun, Syed Afaq Ali Shah,”Learning-based Composite Metrics for Improved Caption Evaluation”, The 56th Annual Meeting of the Association for Computational Linguistics (ACL) SRW 2018.
    15. L Zhang, X Kong, PShen, G Zhu, JSong, Syed Afaq Ali Shah, M Bennamoun, “Reflective Field for Pixel-Level Tasks“, International Conference on Pattern Recognition (ICPR) 2018.
    16. L Zhang, G Zhu, PShen, JSong, Syed Afaq Ali Shah, M Bennamoun, “Learning Spatiotemporal Features using 3DCNN and Convolutional LSTM for Gesture Recognition“, IEEE International Conference on Computer Vision (ICCV) Workshop (2017 Chalearn Looking at People
    17. L Zhang, H Li, G Zhu, P Shen, J Song, Syed Afaq Ali Shah, M Bennamoun,”Improving semantic image segmentation with a probabilistic superpixel-based fully connected CRF”, Chinese Conference on Computer Vision (CCCV) – 2017
    18. H Hu, Syed Afaq Ali Shah, M Bennamoun, “2D and 3D Face Recognition using Convolutional Neural Networks“, IEEE Region Ten Conference (TENCON) 2017
    19. Syed Afaq Ali Shah, U. Nadeem, M. Bennamoun,  F. Sohel, R. Togneri, “Efficient Image Set Classification using Linear regression based Image reconstruction“, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Workshop 2017. [PDF]
    20. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “Automatic 3D Face Landmark Localization based on 3D Vector Field Analysis“, 30th International Conference on Image and Vision Computing New Zealand (IVCNZ) 2015.
    21. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “A Novel Algorithm for Efficient Depth Segmentation Using Low Resolution (Kinect) Images“, IEEE International Conference on Industrial Electronics and Applications (ICIEA) 2015. [ERA Ranking: A]  [PDF]
    22. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “Performance Evaluation of 3D Local Surface Descriptors for Low and High Resolution Range Image Registration“, IEEE Digital Image Computing: Techniques and Applications (DICTA) 2014.
    23. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, “A Novel Local Surface Desription for Automatic 3D Object Recognition in Low Resolution Cluttered Scenes“, IEEE International Conference on Computer Vision (ICCV) Workshop 2013.[PDF]  (Ranked among top 10 in Computer Vision: Google metrics)  
    24. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, Amar A El-Sallam, “3D-DIV: A Novel Local Surface Descriptor for Feature Matching and Pairwise Range Image Registration“, IEEE International Conference on Image Processing (ICIP) 2013. [PDF] (Ranked 2nd in Image Processing: Google metrics)
    25. Syed Afaq Ali Shah, Mohammed Bennamoun, Farid Boussaid, Amar A El-Sallam, “Automatic Object Detection using Objectness Measure”, IEEE International Conference on Communication, Signal Processing and their Applications 2013. [PDF[Code] (My most downloaded paper @academia)
    26. Syed Afaq Ali Shah, Abdul Bais, Ghulam Mubashar Hassan, K.M. Yahya, “Quantification and Visualization of MRI Cartilage of the Knee: A Simplified Approach“, IEEE International Conference on Emerging Technologies (ICET) 2010. [PDF]