Share This Author
Contrastive Representation Learning: A Framework and Review
A general Contrastive Representation Learning framework is proposed that simplifies and unifies many different contrastive learning methods and a taxonomy for each of the components is provided in order to summarise and distinguish it from other forms of machine learning.
Investigating Memorability of Dynamic Media
- Phúc H. Lê Khắc, Ayush Rai, G. Healy, A. Smeaton, N. O’Connor
- Computer ScienceMediaEval
- 31 December 2020
The high-dynamic content in videos and dataset of limited size as the core challenges for the Predicting Media Memorability task are identified and directions to overcome some of these challenges are proposed.