|Member Login


Sadegh Aliakbarian

Sadegh Aliakbarian

Sadegh is an Associated PhD researcher at our Australian National University node and a researcher at Smart Vision Systems, Data61, CSIRO. He is working on vision-based action anticipation. His method for action anticipation is particularly crucial in scenarios where one needs to react before the action is finalised, such as to avoid hitting pedestrians with an autonomous car. Currently, he is working on action anticipation in driving scenarios to predict human centric actions (e.g., driver maneuver, violating traffic rules, front car intention, pedestrian intention, and accidents with cars and pedestrians) before they actually begin to happen. Prior to starting his PhD, he was a researcher at NICTA. Before joining NICTA, Sadegh worked in the Computer Vision industry for more than two years. He also has a Bachelor of Science with honors in Computer Software Engineering.

Sadegh is also interested in other computer vision applications such as weakly-supervised semantic segmentation, usage of synthetic data in computer vision, and sequence learning. For more on his research, see his Google Scholar profile

Australian Centre for Robotic Vision
2 George Street Brisbane, 4001
+61 7 3138 7549