T
Triantafyllos Afouras
Researcher at University of Oxford
Publications - 39
Citations - 3635
Triantafyllos Afouras is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Sign language. The author has an hindex of 16, co-authored 35 publications receiving 2239 citations.
Papers
More filters
Proceedings Article
Counterfactual Multi−Agent Policy Gradients
TL;DR: In this paper, a multi-agent actor-critic method called counterfactual multiagent (COMA) policy gradients is proposed, which uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.
Journal ArticleDOI
Deep Audio-visual Speech Recognition
TL;DR: This work compares two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss, built on top of the transformer self-attention architecture.
Posted Content
Counterfactual Multi-Agent Policy Gradients
TL;DR: A new multi-agent actor-critic method called counterfactual multi- agent (COMA) policy gradients, which uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.
Posted Content
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
Jakob Foerster,Nantas Nardelli,Gregory Farquhar,Triantafyllos Afouras,Philip H. S. Torr,Pushmeet Kohli,Shimon Whiteson +6 more
TL;DR: In this paper, a multi-agent variant of importance sampling is used to decay obsolete data and conditioning each agent's value function on a fingerprint that disambiguates the age of the data sampled from the replay memory.
Proceedings ArticleDOI
The Conversation: Deep Audio-Visual Speech Enhancement
TL;DR: A deep audio-visual speech enhancement network that is able to separate a speaker's voice given lip regions in the corresponding video, by predicting both the magnitude and the phase of the target signal.