About
Hi, I am currently a Lecturer (Assistant Professor) in the School of Electrical Engineering and Computer Science at The University of Queensland.
Prior to this, I was Lecturer and Research Fellow (Level B) at Human-Centric AI Group in School of Electrical Engineering, Computing and Mathematical Sciences at Curtin University. My core research area is Affective Computing using Computer Vision and Machine Learning techniques. I have prior experience in working with multimodal data such as image, video, text and physiological signals. In my current role as well, I am pursuing research in human behaviour understanding, affective computing, human centred ai, rehabilitation robotics in different real-world applications.
I obtained my PhD in Information Technology from Monash University in Oct 2022. My PhD thesis was on 'Automatic Eye Gaze Estimation with Limited Supervision' which mainly focuses on self-supervised, unsupervised, weakly/semi-supervised learning paradigms for generalized gaze representation learning.
Employment
-
The University of Queensland Lecturer (Assistant Professor)2025 - Present
-
Curtin University Research Academic (Post-Doctoral)2023 - 2025
-
Monash University Research Fellow (Post-Doctoral)2022 - 2023
Education
Education history is unavailable.
Projects & Funding
Projects & funding information is unavailable.
Publications (38)
- TIME 2026: 2nd International Workshop on Transformative Insights in Multi-faceted Evaluation Save
- CSGaze: Context-aware Social Gaze Prediction Save
- Empathy Detection From Text, Audiovisual, Audio or Physiological Signals: A Systematic Review of Task Formulations and Machine Learning Methods Save
- Multimodal Deepfake Generation and Detection: Challenges, Methods, and Future Directions Save
- Proceedings of the 3rd International Workshop on Multimodal and Responsible Affective Computing Save
- Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations Save
- Face the Sound: Synthesizing Listener Facial Motion from Speaker Speech Save
- AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations Save
- 1M-Deepfakes Detection Challenge Save
- AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset Save