2022 . 05 . 18
Online

AI-Café presents: Deep Ensembles for the Prediction of Media Interestingness

May 18th, 2022 (from 3 PM to 4PM CEST)

Speaker:

Mihai Gabriel Constantin

(Researcher at the AI Multimedia Lab, University Politehnica of Bucharest)

Description of the Talk:

In the context of the ever-growing quantity of multimedia content from social, news and educational platforms, generating meaningful recommendations, ratings, and filters now requires a more advanced understanding of their impact on the user, such as their subjective perception. Visual interestingness is one of the most important subjective perception concepts and is currently a popular avenue of research in affective computing.

However, given the high degree of complexity of this subject caused by its inherent multimodality and subjectivity, classical single-system deep neural network-based approaches currently show relatively low prediction capabilities when compared with other computer vision concepts. We will therefore present our advances in deploying a set of larger ensembling-based architectures that use late fusion for greatly increasing single-system results. This session will present one of the first attempts at using a deep neural network as the primary ensembling engine, as well as introduce some novel neural network layers and architectures that are specially designed for ensembling.

Watch the recording:

Speaker's short bio:

Dr. Mihai Gabriel Constantin is a researcher at the AI Multimedia Lab, University Politehnica of Bucharest, Romania, and got his Ph.D. at the Faculty of Electronics, Telecommunications, and Information Technology at the same university.  His Ph.D. topic was “Automatic Analysis of the Visual Impact of Multimedia Data”.  He has authored over 30 scientific papers in international conferences and high-impact journals, with an emphasis on the prediction of the subjective impact of multimedia items on human viewers and deep ensembles, having a Google Scholar h-index of 11.

He participated as a researcher in more than 10 European, national or industry-based research projects, and is a member of technical program committees and reviewer for several workshops, conferences and journals, as well as an organizer for several benchmarking competitions.


AI-Café Team

Carmen Mac Williams Organizer, and Moderator of the AI-Cafe. She is the Director of the company Grassroots Arts, and a partner in the European AI4media project.

Emma and Theresa Co-organisers and co-moderators for this new season of Café Season. They are Research Assistants at Grassroots Arts.


This Café is organized by Grassroots Arts. If you have questions about the organisation of this AI-Café or if you want to become a Speaker yourself in one of the next Web Cafe Sessions, please contact carmen@grassroots-arts.eu.

The recordings of the past Web Cafes you can find on our AI-Café video channel: https://www.gotostage.com/channel/ai-cafe. Here is the link to the AI-Cafe website: https://ai-cafe.eu/

AI-Cafe WEBCAFE – INFORMATION LEGAL NOTICE > HERE

COOKIES

AI4Media may use cookies to store your login data, collect statistics to optimize the website's functionality and to perform marketing actions based on your interests.

COOKIES
They allow you to browse the website and use its applications as well as to access secure areas of the website. Without these cookies, the services you have requested cannot be provided.
These cookies are necessary to allow the main functionality of the website and they are activated automatically when you enter this website. They store user preferences for site usage so that you do not need to reconfigure the site each time you visit it.
These cookies direct advertising according to the interests of each user so as to direct advertising campaigns, taking into account the tastes of users, and they also limit the number of times you see the ad, helping to measure the effectiveness of advertising and the success of the website organisation.

Required Cookies They allow you to browse the website and use its applications as well as to access secure areas of the website. Without these cookies, the services you have requested cannot be provided.

Functional Cookies These cookies are necessary to allow the main functionality of the website and they are activated automatically when you enter this website. They store user preferences for site usage so that you do not need to reconfigure the site each time you visit it.

Advertising Cookies These cookies direct advertising according to the interests of each user so as to direct advertising campaigns, taking into account the tastes of users, and they also limit the number of times you see the ad, helping to measure the effectiveness of advertising and the success of the website organisation.