Explore the latest research from Facebook

All Publications

August 20, 2021 Virginie Do, Jamal Atif, Jérôme Lang, Nicolas Usunier
Paper

Online Selection of Diverse Committees

We study three methods, theoretically and experimentally: a greedy algorithm that includes volunteers as long as proportionality is not violated; a non-adaptive method that includes a volunteer with a probability depending only on their features, assuming that the joint feature distribution in the volunteer pool is known; and a reinforcement learning based approach when this distribution is not known a priori but learnt online.
Paper
June 18, 2021 Oran Gafni, Oron Ashual, Lior Wolf
Paper

Single-Shot Freestyle Dance Reenactment

In this work, we propose a novel method that can reanimate a single image by arbitrary video sequences, unseen during training. The method combines three networks: (i) a segmentationmapping network, (ii) a realistic frame-rendering network, and (iii) a face refinement network.
Paper
June 11, 2021 Alexandros Haliassos, Konstantinos Vougioukas, Stavros Petridis, Maja Pantic
Paper

Lips Don’t Lie: A Generalisable and Robust Approach to Face Forgery Detection

In this paper, we propose LipForensics, a detection approach capable of both generalizing to novel manipulations and withstanding various distortions. LipForensics targets high-level semantic irregularities in mouth movements, which are common in many generated videos. It consists in first pretraining a spatio-temporal network to perform visual speech recognition (lipreading), thus learning rich internal representations related to natural mouth motion.
Paper
June 7, 2021 Brandon Amos, Samuel Stanton, Denis Yarats, Andrew Gordon Wilson
Paper

On the model-based stochastic value gradient for continuous reinforcement learning

In response, researchers have proposed model-based agents with increasingly complex components, from ensembles of probabilistic dynamics models, to heuristics for mitigating model error. In a reversal of this trend, we show that simple model-based agents can be derived from existing ideas that not only match, but outperform state-of-the-art model-free agents in terms of both sample-efficiency and final reward.
Paper
June 6, 2021 Panagiotis Tzirakis, Anurag Kumar, Jacob Donley
Paper

Multi-Channel Speech Enhancement Using Graph Neural Networks

In this paper, we introduce a different research direction by viewing each audio channel as a node lying in a non-Euclidean space and, specifically, a graph.
Paper
June 6, 2021 Yaxuan Zhou, Hao Jiang, Vamsi Krishna Ithapu
Paper

On the Predictability of HRTFs from Ear Shapes Using Deep Networks

Using 3D ear shapes as inputs, we explore the bounds of HRTF predictability using deep neural networks. To that end, we propose and evaluate two models, and identify the lowest achievable spectral distance error when predicting the true HRTF magnitude spectra.
Paper
June 6, 2021 Lingfei Wu, Yu Chen, Heng Ji, Yunyao Li
Paper

Deep Learning on Graphs for Natural Language Processing

This tutorial of Deep Learning on Graphs for Natural Language Processing (DLG4NLP) is timely for the computational linguistics community, and covers relevant and interesting topics, including automatic graph construction for NLP, graph representation learning for NLP, various advanced GNN based models (e.g., graph2seq, graph2tree, and graph2graph) for NLP, and the applications of GNNs in various NLP tasks (e.g., machine translation, natural language generation, information extraction and semantic parsing).
Paper
June 1, 2021 Bindita Chaudhuri, Nikolaos Sarafianos, Linda Shapiro, Tony Tung
Paper

Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans

We introduce a novel approach to generate diverse high fidelity texture maps for 3D human meshes in a semi- supervised setup.
Paper
May 31, 2021 Rogerio Bonatti, Arthur Bucker, Sebastian Scherer, Mustafa Mukadam, Jessica Hodgins
Paper

Batteries, camera, action! Learning a semantic control space for expressive robot cinematography

In this work, we develop a data-driven framework that enables editing of these complex camera positioning parameters in a semantic space (e.g. calm, enjoyable, establishing).
Paper
May 19, 2021 Brian R. Bartoldson, Ari S. Morcos, Adrian Barbu, Gordon Erlebacher
Paper

The Generalization-Stability Tradeoff In Neural Network Pruning

We demonstrate that this “generalization-stability tradeoff” is present across a wide variety of pruning settings and propose a mechanism for its cause: pruning regularizes similarly to noise injection. Supporting this, we find less pruning stability leads to more model flatness and the benefits of pruning do not depend on permanent parameter removal.
Paper