Research Area
Year Published

631 Results

August 19, 2018

A real-time framework for detecting efficiency regressions in a globally distributed codebase

Knowledge Discovery in Databases (KDD)

This paper describes the end-to-end regression detection system designed and used at Facebook. The main detection algorithm is based on sequential statistics supplemented by signal processing transformations, and the performance of the algorithm was assessed with a mixture of online and offline tests across different use cases.

By: Martin Valdez-Vivas, Caner Gocmen, Andrii Korotkov, Ethan Fang, Kapil Goenka, Sherry Chen
August 16, 2018

Constrained Bayesian Optimization with Noisy Experiments

Bayesian Analysis 2018

We derive an expression for expected improvement under greedy batch optimization with noisy observations and noisy constraints, and develop a quasi-Monte Carlo approximation that allows it to be efficiently optimized.

By: Ben Letham, Brian Karrer, Guilherme Ottoni, Eytan Bakshy
August 14, 2018

Deep Appearance Models for Face Rendering


We introduce a deep appearance model for rendering the human face. Inspired by Active Appearance Models, we develop a data-driven rendering pipeline that learns a joint representation of facial geometry and appearance from a multiview capture setup.

By: Stephen Lombardi, Jason Saragih, Tomas Simon, Yaser Sheikh
August 13, 2018

Unsupervised Generation of Free-Form and Parameterized Avatars


We study two problems involving the task of mapping images between different domains. The first problem, transfers an image in one domain to an analog image in another domain. The second problem, extends the previous one by mapping an input image to a tied pair, consisting of a vector of parameters and an image that is created using a graphical engine from this vector of parameters.

By: Adam Polyak, Yaniv Taigman, Lior Wolf
August 10, 2018

Learning to Feel Words: A Comparison of Learning Approaches to Acquire Haptic Words

ACM Symposium on Applied Perception (SAP)

Recent studies have shown that decomposing spoken or written language into phonemes and transcribing each phoneme into a unique vibrotactile pattern enables people to receive lexical messages on the arm. A potential barrier to adopting this new communication system is the time and effort required to learn the association between phonemes and vibrotactile patterns. Therefore, in this study, we compared the learnability and generalizability of different learning approaches, including guided learning, self-directed learning, and a mnemonic device.

By: Jennifer Chen, Robert Turcott, Pablo Castillo, Wahyudinata Setiawan, Frances Lau, Ali Israr
Areas: AR/VR
July 30, 2018

A Phonemic-Based Tactile Display for Speech Communication

IEEE Transactions on Haptics

Despite a long history of research, the development of synthetic tactual aids to support the communication of speech has proven to be a difficult task. The current paper describes a new tactile speech device based on the presentation of phonemic-based tactile codes.

By: Charlotte M. Reed, Hong Z Tan, Zachary D Perez, E. Courtenay Wilson, Frederico M. Severgnini, Jaehong Jung, Juan S. Martinez, Yang Jiao, Ali Israr, Frances Lau, Keith Klumb, Robert Turcott, Freddy Abnousi
July 29, 2018

Online Optical Marker-based Hand Tracking with Deep Labels

Special Interest Group on Computer Graphics and Interactive Techniques (SIGGRAPH)

We propose a technique that frames the labeling problem as a keypoint regression problem conducive to a solution using convolutional neural networks.

By: Shangchen Han, Beibei Liu, Robert Wang, Yuting Ye, Christopher D. Twigg, Kenrick Kin
July 20, 2018

Controllable Abstractive Summarization

ACL NMT Workshop

We present a neural summarization model with a simple but effective mechanism to enable users to specify these high level attributes in order to control the shape of the final summaries to better suit their needs.

By: Angela Fan, David Grangier, Michael Auli
July 18, 2018

What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties

Association for Computational Linguistics (ACL)

We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.

By: Alexis Conneau, Germán Kruszewski, Guillaume Lample, LoÏc Barrault, Marco Baroni
July 18, 2018

Total Ionizing Dose Assessment of a Commercial 200V PMOSFET

IEEE Nuclear & Space Radiation Effects Conference (NSREC)

Total ionizing dose testing of commercial 200 V PMOSFETs. At 100 kRad(Si), observed VT increase of ~ 3 V for biased ON devices and increase of ~ 1 V for biased OFF devices. The RDS_ON did not degrade with dose.

By: Raichelle Aniceto, Randall Milanowski, Slaven Moro, Norman Hall, Bert Vermeire, Josh Shields, Kerri Cahoy