Rate My Professor Mahsa Baktashmotlagh

Baktashmotlagh has secured major grants including the ARC Future Fellowship for Rethinking Topological Persistence (2024-2028), Grains Research & Development Corporation funding for Analytics for the Australian Grains Industry (AAGI) (2023-2027), and a project on Reducing Simulation-to-Reality Gap as Remedy to Learning Under Uncertainty (2021-2027). She supervises numerous PhD students as principal or associate advisor on topics like domain generalization, semantic segmentation for crop health assessment, out-of-distribution generalisation in feature spaces, robotics manipulation of articulated objects, and plant phenotyping from video data. Her publication record comprises over 75 works from 2011 to 2026 in leading venues such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Journal of Machine Learning Research, Knowledge-Based Systems, and IEEE Transactions on Knowledge and Data Engineering. Key publications include DI-NIDS: domain invariant network intrusion detection system (Knowledge-Based Systems, 2023), Source-free progressive graph learning for open-set domain adaptation (IEEE TPAMI, 2023), Interpretable signed link prediction with signed infomax hyperbolic graph (IEEE TKDE, 2023), Distribution-matching embedding for visual domain adaptation (JMLR, 2016), and Unsupervised domain adaptation by domain invariant projection (ICCV, 2013). Her research has accumulated over 4,000 citations per Google Scholar.