Professor  Ajmal Saeed Mian

Ajmal Mian is a Professor of Computer Science at The University of Western Australia. He leads the Machine Intelligence Group which is the most prominent research group from Western Australia in Artificial Intelligence, Deep Learning and Computer Vision. Professor Mian is the Early Career WA Scientist of the Year 2012 and recipient of two prestigious fellowships from the Australian Research Council (ARC). He has received several other awards including the Australian Academy of Science ARC award, Excellence in Research Supervision Award, EH Thompson Award, ASPIRE Professional Development Award, Vice-chancellors Mid-career Research Award, Outstanding Young Investigator Award, the Australasian Distinguished Doctoral Dissertation Award from Computing Research & Education association of Australasia (CORE) and various best paper awards. He has secured several research grants from the Australian Research Council, the National Health and Medical Research Council of Australia and US Department of Defence DARPA totalling to over $40 million in research funding. He is an Associate Editor of three high impact journals namely the IEEE Transactions on Neural Networks & Learning Systems, IEEE Transactions on Image Processing and the Pattern Recognition journal. These journals are ranked A* by CORE. Mian also served as a Guest Editor for special issues in Remote Sensing, Neural Computing & Applications, Pattern Recognition, Image & Vision Computing, Computer Vision & Image Understanding, and Machine Vision Applications. He was General Chair of the International Conference on Digital Image Computing Techniques & Applications (DICTA) 2019, General Chair of the Asian Conference on Computer Vision (ACCV) 2018, Program Chair of DICTA 2012 and Area Chair of CVPR 2022, ACM Multimedia 2020, IEEE Winter Conference on Applications of Computer Vision (WACV) 2019, WACV 2018, International Conference on Pattern Recognition 2016 and ACCV 2014. Ajmal Mian is the Vice-President of the Australian Pattern Recognition Society. He has supervised 18 PhD student theses to completion and 7 Postdoctoral Fellows. He has published over 200 scientific papers in prestigious journals and conferences such as TPAMI, IJCV, TNNLS, TIP, PR, TGRS, TBME, CVPR, ICCV and ECCV. His research interests are in computer vision, machine learning, deep learning including adversarial attacks and defences on deep learning models, 3D shape analysis, point cloud analysis, facial recognition, human action recognition and video understanding.

• 3D Deceptive Textures for Physical World Adversarial Attacks
  Deep learning offers state-of-the-art solutions for multiple computer vision tasks. How-ever, deep neural models are vulnerable to slight input perturbations that can significantly change model...
• Deep Learning for Multiple Object Tracking
  Multiple Object Tracking (MOT) plays an important role in solving many fundamental problems in video analysis. MOT involves object detection followed by object association. While object detection...
• Deep Learning over 3D Point Clouds
  3D point clouds are becoming an important data source for vision tasks such as auton-omous driving and robotic perception. However, deep learning over unstructured point clouds is challenging. We...
• Dense 3D Face Correspondence for Deep 3D Face Recognition and Medical Applications
  In this talk, I will present our research on dense 3D face correspondence which is a core problem in facial analysis for many applications such as biometric identification, symptomatology for the...
• Learning from Legacy MoCap Data for Precision Modelling of 3D Human Motion for Behavioural and Performance Analysis
  Modelling human actions is useful for surveillance, sports and medical applications. State of the art models are based on deep learning from large amounts of annotated data which is expensive to...
• Threat of Adversarial Attacks on Deep Learning in Computer Vision
  Deep learning is at the heart of the current rise of artificial intelligence. However, deep models are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that make the...