BIU learning club – Assaf Arbelle – What is next in Vision and Language models?

Location:

Building 1300 (students’ dorms), room 1

Title:

What is next in Vision and Language models?

Abstract:

In recent years, two mostly separated fields of machine learning, computer vision and natural language processing, have gradually become closer. Advancements in each field have greatly influenced the other, driven in part by the abundance of weekly annotated data in the form of image-text pairs. These advancements brought focus to the Vision-Language models (VL) which jointly process images and free-text. Our group, the AI-Vision group at IBM Research have focused our research on VL models, their limitations and applications. In this talk, I will present our latest work in the field and covering topics such as Weakly Supervised Phrase Grounding, Foundation Models for Expert Task Applications, Understanding Structured Vision and Language Concepts and more.

Short Bio:

Assaf Arbelle is currently the manager of the AI-Vision group in IBM-Research. The research focus of the group is self-supervised learning for computer vision tasks and vision and language tasks. Assaf received his PhD in 2020 from the department of Electrical and Computer Engineering from Ben-Gurion University of the Negev for his work on “Live Cell Segmentation in Microscopy Videos”.