MERL

∙ Cambridge , United States ∙ 0 followers

Mitsubishi Electric Research Laboratories (MERL) is the North American arm of the Corporate R&D organization of Mitsubishi Electric Corporation.

Audio-Visual Scene-Aware Dialog

We introduce the task of scene-aware dialog. Given a follow-up question ...
01/25/2019 ∙ by Huda Alamri, et al. ∙ 48 ∙ share

read it
ViewSynth: Learning Local Features from Depth using View Synthesis

We address the problem of jointly detecting keypoints and learning descr...
11/22/2019 ∙ by Jisan Mahmud, et al. ∙ 14 ∙ share

read it
Local Policy Optimization for Trajectory-Centric Reinforcement Learning

The goal of this paper is to present a method for simultaneous trajector...
01/22/2020 ∙ by Patrik Kolaric, et al. ∙ 14 ∙ share

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 ...
03/15/2020 ∙ by Pengxiang Wu, et al. ∙ 13 ∙ share

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...
02/15/2019 ∙ by Bharathkumar Ramachandra, et al. ∙ 12 ∙ share

read it
Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs

Graph convolutional networks (GCNs) suffer from the irregularity of grap...
09/26/2019 ∙ by Yecheng Lyu, et al. ∙ 8 ∙ share

read it
Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction

We propose a new concept of rateless auto-encoders (RL-AEs) that enable ...
05/06/2020 ∙ by Toshiaki Koike-Akino, et al. ∙ 5 ∙ share

read it
Sem-GAN: Semantically-Consistent Image-to-Image Translation

Unpaired image-to-image translation is the problem of mapping an image i...
07/12/2018 ∙ by Anoop Cherian, et al. ∙ 4 ∙ share

read it
Spatio-Temporal Ranked-Attention Networks for Video Captioning

Generating video descriptions automatically is a challenging task that i...
01/17/2020 ∙ by Anoop Cherian, et al. ∙ 4 ∙ share

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...
11/20/2017 ∙ by Ziming Zhang, et al. ∙ 0 ∙ share

read it
BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning

Understanding the global optimality in deep learning (DL) has been attra...
11/19/2017 ∙ by Ziming Zhang, et al. ∙ 0 ∙ share

read it
3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances

Unsupervised object modeling is important in robotics, especially for ha...
10/17/2017 ∙ by Wim Abbeloos, et al. ∙ 0 ∙ share

read it
Full-Capacity Unitary Recurrent Neural Networks

Recurrent neural networks are powerful models for processing sequential ...
10/31/2016 ∙ by Scott Wisdom, et al. ∙ 0 ∙ share

read it
Submodular Function Maximization for Group Elevator Scheduling

We propose a novel approach for group elevator scheduling by formulating...
06/28/2017 ∙ by Srikumar Ramalingam, et al. ∙ 0 ∙ share

read it
Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge

Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) is demo...
08/21/2017 ∙ by David Zhuzhunashvili, et al. ∙ 0 ∙ share

read it
Deep clustering: Discriminative embeddings for segmentation and separation

We address the problem of acoustic source separation in a deep learning ...
08/18/2015 ∙ by John R. Hershey, et al. ∙ 0 ∙ share

read it
Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures

Model-based methods and deep neural networks have both been tremendously...
09/09/2014 ∙ by John R. Hershey, et al. ∙ 0 ∙ share

read it
Online Convolutional Dictionary Learning for Multimodal Imaging

Computational imaging methods that can exploit multiple modalities have ...
06/13/2017 ∙ by Kevin Degraux, et al. ∙ 0 ∙ share

read it
CASENet: Deep Category-Aware Semantic Edge Detection

Boundary and edge cues are highly beneficial in improving a wide variety...
05/27/2017 ∙ by Zhiding Yu, et al. ∙ 0 ∙ share

read it
Signal reconstruction via operator guiding

Signal reconstruction from a sample using an orthogonal projector onto a...
05/09/2017 ∙ by Andrew Knyazev, et al. ∙ 0 ∙ share

read it
SEAGLE: Sparsity-Driven Image Reconstruction under Multiple Scattering

Multiple scattering of an electromagnetic wave as it passes through an o...
05/05/2017 ∙ by Hsiou-Yuan Liu, et al. ∙ 0 ∙ share

read it
Signed Laplacian for spectral clustering revisited

Classical spectral clustering is based on a spectral decomposition of a ...
01/05/2017 ∙ by Andrew V. Knyazev, et al. ∙ 0 ∙ share

read it
Representation and Coding of Signal Geometry

Approaches to signal representation and coding theory have traditionally...
12/23/2015 ∙ by Petros T. Boufounos, et al. ∙ 0 ∙ share

read it
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds

Recent deep networks that directly handle points in a point set, e.g., P...
12/19/2017 ∙ by Yaoqing Yang, et al. ∙ 0 ∙ share

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...
12/19/2017 ∙ by Yiru Shen, et al. ∙ 0 ∙ share

read it
Privacy-Preserving Adversarial Networks

We propose a data-driven framework for optimizing privacy-preserving dat...
12/19/2017 ∙ by Ardhendu Tripathy, et al. ∙ 0 ∙ share

read it
Attentional Network for Visual Object Detection

We propose augmenting deep neural networks with an attention mechanism f...
02/06/2017 ∙ by Kota Hara, et al. ∙ 0 ∙ share

read it
Attention-Based Multimodal Fusion for Video Description

Currently successful methods for video description are based on encoder-...
01/11/2017 ∙ by Chiori Hori, et al. ∙ 0 ∙ share

read it
Learning Joint Feature Adaptation for Zero-Shot Recognition

Zero-shot recognition (ZSR) aims to recognize target-domain data instanc...
11/23/2016 ∙ by Ziming Zhang, et al. ∙ 0 ∙ share

read it
Learning optimal nonlinearities for iterative thresholding algorithms

Iterative shrinkage/thresholding algorithm (ISTA) is a well-studied meth...
12/15/2015 ∙ by Ulugbek S. Kamilov, et al. ∙ 0 ∙ share

read it
Compressive Imaging with Iterative Forward Models

We propose a new compressive imaging method for reconstructing 2D or 3D ...
10/05/2016 ∙ by Hsiou-Yuan Liu, et al. ∙ 0 ∙ share

read it
Coupled Generative Adversarial Networks

We propose coupled generative adversarial network (CoGAN) for learning a...
06/24/2016 ∙ by Ming-Yu Liu, et al. ∙ 0 ∙ share

read it
Depth Superresolution using Motion Adaptive Regularization

Spatial resolution of depth sensors is often significantly lower compare...
03/04/2016 ∙ by Ulugbek S. Kamilov, et al. ∙ 0 ∙ share

read it
Learning to Remove Multipath Distortions in Time-of-Flight Range Images for a Robotic Arm Setup

Range images captured by Time-of-Flight (ToF) cameras are corrupted with...
01/08/2016 ∙ by Kilho Son, et al. ∙ 0 ∙ share

read it
Accelerated graph-based nonlinear denoising filters

Denoising filters, such as bilateral, guided, and total variation filter...
12/01/2015 ∙ by Andrew Knyazev, et al. ∙ 0 ∙ share

read it
Sequential Optimization for Efficient High-Quality Object Proposal Generation

We are motivated by the need for a generic object proposal generation al...
11/14/2015 ∙ by Ziming Zhang, et al. ∙ 0 ∙ share

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...
11/13/2015 ∙ by Oncel Tuzel, et al. ∙ 0 ∙ share

read it
Deep Gaussian Conditional Random Field Network: A Model-based Deep Network for Discriminative Denoising

We propose a novel deep network architecture for image denoising based ...
11/12/2015 ∙ by Raviteja Vemulapalli, et al. ∙ 0 ∙ share

read it
Edge-enhancing Filters with Negative Weights

In [DOI:10.1109/ICMEW.2014.6890711], a graph-based denoising is performe...
09/08/2015 ∙ by Andrew Knyazev, et al. ∙ 0 ∙ share

read it
Accelerated graph-based spectral polynomial filters

Graph-based spectral denoising is a low-pass filtering using the eigende...
09/08/2015 ∙ by Andrew Knyazev, et al. ∙ 0 ∙ share

read it
Conjugate Gradient Acceleration of Non-Linear Smoothing Filters

The most efficient signal edge-preserving smoothing filters, e.g., for d...
09/04/2015 ∙ by Andrew Knyazev, et al. ∙ 0 ∙ share

read it
Layered Interpretation of Street View Images

We propose a layered street view model to encode both depth and semantic...
06/15/2015 ∙ by Ming-Yu Liu, et al. ∙ 0 ∙ share

read it
Deep Hierarchical Parsing for Semantic Segmentation

This paper proposes a learning-based approach to scene parsing inspired ...
03/09/2015 ∙ by Abhishek Sharma, et al. ∙ 0 ∙ share

read it
Efficient Upsampling of Natural Images

We propose a novel method of efficient upsampling of a single natural im...
02/28/2015 ∙ by Chinmay Hegde, et al. ∙ 0 ∙ share

read it
Unsupervised Network Pretraining via Encoding Human Design

Over the years, computer vision researchers have spent an immense amount...
02/19/2015 ∙ by Ming-Yu Liu, et al. ∙ 0 ∙ share

read it
Greedy Sparsity-Constrained Optimization

Sparsity-constrained optimization has wide applicability in machine lear...
03/25/2012 ∙ by Sohail Bahmani, et al. ∙ 0 ∙ share

read it
Online Coordinate Boosting

We present a new online boosting algorithm for adapting the weights of a...
10/24/2008 ∙ by Raphael Pelossof, et al. ∙ 0 ∙ share

read it
End-to-end Conversation Modeling Track in DSTC6

End-to-end training of neural networks is a promising approach to automa...
06/22/2017 ∙ by Chiori Hori, et al. ∙ 0 ∙ share

read it
Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM

We present a state-of-the-art end-to-end Automatic Speech Recognition (A...
06/08/2017 ∙ by Takaaki Hori, et al. ∙ 0 ∙ share

read it
A Short Note on Improved ROSETA

This note presents a more efficient formulation of the robust online sub...
10/16/2017 ∙ by Hassan Mansour, et al. ∙ 0 ∙ share

read it

MERL

Featured Researchers