Home      Discussions      About
Join us
Latest Conferences Trending
ICLR
NIPS
ICML
CVPR
ICCV
ECCV
ICRA
MICCAI
IROS
IJRR
RLDM
ICLR 2019
MIDL
Sep 27, 2017
Computer Vision
Computation and Language

A Read-Write Memory Network for Movie Story Understanding

We propose a novel memory network model named Read-Write Memory Network (RWMN) to perform question and answering tasks for large-scale, multimodal ...
Mar 22, 2017
Conferences: test
Computer Vision

Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D ...

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convol...
Jan 09, 2016
By zs2262
Conferences: test
Computer Vision

Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs

We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained a...
Apr 07, 2017
By csilvia
Conferences: test
Artificial Intelligence
Machine Learning

Recurrent Environment Simulators

Models that can simulate how environments change in response to actions can be used by agents to plan and act efficiently. We improve on previous e...
Aug 30, 2017
Conferences: test
Computer Vision

Pix2face: Direct 3D Face Model Estimation

An efficient, fully automatic method for 3D face shape and pose estimation in unconstrained 2D imagery is presented. The proposed method jointly es...
Jun 07, 2014
Conferences: test
Machine Learning

A Drifting-Games Analysis for Online Learning and Applications to ...

We provide a general mechanism to design online learning algorithms based on a minimax analysis within a drifting-games framework. Different online...
Nov 05, 2017
Conferences: test
Machine Learning
Discrete Mathematics

We demonstrate the practical utility of the proposed framework and compare it to standard baselines. We compare the performance of the algorithms in terms of their wall-clock running time and the obtained utility. We consider the following problems:

Stochastic Submodular Maximization: The Case of Coverage Functions

Stochastic optimization of continuous objectives is at the heart of modern machine learning. However, many important problems are of discrete natur...
May 20, 2016
Conferences: test
Computer Vision
Machine Learning
Neural and Evolutionary Computation

Virtual Worlds as Proxy for Multi-Object Tracking Analysis

Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the ...
Feb 11, 2015
By sioffe
Conferences: test
Machine Learning

Batch Normalization: Accelerating Deep Network Training by Reducing...

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of...
Sep 15, 2017
Conferences: test
Artificial Intelligence
Computer Vision
Robotics

Unsupervised state representation learning with robotic priors: a ...

Our understanding of the world depends highly on our capacity to produce intuitive and simplified representations which can be easily used to solve...
Sep 20, 2017
Conferences: test
Robotics
Artificial Intelligence
Machine Learning
Neural and Optical Computation

Bayesian Optimization with Automatic Prior Selection for Data-Effic...

One of the most interesting features of Bayesian optimization for direct policy search is that it can leverage priors (e.g., from simulation or fro...
May 22, 2017
By mathieu
Machine Learning

Factorization machines and polynomial networks are supervised polynomial models based on an efficient low-rank decomposition. We extend these models to the multi-output setting, i.e., for learning vector-valued functions, with application to multi...

Multi-output Polynomial Networks and Factorization Machines

Factorization machines and polynomial networks are supervised polynomial models based on an efficient low-rank decomposition. We extend these model...
Mar 05, 2018
Conferences: test
Machine Learning

Stochastic Activation Pruning for Robust Adversarial Defense

Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, i...
Mar 16, 2017
Conferences: test
Computer Vision
Machine Learning

Convolutional neural network architecture for geometric matching

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline...
Jun 08, 2015
By songhan
Conferences: test
Neural and Evolutionary Computation
Computer Vision
Machine Learning

Learning both Weights and Connections for Efficient Neural Networks

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional ne...
Oct 26, 2016
Conferences: test
Machine Learning
Social and Information Networks
Physics and Society

Estimating the Size of a Large Network and its Communities from a R...

Most real-world networks are too large to be measured or studied directly and there is substantial interest in estimating global network properties...
May 04, 2017
Conferences: test
Computer Vision

Attributes2Classname: A discriminative model for attribute-based ...

We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim t...
Jun 05, 2017
Conferences: test
Machine Learning

Stochastic Gradient Monomial Gamma Sampler

Recent advances in stochastic gradient techniques have made it possible to estimate posterior distributions from large datasets via Markov Chain Mo...
Apr 02, 2018
Conferences: test
Computer Vision

Learning Descriptor Networks for 3D Shape Synthesis and Analysis

This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The ma...
Feb 08, 2017
Conferences: test
Computation and Language
Artificial Intelligence
Neural and Optical Computation
Machine Learning

In this paper, we introduced a novel method for visualizing the importance of specific inputs in determining the output of an LSTM. By searching for phrases which consistently provide large contributions, we are able to distill trained, state of t...

Automatic Rule Extraction from Long Short Term Memory Networks

Although deep learning models have proven effective at solving problems in natural language processing, the mechanism by which they come to their c...
There aren't more projects

Every arXiv paper needs to be discussed

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description