Aula aberta no âmbito da Unidade Curricular de Aprendizagem Profunda, por João Carreira (Deepmind).

A brief overview of advances in video understanding and generation from the last decade, covering architectures, learning approaches and datasets - all the way from Kinetics-based 3d convolutional networks all the way to SORA.

Bio: João Carreira is a Research Scientist at Google DeepMind. He completed his PhD at the University of Bonn and was a PostDoc at Berkeley. His focus at DeepMind has been on learning from video, and was one of the core creators of the Kinetics dataset and more recently the Perception Test, and the I3D and Perceiver models.