Scholar
Akshay Asthana
Google Scholar ID: SEolNVkAAAAJ
Chief Scientist (AI), Seeing Machines Inc.
Citations & Impact
Citations
808
H-index
11
i10-index
13
Publications
20
Co-authors
29
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Accepted in WACV 2024 and ICLR 2024; Awarded ARC Linkage award with ANU to study in-vehicle situation awareness using visual and audio sensors in 2022.
Research Experience
- Previously a Marie Curie Research Fellow in the iBUG group at Imperial College London, supported by the Marie Curie International Incoming Fellowship (MC-IIF 2012). Now, as a Chief Scientist at Seeing Machines, Inc., he leads the Research group.
Education
- PhD in Computer Vision from the Research School of Engineering, Australian National University, supported by the AUSAID Australian Leadership Award Scholarship (2008-2012). During his PhD, he also worked at the Mitsubishi Electric Research Lab (MERL) in Cambridge (MA, USA) and the Robotics Institute (RI), Carnegie Mellon University (CMU) in Pittsburgh (PA, USA).
Background
- Currently a Chief Scientist (Artificial Intelligence) at Seeing Machines, Inc., leading the Research group specializing in the development and deployment of cutting-edge 2D and 3D algorithms for full-body tracking, efficient object detection, dense image segmentation, monocular depth estimation, network quantization, quantization-aware training, and low-precision (4-bit) models inference. His research interests lie at the intersection of computer vision, machine learning, and deep learning, with a focus on non-rigid object registration and tracking.
Miscellany
- Served as a PC Member for several international conferences such as Emotion Recognition In The Wild Challenge and Workshop @ ACM ICMI 2015, Emotion Recognition In The Wild Challenge and Workshop @ ACM ICMI 2014, Workshop on Computer Vision for Affective Computing (CV4AC) @ ACCV 2014, Emotion Recognition In The Wild Challenge and Workshop @ ACM ICMI 2013, and IEEE International Conference on Automatic Face and Gesture 2013.
