Publications

Publication

August 09, 2021

COMPUTER VISION

GRAPHICS

Deep Relightable Appearance Models for Animatable Faces

We present a method for building high-fidelity animatable 3D face models that can be posed and rendered with novel lighting environments in real-time. …

Sai Bi, Stephen Lombardi,Shunsuke Saito, Tomas Simon, Shih-en Wei, Kevyn McPhail, Ravi Ramamoorthi, Yaser Sheikh, Jason Saragih

August 09, 2021

Read the Paper

Publication

June 19, 2021

CORE MACHINE LEARNING

COMPUTER VISION

Robust Audio-Visual Instance Discrimination

We present a self-supervised learning method to learn audio and video representations …

Pedro Morgado, Ishan Misra, Nuno Vasconcelos

June 19, 2021

Read the Paper

Publication

June 19, 2021

COMPUTER VISION

Fast and Accurate Model Scaling

In this work we analyze strategies for convolutional neural network scaling; that is, the process of scaling a base convolutional network …

Piotr Dollár, Mannat Singh, Ross Girshick

June 19, 2021

Read the Paper

Publication

June 18, 2021

COMPUTER VISION

GRAPHICS

Single-Shot Freestyle Dance Reenactment

The task of motion transfer between a source dancer and a target person is a special case of the pose transfer problem …

Oran Gafni, Oron Ashual Lior Wolf

June 18, 2021

Read the Paper

Publication

June 16, 2021

CORE MACHINE LEARNING

COMPUTER VISION

IIRC: Incremental Implicitly-Refined Classification

We introduce the “Incremental Implicitly-Refined Classification (IIRC)” setup, an extension to the class incremental …

Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar

June 16, 2021

Read the Paper

Publication

June 11, 2021

COMPUTER VISION

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

Although current deep learning-based face forgery detectors achieve impressive performance in constrained scenarios …

Alexandros Haliassos, Konstantinos Vougioukas, Stavros Petridis, Maja Pantic

June 11, 2021

Read the Paper

Publication

June 10, 2021

COMPUTER VISION

TextStyleBrush: Transfer of text aesthetics from a single example

We present a novel approach for disentangling the content of a text image from all aspects of its appearance …

Praveen Krishnan, Rama Kovvuri, Guan Pang, Boris Vassilev, Tal Hassner

June 10, 2021

Read the Paper

Publication

June 01, 2021

NLP

The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks…

Naman Goyal, Cynthia Gao, Vishrav Chaudhary, Peng-Jen Chen, Guillaume Wenzek, Da Ju, Sanjana Krishnan, Marc’Aurelio Ranzato, Francisco Guzmán, Angela Fan

June 01, 2021

Read the Paper

Publication

May 31, 2021

ROBOTICS

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

Aerial vehicles are revolutionizing the way film-makers can capture shots of actors by composing novel aerial and dynamic viewpoints …

Rogerio Bonatti, Arthur Bucker, Sebastian Scherer, Mustafa Mukadam, Jessica Hodgins

May 31, 2021

Read the Paper

Publication

May 29, 2021

NLP

Autoregressive Entity Retrieval

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities …

Nicola De Cao, , Gautier Izacard, Sebastian Riedel, Fabio Petroni

May 29, 2021

Read the Paper

Publication

May 21, 2021

NLP

Unsupervised Speech Recognition

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a “downstream” task to guide the process of phrase…

Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli

May 21, 2021

Read the Paper

Publication

May 19, 2021

SYSTEMS RESEARCH

TT-REC: Tensor Train Compression for Deep Learning Recommendation Model Embeddings

The memory capacity of embedding tables in deep learning recommendation models (DLRMs) is increasing dramatically from tens of GBs to TBs across the industry …