
UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision
In this paper, we explore how three related tasks, namely keypoint detec...
read it

Visualization of Convolutional Neural Networks for Monocular Depth Estimation
Recently, convolutional neural networks (CNNs) have shown great success ...
read it

FPCCNet: Fast Point Cloud Clustering for Instance Segmentation
Instance segmentation is an important preprocessing task in numerous re...
read it

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
We revisit the problem of estimating depth of a scene from its single RG...
read it

Joint Learning of Multiple Image Restoration Tasks
Convolutional neural networks have recently been successfully applied to...
read it

Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
In this paper, we study design of deep neural networks for tasks of imag...
read it

A vision based system for underwater docking
Autonomous underwater vehicles (AUVs) have been deployed for underwater ...
read it

Deformation estimation of an elastic object by partial observation using a neural network
Deformation estimation of elastic object assuming an internal organ is i...
read it

Exploiting Active Subspaces in Global Optimization: How Complex is your Problem?
When applying optimization method to a realworld problem, the possessio...
read it

HyperNetworks with statistical filtering for defending adversarial examples
Deep learning algorithms have been known to be vulnerable to adversarial...
read it

Optimization on Product Submanifolds of Convolution Kernels
Recent advances in optimization methods used for training convolutional ...
read it

Linear Discriminant Generative Adversarial Networks
We develop a novel method for training of GANs for unsupervised and clas...
read it

QNetworks for Binary Vector Actions
In this paper reinforcement learning with binary vector actions was inve...
read it

Kernel method for persistence diagrams via kernel embedding and weight factor
Topological data analysis is an emerging mathematical concept for charac...
read it

Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs
In this work, we address the problem of improvement of robustness of fea...
read it

Persistence Diagrams with Linear Machine Learning Models
Persistence diagrams have been widely recognized as a compact descriptor...
read it

Structural Data Recognition with Graph Model Boosting
This paper presents a novel method for structural data recognition using...
read it

Truncating Wide Networks using Binary Tree Architectures
Recent study shows that a wide deep network can obtain accuracy comparab...
read it

Looking at Outfit to Parse Clothing
This paper extends fullyconvolutional neural networks (FCN) for the clo...
read it

Automatic Generation of Typographic Font from a Small Font Subset
This paper addresses the automatic generation of a typographic font from...
read it

Selfcalibrationbased Approach to Critical Motion Sequences of Rollingshutter Structure from Motion
In this paper we consider critical motion sequences (CMSs) of rollingsh...
read it

Optimization on Submanifolds of Convolution Kernels in CNNs
Kernel normalization methods have been employed to improve robustness of...
read it

Inverse Renormalization Group Transformation in Bayesian Image Segmentations
A new Bayesian image segmentation algorithm is proposed by combining a l...
read it

Design of Kernels in Convolutional Neural Networks for Image Classification
Despite the effectiveness of Convolutional Neural Networks (CNNs) for im...
read it

Bayesian image segmentations by Potts prior and loopy belief propagation
This paper presents a Bayesian image segmentation model based on Potts p...
read it

Evolutionary Quantum Logic Synthesis of Boolean Reversible Logic Circuits Embedded in Ternary Quantum Space using Heuristics
It has been experimentally proven that realizing universal quantum gates...
read it

Traffic data reconstruction based on Markov random field modeling
We consider the traffic data reconstruction problem. Suppose we have the...
read it

Symbolic Segmentation Using Algorithm Selection
In this paper we present an alternative approach to symbolic segmentatio...
read it

VC dimension of ellipsoids
We will establish that the VC dimension of the class of ddimensional el...
read it

Sourceside Prediction for Neural Headline Generation
The encoderdecoder model is widely used in natural language generation ...
read it

A Corpus of Deep Argumentative Structures as an Explanation to Argumentative Relations
In this paper, we compose a new task for deep argumentative structure an...
read it

Revisiting the Design Issues of Local Models for Japanese PredicateArgument Structure Analysis
The research trend in Japanese predicateargument structure (PAS) analys...
read it

A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
This study addresses the problem of identifying the meaning of unknown w...
read it

Composing Distributed Representations of Relational Patterns
Learning distributed representations for relation instances is a central...
read it

Other Topics You May Also Agree or Disagree: Modeling InterTopic Preferences using Tweets and Matrix Factorization
We present in this paper our approach for modeling intertopic preferenc...
read it

Learning Semantically and Additively Compositional Distributional Representations
This paper connects a vectorbased composition model to a formal semanti...
read it

An Attentive Neural Architecture for Finegrained Entity Type Classification
In this work we propose a novel attentionbased neural network model for...
read it

The Mechanism of Additive Composition
Additive composition (Foltz et al, 1998; Landauer and Dumais, 1997; Mitc...
read it

Rectilinear Link Diameter and Radius in a Rectilinear Polygonal Domain
We study the computation of the diameter and radius under the rectilinea...
read it

Gapplanar Graphs
We introduce the family of kgapplanar graphs for k ≥ 0, i.e., graphs t...
read it

Physical Layer SecurityAware Routing and Performance Tradeoffs in Ad Hoc Networks
The application of physical layer security in ad hoc networks has attrac...
read it

Improved TimeSpace Tradeoffs for Computing Voronoi Diagrams
Let P be a planar set of n sites in general position. For k∈{1,...,n1},...
read it

Packing Plane Spanning Trees and Paths in Complete Geometric Graphs
We consider the following question: How many edgedisjoint plane spannin...
read it

Deep Structured EnergyBased Image Inpainting
In this paper, we propose a structured image inpainting method employing...
read it

Reconfiguration of Colorable Sets in Classes of Perfect Graphs
A set of vertices in a graph is ccolorable if the subgraph induced by t...
read it

Binary linear complementary dual codes
Linear complementary dual codes (or codes with complementary duals) are ...
read it

Reconfiguring spanning and induced subgraphs
Subgraph reconfiguration is a family of problems focusing on the reachab...
read it

Persistence Weighted Gaussian Kernel for Probability Distributions on the Space of Persistence Diagrams
A persistence diagram characterizes robust geometric and topological fea...
read it

On the classification of linear complementary dual codes
We give a complete classification of binary linear complementary dual co...
read it

Improved Fusion of Visual and Language Representations by Dense Symmetric CoAttention for Visual Question Answering
A key solution to visual question answering (VQA) exists in how to fuse ...
read it
Tohoku University
Tohoku University (東北大学, Tōhoku daigaku), abbreviated to Tohokudai, located in Sendai, Miyagi in the Tōhoku Region, Japan, is a Japanese national university.