Multimodality and Embodiment in Vision, by Prof. Amir Zamir

Inaugural Lecture - Multimodality and Embodiment in Vision
Abstract
The remarkable progress in Computer Vision and Machine Learning now enables us to automatically detect the objects in images, caption them, or estimate the 3D structure. But are we close to sophisticated visual capabilities, such as those that even simple biological organisms exhibit? I discuss two related directions as steps toward that goal: multimodality and embodiment.
About the speaker
Amir Zamir is an Assistant Professor of computer science at EPFL. His research is in computer vision, machine learning, and perception-for-robotics. Before joining EPFL in 2020, he was with UC Berkeley, Stanford, and UCF. He has received paper awards at SIGGRAPH 2022, CVPR 2020, CVPR 2018, CVPR 2016, and the NVIDIA Pioneering Research Award 2018, PAMI Everingham Prize 2022, and ECCV/ECVA Young Researcher Award 2022. His research has been covered by press outlets, such as The New York Times and Forbes. He was the computer vision and machine learning chief scientist of Aurora Solar, a Forbes AI 50 company, from 2015 to 2022.
Publications, project pages, code: amirzamir.com