Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. Architectures such as Convolutional Neural Networks (CNNs) and more recently the Transformer based on Attention mechanisms are solving many problem in the Computer Vision field. This course will cover the principles of deep learning applied to different Computer Vision applications as well as covering the basics of Multimodal Learning.

The course webpage can be found: [2019], [2018], [2017], [2016]

DLCV Lectures (2018)