November 3, 2018

Exploring the Effect of Computer-Generated Descriptions on the Photo Sharing Experience of People with Visual Impairments

Conference on Computer-Supported Cooperative Work and Social Computing (CSCW)

Like sighted people, visually impaired people want to share photographs on social networking services, but find it difficult to identify and select photos from their albums. We aimed to address this problem by incorporating state-of-the-art computer-generated descriptions into Facebook’s photo-sharing feature.

Yuhang Zhao, Shaomei Wu, Lindsay Reynolds, Shiri Azenkot
April 25, 2018

Examining the Demand for Spam: Who Clicks?

Conference on Human Factors in Computing Systems (CHI)

Some spam content manages to evade detection and engage users which is why, in this paper, we focus on the demand side of the spam equation examining what drives users to click on spam via a largescale analysis of de-identified, aggregated Facebook log data (n=600,000).

Elissa M. Redmiles, Neha Chachra, Brian Waismeyer
April 25, 2018

A Face Recognition Application for People with Visual Impairments: Understanding Use Beyond the Lab

Conference on Human Factors in Computing Systems (CHI)

We present Accessibility Bot, a research prototype bot on Facebook Messenger, which leverages state-of-the-art computer vision algorithms and the existing set of tagged photos of a user’s friends on Facebook to help people with visually impairments recognize their friends.

Yuhang Zhao, Shaomei Wu, Lindsay Reynolds, Shiri Azenkot
April 21, 2018

Communication Behavior in Embodied Virtual Reality

Human Computer Interaction Conference (CHI)

To investigate communication behavior with embodied virtual reality onto an avatar in a virtual 3D environment, we had 30 dyads complete two tasks using a shared visual workspace: negotiating an apartment layout and placing model furniture on an apartment floor plan.

Harrison Jesse Smith, Michael Neff
April 21, 2018

Coding Tactile Symbols for Phonemic Communication

Conference on Human Factors in Computing Systems (CHI)

We present a study to examine one’s learning and processing capacity of broadband tactile information, such as that derived from speech.

Siyan Zhao, Ali Israr, Frances Lau, Freddy Abnousi
February 4, 2018

StarSpace: Embed All The Things!

Conference on Artificial Intelligence (AAAI)

We present StarSpace, a general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification, ranking tasks such as information retrieval/web search, collaborative filtering-based or content-based recommendation, embedding of multi-relational graphs, and learning word, sentence or document level embeddings.

Ledell Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, Jason Weston
February 2, 2018

Efficient Large-Scale Multi-Modal Classification

Conference on Artificial Intelligence (AAAI)

We investigate various methods for performing multi-modal fusion and analyze their trade-offs in terms of classification accuracy and computational efficiency.

Douwe Kiela, Edouard Grave, Armand Joulin, Tomas Mikolov
January 14, 2018

Experimental Demonstration of Digital Pre-Distortion for Millimeter Wave Power Amplifiers with GHz Bandwidth

IEEE Radio Wireless Week (RWW)

This paper presents an experimental demonstration of digital pre-distortion (DPD) on E-band power amplifiers (PA) with GHz channel bandwidth.

Qi Tang, Hongyu Zhou, Abhishek Tiwari, Joseph Stewart, Qi Qu, Dawei Zhang, Hamid Hemmati
December 12, 2017

Supporting Diverse Dynamic Intent-based Policies using Janus

International Conference on emerging Networking EXperiments and Technologies (CoNEXT)

In this paper we propose Janus, a system which makes two major contributions to network policy abstractions. First, we extend the prior policy graph abstraction model to represent complex QoS and dynamic stateful/temporal policies. Second, we convert the policy configuration problem into an optimization problem with the goal of maximizing the number of satisfied and configured policies, and minimizing the number of path changes under dynamic environments.

Anubhavnidhi Abhashkumar, Joon-Myung Kang, Sujata Banerjee, Aditya Akella, Ying Zhang, Wenfei Wu
December 10, 2017

Social Structure and Trust in Massive Digital Markets

International Conference on Information Systems (ICIS)

In this paper we measure the extent to which situating transactions in networks can generate trust in online marketplaces with an empirical approach that provides external validity while eliminating many potential confounds.

David Holtz, Diana Lynn MacLean, Sinan Aral
December 4, 2017

One-Sided Unsupervised Domain Mapping

Neural Information Processing Systems (NIPS)

In this work, we present a method of learning GAB without learning GBA. This is done by learning a mapping that maintains the distance between a pair of samples.

Sagie Benaim, Lior Wolf
December 4, 2017

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

Neural Information Processing Systems (NIPS)

In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research.

Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, Larry Zitnick
December 4, 2017

Unbounded Cache Model for Online Language Modeling with Open Vocabulary

Neural Information Processing Systems (NIPS)

In this paper, we propose an extension of continuous cache models, which can scale to larger contexts. In particular, we use a large scale non-parametric memory component that stores all the hidden activations seen in the past.

Edouard Grave, Moustapha Cisse, Armand Joulin
December 4, 2017

VAIN: Attentional Multi-agent Predictive Modeling

Neural Information Processing Systems (NIPS)

In this paper we introduce VAIN, a novel attentional architecture for multi-agent predictive modeling that scales linearly with the number of agents. Multi-agent predictive modeling is an essential step for understanding physical, social and team-play systems.

Yedid Hoshen
December 4, 2017

Gradient Episodic Memory for Continual Learning

Neural Information Processing Systems (NIPS)

One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge. To better understand this issue, we study the problem of continual learning, where the model observes, once and one by one, examples concerning a sequence of tasks.

David Lopez-Paz, Marc'Aurelio Ranzato
December 4, 2017

Poincaré Embeddings for Learning Hierarchical Representations

Neural Information Processing Systems (NIPS)

In this work, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space – or more precisely into an n-dimensional Poincaré ball.

Maximilian Nickel, Douwe Kiela
December 4, 2017

Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples

Neural Information Processing Systems (NIPS)

We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable.

Moustapha Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet
December 4, 2017

Attentive Explanations: Justifying Decisions and Pointing to the Evidence

Interpretable Machine Learning Symposium at NIPS

In this work, we emphasize the importance of model explanation in various forms such as visual pointing and textual justification.

Dong Huk Park, Lisa Anne Hendricks, Zeynep Akata, Anna Rohrbach, Bernt Schiele, Trevor Darrell, Marcus Rohrbach
December 4, 2017

On the Optimization Landscape of Tensor Decompositions

Neural Information Processing Systems (NIPS)

In this paper, we analyze the optimization landscape of the random over-complete tensor decomposition problem, which has many applications in unsupervised learning, especially in learning latent variable models. In practice, it can be efficiently solved by gradient ascent on a non-convex objective.

Rong Ge, Tengyu Ma
December 4, 2017

Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model

Neural Information Processing Systems (NIPS)

We present a novel training framework for neural sequence models, particularly for grounded dialog generation.

Jiasen Lu, Anitha Kannan, Jianwei Yang, Devi Parikh, Dhruv Batra