Paper
Publication
Input-level Inductive Biases for 3D Reconstruction
Paper
Publication
More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech
Paper
Publication
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
Paper
Publication
Temporal Cycle-Consistency Learning
Paper
Publication
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Paper
Publication
GuessWhat?! Visual object discovery through multi-modal dialogue