Professor Sridha Sridharan
Faculty of Engineering,
School of Electrical Engineering & Robotics
Biography
Prof Sridha Sridharan is the Program Leader of the Signal Processing, Artificial Intelligence and Vision Technologies (SAIVT) Research Program at QUT. Please see Google Scholar for Prof Sridha Sridharan's areas of research interest and publications: https://scholar.google.com.au/citations?hl=en&user=v8-lMdUAAAAJIf interested in undertaking PhD research at QUT in the areas of Artificial Intelligence, Computer Vision, Machine Learning or in the area of Signal Processing please go to our SAIVT Research Program website:
https://research.qut.edu.au/saivt/ Professor Sridharan has received grants for his research in excess of $20M from competitive and industry funding sources. He has received 10 Australian Research Council (ARC) grants (7 ARC Discovery/Large and 12 ARC Linkage/Collaborative/APAI);Prof Sridharan has supervised 86 PhD students at QUT (as a Principal or active Associate Supervisor) in the area of Image and Speech Technologies. He has published over 400 papers consisting of 9 book chapters, 104 journal articles and over 300 refereed international conference publications the areas of Speech and Image technologies. Prof Sridharan is currently engaged in research in the following areas: Image and Video Technology - Computer Vision and Machine Learning: Computer Vision; Video Surveillance; Multi-camera management; Crowd Monitoring; Abnormal Event Detection;Person Detection and Tracking;Vehicle Detection and Tracking; Video Event Detection; Human Identification at Distance; Soft Biometrics; Multimodal Biometrics; Anti-spoofing Biometrics; Iris Recognition at a Distance; Gait Recognition; 2-D and 3-D Face Recognition – Cooperative and Uncooperative; Facial Expression Recognition; Face Clustering and diarisation; Human Action Recognition;Object recognition and scene understanding; Multispectral and hyperspectral image analysis; Sports analytics;Image analysis for unmanned aircrafts; 3-D modelling of objects and scenes; Robot navigation and robot-human interaction; Video indexing, search, retrieval and summarisation. Speech and Audio Technology: Signal Processing and Recognition:Speech Detection, Speech Enhancement Single/Multi-microphone; Language Identification; Speaker Verification and Identification; Speech Recognition; Key Word Spotting/Spoken Term Detection; Speaker Indexing/Diarisation/Segmentation/Clustering ;Speaker Role Detection; Multimodal Speech Processing (audio and video);Speech Emotion Detection. For more details see: https://research.qut.edu.au/saivt/
Personal details
Positions
- Principal Research Fellow
Faculty of Engineering,
School of Electrical Engineering & Robotics - Emeritus Professor
Administrative Division,
Human Resources
Keywords
Computer Vision, Machine Learning, Deep Learning, Artificial Intelligence, Image Processing, Signal Processing, Biometrics, Surveillance, Speaker Recognition, Robotics
Research field
Artificial intelligence
Field of Research code, Australian and New Zealand Standard Research Classification (ANZSRC), 2020
Qualifications
- PhD (University of New South Wales)
- MSc (Victoria University of Manchester)
Professional memberships and associations
- Life Senior Member - IEEE - Institute of Electrical and Electronics Engineers
For more information on Prof Sridha Sridharan research activities visit website: https://research.qut.edu.au/saivt/
Teaching
Professor Sridha Sridharan is currently a full-time researcher at QUT and his teaching involves supervision of PhD students in the areas of AI, Computer Vision, Machine Learning and Signal Processing within the SAIVT Research Program which he leads. A major focus of Prof Sridharan’s research is in applying Deep Machine Learning techniques to solve real world problems in Computer Vision and Speech and Language Processing. More details about the SAIVT research program can be found in: https://research.qut.edu.au/saivt/ Currently we are looking to recruit PhD students in the areas of computer vision, deep machine learning, and all areas of speech technology including speech and speaker recognition. Scholarships are available to outstanding domestic and international students covering living allowance, tuition fees and health cover. To apply contact Professor Sridha Sridharan at s.sridharan@qut.edu.au
Experience
Publications
- Nguyen, K., Fookes, C., Sridharan, S. & Ross, A. (2023). Complex-valued Iris Recognition Network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 182–196. https://eprints.qut.edu.au/230669
- Dissanayake, T., Fernando, T., Denman, S., Sridharan, S. & Fookes, C. (2023). Multi-stage stacked temporal convolution neural networks (MS-S-TCNs) for biosignal segmentation and anomaly localization. Pattern Recognition, 139. https://eprints.qut.edu.au/238599
- Khatun, A., Denman, S., Sridharan, S. & Fookes, C. (2023). Pose-driven attention-guided image generation for person re-Identification. Pattern Recognition, 137. https://eprints.qut.edu.au/237373
- Vidanapathirana, K., Moghadam, P., Sridharan, S. & Fookes, C. (2023). Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization. IEEE Robotics and Automation Letters, 8(5), 2494–2501. https://eprints.qut.edu.au/238892
- Nguyen, D., Nguyen, D., Sridharan, S., Denman, S., Nguyen, T., Dean, D. & Fookes, C. (2023). Meta-transfer learning for emotion recognition. Neural Computing and Applications, 35(14), 10535–10549. https://eprints.qut.edu.au/237855
- Hewa Thondilege, A., Nguyen Thanh, K., Sridharan, S. & Fookes, C. (2022). Accurate 3D hand mesh recovery from a single RGB image. Scientific Reports, 12(1). https://eprints.qut.edu.au/233432
- Priyasad, D., Fernando, T., Denman, S., Sridharan, S. & Fookes, C. (2022). Affect recognition from scalp-EEG using channel-wise encoder networks coupled with geometric deep learning and multi-channel feature fusion. Knowledge-Based Systems, 250. https://eprints.qut.edu.au/232909
- Tursun, O., Denman, S., Sridharan, S., Goan, E. & Fookes, C. (2022). An efficient framework for zero-shot sketch-based image retrieval. Pattern Recognition, 126. https://eprints.qut.edu.au/227841
- Tursun, O., Denman, S., Sivapalan, S., Sridharan, S., Fookes, C. & Mau, S. (2022). Component-based Attention for Large-scale Trademark Retrieval. IEEE Transactions on Information Forensics and Security, 17, 2350–2363. https://eprints.qut.edu.au/136009
- Fernando, T., Gammulle, H., Denman, S., Sridharan, S. & Fookes, C. (2022). Deep Learning for Medical Anomaly Detection: A Survey. ACM Computing Surveys, 54(7). https://eprints.qut.edu.au/214059
QUT ePrints
For more publications by Sridha, explore their research in QUT ePrints (our digital repository).
Selected research projects
- Title
- Unlocking Mass Mobile Video Analytics with Advanced Neural Memory Networks
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- DP200101942
- Start year
- 2021
- Keywords
- Title
- One shot three-dimensional reconstruction of human anatomy and motion
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- DP170100632
- Start year
- 2017
- Keywords
- Title
- Improving Productivity and Efficiency of Australian Airports - A Real Time Analytics and Statistical Approach
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- LP140100282
- Start year
- 2015
- Keywords
- Bayesian Networks; Video Analytics; Operations Management
- Title
- Monitoring intuitive expertise in the context of airport security screening
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- LP140100221
- Start year
- 2015
- Keywords
- Intuitive Expertise; Airport Security; Automated Monitoring
- Title
- Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- DP140100793
- Start year
- 2014
- Keywords
- Face Processing; Face Recognition; Computer Vision
- Title
- The next generation speaker recognition system
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- LP130100110
- Start year
- 2013
- Keywords
- Speaker verification; speech processing; signal processing
- Title
- Omniscient Face Recognition for Uncooperative Subjects
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- DP110100827
- Start year
- 2011
- Keywords
- Face Recognition; Computer Vision; Biometrics; Image Processing
- Title
- Intelligent Surveillance Research for Crowd Monitoring and Event Detection
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- PR09-0089
- Start year
- 2010
- Keywords
- Video Surveillance; Video Event Detection
- Title
- Airports of the Future
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- LP0990135
- Start year
- 2009
- Keywords
- Complex Systems Engineering; Airport Operations Management; Business Process Modelling; Surveillance and Identity Management; Human Systems Interaction; Risk and Emergency Management
- Title
- Robust Automatic Speaker Diarisation of Audio Documents by Exploiting Prior Sources of Information
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- LP0991238
- Start year
- 2009
- Keywords
- Speaker Diarisation; Speaker Recognition; Speaker Identification; Speech Processing; Signal Processing; Pattern Recognition
Projects listed above are funded by Australian Competitive Grants. Projects funded from other sources are not listed due to confidentiality agreements.
Supervision
Current supervisions
- Lifelong Collaborative Learning
PhD, Principal Supervisor
Other supervisors: Adjunct Professor Peyman Moghadam, Professor Clinton Fookes, Dr Tharindu Fernando Warnakulasuriya - Transformer Neural Networks on Fine-Grained Sports Data
PhD, Principal Supervisor
Other supervisors: Professor Clinton Fookes, Dr Harshala Gammulle - Multimodal Co-learning AI meets Remote Sensing
PhD, Associate Supervisor
Other supervisors: Dr Kien Nguyen Thanh, Professor Clinton Fookes - Improving Fine-Grained Understanding of Point Clouds Using Spatio-Temporal Priors
PhD, Associate Supervisor
Other supervisors: Professor Clinton Fookes, Adjunct Professor Peyman Moghadam - Self-Supervised Learning for 3D Multimodal Perception
PhD, Associate Supervisor
Other supervisors: Professor Clinton Fookes, Adjunct Professor Peyman Moghadam, Dr Tharindu Fernando Warnakulasuriya - Deep Spatial-Spectral Representation Learning for Hyperspectral Data
PhD, Principal Supervisor
Other supervisors: Adjunct Professor Peyman Moghadam, Professor Clinton Fookes, Dr Tharindu Fernando Warnakulasuriya, Dr Maryam Haghighat - Towards Unsupervised and Transparent Deep Learning for Aerial Person Re-ID
PhD, Associate Supervisor
Other supervisors: Dr Kien Nguyen Thanh, Professor Clinton Fookes
Completed supervisions (Doctorate)
- Missing Ingredients in Optimising Large-scale Image Retrieval with Deep features (2022)
- Multimodal Image Correspondence (2022)
- Regularized Ensemble Correlation Filter Tracking (2022)
- Deep Learning for Person Re-Identification (2021)
- Multimodal Dense Map-Centric SLAM (2021)
- Deep Domain Adaptation and Generalisation (2020)
- Multimodal Emotion Recognition Using Deep Learning Techniques (2020)
- Non-rigid 3D Reconstruction of the Human Body in Motion (2020)
- Question-answering on Image/Video Content (2020)
- Representation and Reconstruction of 3D Shapes in Computer Vision (2020)
Supervision topics
The supervisions listed above are only a selection.