[C4AI – Perspectives in A.I. Seminar] Next talk of the Perspectives in AI seminar of the C4AI will host: Prof. Dr. Thamar Solorio, (Professor in the department of NLP at MBZUAI and tenured professor of Computer Science at the University of Houston) on February 20th 2024, 11h – 12h30​​ Brasilia time, to talk about “Exploring the Limits of Textual information and Open Models for Video Question Answering”.  (Open/free/online event – Seminar in English).  

Title: “Exploring the Limits of Textual information and Open Models for Video Question Answering”
Open and Free seminar – Add to your Agenda!
Add to you agenda (google calendar): https://calendar.google.com/calendar/event?action=TEMPLATE&tmeid=MDZ1aG1taXBmNzc5NWNtZXQ3dHIzN2JyYnYgYzRhaUB1c3AuYnI&tmsrc=c4ai%40usp.br   

C4AI Youtube Channel https://www.youtube.com/c/C4AIUSP
Seminar Link:https://www.youtube.com/watch?v=nKGORrefzRU  (set reminder)

Perspectives in A.I. Seminar: 
Prof. Dr. Thamar Solorio, to talk about “Exploring the Limits of Textual information and Open Models for Video Question Answering”

Abstract:

Video Question Answering (vQA) deals with the problem of answering questions that can be resolved by watching a video, usually a short one, of around one minute or so. The current state of the art (SOTA) solutions to vQA consist of a complex arrangement of large vision and language models, with usually expensive end to end training involved and/or relying on APIs of closed models. The use of closed models is an interesting exercise, but we have no ability to perform error analysis or room to inspect the model for potential contamination in the training set. Even so, there is still a huge performance gap from these sophisticated solutions compared to human performance. My group has been exploring the adaptation of SOTA solutions to vQA problems with open domain models and lower computational needs. In particular, we have been focusing on generating richer textual representations of the video frames. During this talk I will present our recent results and lessons learned on these efforts.
 
Short-Bio:

Thamar Solorio is a Professor in the department of NLP at MBZUAI. She is also a tenured professor of Computer Science at the University of Houston. She is the director and founder of the RiTUAL Lab. Her research interests include multilinguality and low resource NLP, as well as information extraction, and more recently, language and vision problems. She is the recipient of an National Science Foundation (NSF) CAREER award for her work on authorship attribution, and recipient of the 2014 Emerging Leader ABIE Award in Honor of Denice Denton. She just completed two terms as elected board member of the North American Chapter of the Association of Computational Linguistics (NAACL) and was PC co-chair for NAACL 2019. She is an Editor in Chief for the ACL Rolling Review (ARR) initiative and member of the advisory board for ARR. Her research has been funded by NSF and ADOBE.
LinkedIn: https://www.linkedin.com/in/thamar-solorio/ 

#c4ai #ArtificialIntelligence #AIResearch

Categories:

Tags:

Comments are closed