In June 2022, Prime Video science teams presented two papers at the Conference on Computer Vision and Pattern Recognition.
At Prime Video, our teams are involved in cutting-edge work across multiple areas of artificial intelligence including computer vision, machine learning, and natural-language processing. Our teams are leaders in the field of computer vision and are constantly solving challenging scientific problems and building solutions for them that delight Prime Video customers.
CVPR is the premier annual computer vision event comprising of the main conference and several co-located workshops and short courses. Prime Video teams presented the following two papers at the conference:
- Robust cross-modal representation learning with progressive self-distillation by Alex Andonian (MIT), Shixing Chen (Applied Scientist II – Prime Video), and Raffay Hamid (Senior Principal Scientist – Prime Video).
- Depth-guided sparse structure from motion for movies and TV shows by Sheng Liu (University of Buffalo), Xiaohan Nie (Senior Applied Scientist – Amazon Devices), and Raffay Hamid (Senior Principal Scientist – Prime Video).
Read more about CVPR and Amazon’s contributions on the Amazon Science website.