Temporal Gaussian Mixture Layer for Videos

ICLR 2019 2 code implementations

We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos.

 SOTA for Action Detection on THUMOS' 14 (using extra training data)

ACTION DETECTION ACTIVITY DETECTION

E3: Entailment-driven Extracting and Editing for Conversational Machine Reading

ACL 2019 1 code implementation

Conversational machine reading systems help users answer high-level questions (e. g. determine if they qualify for particular government benefits) when they do not know the exact rules by which the determination is made(e. g. whether they need certain income levels or veteran status).

READING COMPREHENSION

Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data

13 Aug 20181 code implementation

We present hidden fluid mechanics (HFM), a physics informed deep learning framework capable of encoding an important class of physical laws governing fluid motions, namely the Navier-Stokes equations.

Multi$^{\mathbf{3}}$Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery

5 Dec 20181 code implementation

We propose a novel approach for rapid segmentation of flooded buildings by fusing multiresolution, multisensor, and multitemporal satellite imagery in a convolutional neural network.

FLOODED BUILDING SEGMENTATION

Mapping Informal Settlements in Developing Countries using Machine Learning and Low Resolution Multi-spectral Data

3 Jan 20191 code implementation

2) We show that it is possible to detect informal settlements using freely available low-resolution (LR) data, in contrast to previous studies that use very-high resolution (VHR) satellite and aerial imagery, something that is cost-prohibitive for NGOs.

Adversarial Uncertainty Quantification in Physics-Informed Neural Networks

9 Nov 20182 code implementations

We present a deep learning framework for quantifying and propagating uncertainty in systems governed by non-linear differential equations using physics-informed neural networks.

LATENT VARIABLE MODELS

Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials

18 Feb 20191 code implementation

Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges.

Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning

6 Jul 20161 code implementation

Our method is open source and freely available for the community to use.

Deep Neural Networks for Bot Detection

12 Feb 20182 code implementations

In this paper, we propose a deep neural network based on contextual long short-term memory (LSTM) architecture that exploits both content and metadata to detect bots at the tweet level: contextual features are extracted from user metadata and fed as auxiliary input to LSTM deep nets processing the tweet text.

SENTIMENT ANALYSIS

Physics-Informed Neural Networks for Power Systems

9 Nov 20192 code implementations

This work unlocks a range of opportunities in power systems, being able to determine dynamic states, such as rotor angles and frequency, and uncertain parameters such as inertia and damping at a fraction of the computational time required by conventional methods.