
AudioVisual SceneAware Dialog
We introduce the task of sceneaware dialog. Given a followup question ...
read it

ViewSynth: Learning Local Features from Depth using View Synthesis
We address the problem of jointly detecting keypoints and learning descr...
read it

Local Policy Optimization for TrajectoryCentric Reinforcement Learning
The goal of this paper is to present a method for simultaneous trajector...
read it

MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
The ability to reliably perceive the environmental states, particularly ...
read it

Street Scene: A new dataset and evaluation protocol for video anomaly detection
Progress in video anomaly detection research is currently slowed by smal...
read it

GraphPreserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs
Graph convolutional networks (GCNs) suffer from the irregularity of grap...
read it

Stochastic Bottleneck: Rateless AutoEncoder for Flexible Dimensionality Reduction
We propose a new concept of rateless autoencoders (RLAEs) that enable ...
read it

SemGAN: SemanticallyConsistent ImagetoImage Translation
Unpaired imagetoimage translation is the problem of mapping an image i...
read it

SpatioTemporal RankedAttention Networks for Video Captioning
Generating video descriptions automatically is a challenging task that i...
read it

Invariant Representations from Adversarially Censored Autoencoders
We combine conditional variational autoencoders (VAE) with adversarial c...
read it

Channel Decoding with Quantum Approximate Optimization Algorithm
Motivated by the recent advancement of quantum processors, we investigat...
read it

Deep LearningBased Constellation Optimization for Physical Network Coding in TwoWay Relay Networks
This paper studies a new application of deep learning (DL) for optimizin...
read it

Learning to Modulate for Noncoherent MIMO
The deep learning trend has recently impacted a variety of fields, inclu...
read it

Polar Coding with Chemical Reaction Networks
In this paper, we propose a new polar coding scheme with molecular progr...
read it

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning
In this paper, we propose a reinforcement learningbased algorithm for t...
read it

Neural Turbo Equalization: Deep Learning for FiberOptic Nonlinearity Compensation
Recently, datadriven approaches motivated by modern deep learning have ...
read it

Efficient Exploration in Constrained Environments with GoalOriented Reference Path
In this paper, we consider the problem of building learning agents that ...
read it

Analysis of Nonlinear Fiber Interactions for FiniteLength ConstantComposition Sequences
In order to realize probabilistically shaped signaling within the probab...
read it

Huffmancoded Sphere Shaping and Distribution Matching Algorithms via Lookup Tables
In this paper, we study amplitude shaping schemes for the probabilistic ...
read it

Robust Machine Learning via Privacy/RateDistortion Theory
Robust machine learning formulations have emerged to address the prevale...
read it

Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
By lifting the ReLU function into a higher dimensional space, we develop...
read it

BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
Understanding the global optimality in deep learning (DL) has been attra...
read it

3D Object Discovery and Modeling Using Single RGBD Images Containing Multiple Object Instances
Unsupervised object modeling is important in robotics, especially for ha...
read it

FullCapacity Unitary Recurrent Neural Networks
Recurrent neural networks are powerful models for processing sequential ...
read it

Submodular Function Maximization for Group Elevator Scheduling
We propose a novel approach for group elevator scheduling by formulating...
read it

Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge
Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) is demo...
read it

Deep clustering: Discriminative embeddings for segmentation and separation
We address the problem of acoustic source separation in a deep learning ...
read it

Deep Unfolding: ModelBased Inspiration of Novel Deep Architectures
Modelbased methods and deep neural networks have both been tremendously...
read it

Online Convolutional Dictionary Learning for Multimodal Imaging
Computational imaging methods that can exploit multiple modalities have ...
read it

CASENet: Deep CategoryAware Semantic Edge Detection
Boundary and edge cues are highly beneficial in improving a wide variety...
read it

Signal reconstruction via operator guiding
Signal reconstruction from a sample using an orthogonal projector onto a...
read it

SEAGLE: SparsityDriven Image Reconstruction under Multiple Scattering
Multiple scattering of an electromagnetic wave as it passes through an o...
read it

Signed Laplacian for spectral clustering revisited
Classical spectral clustering is based on a spectral decomposition of a ...
read it

Representation and Coding of Signal Geometry
Approaches to signal representation and coding theory have traditionally...
read it

FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
Recent deep networks that directly handle points in a point set, e.g., P...
read it

Neighbors Do Help: Deeply Exploiting Local Structures of Point Clouds
Unlike on images, semantic learning on 3D point clouds using a deep netw...
read it

PrivacyPreserving Adversarial Networks
We propose a datadriven framework for optimizing privacypreserving dat...
read it

Attentional Network for Visual Object Detection
We propose augmenting deep neural networks with an attention mechanism f...
read it

AttentionBased Multimodal Fusion for Video Description
Currently successful methods for video description are based on encoder...
read it

Learning Joint Feature Adaptation for ZeroShot Recognition
Zeroshot recognition (ZSR) aims to recognize targetdomain data instanc...
read it

Learning optimal nonlinearities for iterative thresholding algorithms
Iterative shrinkage/thresholding algorithm (ISTA) is a wellstudied meth...
read it

Compressive Imaging with Iterative Forward Models
We propose a new compressive imaging method for reconstructing 2D or 3D ...
read it

Coupled Generative Adversarial Networks
We propose coupled generative adversarial network (CoGAN) for learning a...
read it

Depth Superresolution using Motion Adaptive Regularization
Spatial resolution of depth sensors is often significantly lower compare...
read it

Learning to Remove Multipath Distortions in TimeofFlight Range Images for a Robotic Arm Setup
Range images captured by TimeofFlight (ToF) cameras are corrupted with...
read it

Accelerated graphbased nonlinear denoising filters
Denoising filters, such as bilateral, guided, and total variation filter...
read it

Sequential Optimization for Efficient HighQuality Object Proposal Generation
We are motivated by the need for a generic object proposal generation al...
read it

Robust Face Alignment Using a Mixture of Invariant Experts
Face alignment, which is the task of finding the locations of a set of f...
read it

Deep Gaussian Conditional Random Field Network: A Modelbased Deep Network for Discriminative Denoising
We propose a novel deep network architecture for image denoising based ...
read it

Edgeenhancing Filters with Negative Weights
In [DOI:10.1109/ICMEW.2014.6890711], a graphbased denoising is performe...
read it
MERL
Mitsubishi Electric Research Laboratories (MERL) is the North American arm of the Corporate R&D organization of Mitsubishi Electric Corporation.