Show from Tell: Audio-Visual Modelling in Clinical Settings

no code implementations • 25 Oct 2023 • Jianbo Jiao, Mohammad Alsharid, Lior Drukker, Aris T. Papageorghiou, Andrew Zisserman, J. Alison Noble

Auditory and visual signals usually present together and correlate with each other, not only in natural environments but also in clinical settings.

Self-Supervised Learning

An Experience Report of Executive-Level Artificial Intelligence Education in the United Arab Emirates

no code implementations • 2 Feb 2022 • David Johnson, Mohammad Alsharid, Rasheed el-Bouri, Nigel Mehdi, Farah Shamout, Alexandre Szenicer, David Toman, Saqr Binghalib

Teaching artificial intelligence (AI) is challenging.

Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound

no code implementations • 14 Aug 2020 • Jianbo Jiao, Yifan Cai, Mohammad Alsharid, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble

For this case, we assume that there is a high correlation between the ultrasound video and the corresponding narrative speech audio of the sonographer.

Contrastive Learning Gaze Prediction +2