Schedule StuTS 68

Talk

Multimodal Learning: Integrating Vision and Language

What is Multimodal Machine Learning and how far are we in bringing vision and language together?

November 19, 2020 Clotilde Tambroni en Computational Linguistics

We will introduce the concept of multimodality and focus, in the talk, on two modalities, vision and language, to present the (state of the art) deep neural models for processing (multimodal) vision and language inputs.

Multimodal Machine Learning develops models for different input modalities, e.g. different sensorial inputs, like images, text, speech, humidity, pressure.

In this talk, we will introduce the concept of multimodality and focus, in the talk, on two modalities, vision and language, to present the (state of the art) deep neural models for processing (multimodal) vision and language inputs.