If you made any changes in Pure these will be visible here soon.

Personal profile

Biography

Munawar Hayat received his Bachelor of Engineering degree from National University of Science and Technology (NUST), Pakistan, in 2009. Later, He was awarded Erasmus Mundus Scholarship for a joint European Masters degree program. He completed his PhD from The University of Western Australia (UWA) in 2015. His PhD thesis received Robert Street Prize (awarded annually to one student whose PhD thesis, of all theses passed during the course of the year, has, in the opinion of the Board of the Graduate Research School (GRS), made the most outstanding contribution to its field). His PhD thesis also received Deans List Honorable mention award (awarded to only a fraction of theses by the GRS, UWA). He worked as a PostDoc at IBM Research Australia before joining University of Canberra.

His research interests are in Computer Vision and Machine Leaning. He has worked towards development of facial analysis techniques from multiple data modalities. In this regards, he has worked on face recognition and facial expression classification from 3D images & videos, low quality 2D images & videos and Kinect acquired data. He has also worked on classification of indoor scene images. He has explored deep learning, manifold learning and other methods of discriminative learning for solving underlying research problems. His work has been published at top venues of the field (e.g. TPAMI, IJCV, TIP, TNNLS, CVPR, ICCV, ECCV). For his future research, he is interested in video data analysis with applications to affective computing and human behaviour understanding, unsupervised feature learning from image data using deep learning, face recognition from surveillance quality imagery and understanding images of indoor and outdoor scenes. Please look at his personal webpage for further details about his research.

Research interests

  • Computer Vision
  • Pattern Recognition
  • Machine Learning

Related Links

Fingerprint Dive into the research topics where Munawar Hayat is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

  • 5 Similar Profiles
Face recognition Engineering & Materials Science
Classifiers Engineering & Materials Science
Neural networks Engineering & Materials Science
Chemical activation Engineering & Materials Science
Support vector machines Engineering & Materials Science
Object recognition Engineering & Materials Science
Discriminant analysis Engineering & Materials Science
Electric fuses Engineering & Materials Science

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Projects 2019 2022

Improving the specificity of affective computing via multimodal analysis

Goecke, R., Hayat, M., Cohn, J. F., Schuller, B. & Morency, L.

1/10/1930/09/22

Project: Other

Research Output 2012 2019

  • 14 Conference contribution
  • 9 Article
4 Citations (Scopus)

Regularization of deep neural networks with spectral dropout

Khan, S., HAYAT, M. & Porikli, F., Feb 2019, In : Neural Networks. 110, p. 82-90 9 p.

Research output: Contribution to journalArticle

Neural networks
Neurons
Chemical activation
Weights and Measures
Deep neural networks
2 Citations (Scopus)

Adversarial Training of Variational Auto-Encoders for High Fidelity Image Generation

Khan, S. H., Hayat, M. & Barnes, N., 12 Mar 2018, Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018. IEEE, Institute of Electrical and Electronics Engineers, Vol. 2018-January. p. 1312-1320 9 p.

Research output: A Conference proceeding or a Chapter in BookConference contribution

Discriminators
Pixels
Feedback
Experiments
43 Citations (Scopus)

Cost-Sensitive Learning of Deep Feature Representations From Imbalanced Data

Khan, S., HAYAT, M., Bennamoun, M., Sohel, F. & Togneri, R., Aug 2018, In : IEEE Transactions on Neural Networks and Learning Systems. 29, 8, p. 3573-3587 15 p.

Research output: Contribution to journalArticle

Costs
Classifiers
Image classification
Sampling
Neural networks
2 Citations (Scopus)

A multimodal system to characterise melancholia: Cascaded bag of words approach

Bhatia, S., Hayat, M. & Goecke, R., 3 Nov 2017, ICMI 2017 - Proceedings of the 19th ACM International Conference on Multimodal Interaction. Glasgow, United Kingdom: Association for Computing Machinery, Inc, p. 274-280 7 p.

Research output: A Conference proceeding or a Chapter in BookConference contribution

4 Citations (Scopus)

A Video-Based Facial Behaviour Analysis Approach to Melancholia

BHATIA, S., HAYAT, M., Breakspear, M., Parker, G. & GOECKE, R., 30 May 2017, Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017). Washington DC, USA: IEEE, Institute of Electrical and Electronics Engineers, p. 754-761 8 p.

Research output: A Conference proceeding or a Chapter in BookConference contribution

Depressive Disorder
Depression
Anhedonia
Speech Perception
Mood Disorders