388 Results
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.
By: Yedid Hoshen
Facebook AI Research (FAIR) 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.
By: David Lopez-Paz, Marc'Aurelio Ranzato
Facebook AI Research (FAIR) 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.
By: Maximilian Nickel, Douwe Kiela
Facebook AI Research (FAIR) November 27, 2017
Fast Gaze-Contingent Optimal Decompositions for Multifocal Displays
SIGGRAPH ASIA
Our goal is to enable interactive optimal decomposition algorithms capable of driving a vergence- and accommodation-tracked multifocal testbed. Ultimately, such a testbed is necessary to establish the requirements for the practical use of multifocal displays, in terms of computational demand and hardware accuracy. To this end, we present an efficient algorithm for optimal decompositions, incorporating insights from vision science.
By: Oliver Mercier, Yusufu Sulai, Kevin Mackenzie, Marina Zannoli, James Hillis, Derek Nowrouzezahrai, Douglas Lanman
AR/VR November 27, 2017
Casual 3D Photography
SIGGRAPH ASIA
We present an algorithm that enables casual 3D photography. Given a set of input photos captured with a hand-held cell phone or DSLR camera, our algorithm reconstructs a 3D photo, a central panoramic, textured, normal mapped, multi-layered geometric mesh representation. Our geometric representation also allows interacting with the scene using 3D geometry-aware effects, such as adding new objects to the scene and artistic lighting effects.
By: Suhib Alsisan, Richard Szeliski, Johannes Kopf
Computational Photography & Intelligent Cameras 
Computer Vision November 27, 2017
Bringing Portraits to Life
SIGGRAPH ASIA
We present a technique to automatically animate a still portrait, making it possible for the subject in the photo to…
By: Hadar Averbuch-Elor, Daniel Cohen-Or, Johannes Kopf, Michael CohenNovember 14, 2017
Fine Pointing Concepts for Optical Intersatellite Links
International Conference on Space Optical Systems (ICSOS)
In this paper we present two fine pointing architectures that support high-accuracy pointing, while also featuring simplification of the small-space optical assembly hardware, reduction in the number and complexity of constituent components, full self-calibration capability, and relaxation of otherwise-strict, cost-driving subassembly requirements.
By: Eric Miller, Kevin Birnbaum, Chien-Chung Chen, Andrew Grier, Matt Hunwardsen, Dominic Jandrain
Connectivity November 1, 2017
High-Resolution Measurement of Data Center Microbursts
ACM Internet Measurement Conference
In this study, we explore the fine-grained behaviors of a large production data center using extremely highresolution measurements (10s to 100s of microsecond) of rack-level traffic. Our results show that characterizing network events like congestion and synchronized behavior in data centers does indeed require the use of such measurements.
By: Qiao Zhang, Vincent Liu, James Hongyi Zeng, Arvind Krishnamurthy
Systems & Networking November 1, 2017
An Empirical Characterization of IFTTT: Ecosystem, Usage, and Performance
ACM Internet Measurement Conference 2017
IFTTT is a popular trigger-action programming platform whose applets can automate more than 400 services of IoT devices and web applications. We conduct an empirical study of IFTTT using a combined approach of analyzing data collected for 6 months and performing controlled experiments using a custom testbed.
By: Xianghang Mi, Feng Qian, Ying Zhang, XiaoFeng Wang
Systems & Networking October 30, 2017
Crowd Intelligence Enhances Automated Mobile Testing
Automated Software Engineering Conference (ASE)
In this paper we show that information extracted from crowdbased testing can enhance automated mobile testing and introduce POLARIZ, which generates replicable test scripts from crowd-based testing, extracting cross-app ‘motif’ events.
By: Ke Mao, Mark Harman, Yue Jia
Systems & Networking