Rate My Professor Toan Do

Thanh-Toan (Toan) Do is a Senior Lecturer in the Department of Data Science and AI at Monash University's Faculty of Information Technology. He obtained his Ph.D. in computer science from the French National Institute for Research in Computer Science and Control (INRIA), Rennes, France, in 2012. Following his doctorate, Do served as a Research Fellow at the Singapore University of Technology and Design from 2013 to 2016. He then held a Research Fellow position at the Australian Centre for Robotic Vision and the University of Adelaide from 2016 to 2018. From 2018 to 2020, he was a Lecturer in the Department of Computer Science at the University of Liverpool. In 2020, he joined Monash University as a Senior Lecturer, where he is currently accepting PhD students and contributes to the Vision and Language research group within the Data Science and AI discipline.

Do's research specializations lie in computer vision and machine learning, with particular emphasis on visual search, visual question answering, metric learning, compact deep learning, few-shot learning, and robotic vision applications. His scholarly impact is evidenced by over 4,690 citations and an h-index of 39 according to Google Scholar. Notable awards include the Harold Boley Award for Most Promising Paper in 2021 for 'Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification' presented at RuleML+RR 2021, and selection as a CVPR 2019 Best Paper Finalist for 'SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences'. Key publications encompass 'Task Weighting in Meta-learning with Trajectory Optimisation' (2023, Transactions on Machine Learning Research), 'Instance-level Few-shot Learning with Class Hierarchy Mining' (2023, IEEE Transactions on Image Processing), 'PAC-Bayes Meta-learning with Implicit Task-specific Posteriors' (2022, IEEE Transactions on Pattern Analysis and Machine Intelligence), 'Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite' (2021, IEEE Transactions on Image Processing), 'Big data directed acyclic graph model for real-time COVID-19 twitter stream detection' (2021, Pattern Recognition), and 'MirrorNet: Bio-Inspired Camouflaged Object Segmentation' (2021). As Chief Investigator, he leads the project 'Large-scale multimodal knowledge management: From organization and user modeling to fast contextual presentation' spanning 2022 to 2025. Do also teaches courses such as Intelligent Image and Video Analysis at Monash University.