1 citations · 3 across the 4 of their papers we have counts for
4 papers
PDFed: Privacy-Preserving and Decentralized Asynchronous Federated Learning for Diffusion Models
Kar Balan, Andrew Gilbert, John Collomosse
We present PDFed, a decentralized, aggregator-free, and asynchronous federated learning protocol for training image diffusion models using a public blockchain. In general, diffusio…
Interpretable Action Recognition on Hard to Classify Actions
Anastasia Anichenko, Frank Guerin, Andrew Gilbert
We investigate a human-like interpretable model of video understanding. Humans recognise complex activities in video by recognising critical spatio-temporal relations among explici…
Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization
Edward Fish, Jon Weinbren, Andrew Gilbert
Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyra…
MOFO: MOtion FOcused Self-Supervision for Video Understanding
Mona Ahmadian, Frank Guerin, Andrew Gilbert
Self-supervised learning (SSL) techniques have recently produced outstanding results in learning visual representations from unlabeled videos. Despite the importance of motion in s…