Takayuki Okatani

is this you? claim profile

∙ 0 followers
Tohoku University

Professor, Perception information processing/intelligent robotics(Computer Vision) at Tohoku University

Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features

This study is concerned with few-shot segmentation, i.e., segmenting the...
09/14/2021 ∙ by Zhijie Wang, et al. ∙ 0 ∙ share

read it
Cross-Region Domain Adaptation for Class-level Alignment

Semantic segmentation requires a lot of training data, which necessitate...
09/14/2021 ∙ by Zhijie Wang, et al. ∙ 0 ∙ share

read it
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes

This paper considers matching images of low-light scenes, aiming to wide...
09/08/2021 ∙ by Wenzheng Song, et al. ∙ 11 ∙ share

read it
Progressive and Selective Fusion Network for High Dynamic Range Imaging

This paper considers the problem of generating an HDR image of a scene f...
08/19/2021 ∙ by Qian Ye, et al. ∙ 0 ∙ share

read it
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks

There is a growing interest in the community in making an embodied AI ag...
06/01/2021 ∙ by Van-Quang Nguyen, et al. ∙ 0 ∙ share

read it
Pushing the Envelope of Thin Crack Detection

In this study, we consider the problem of detecting cracks from the imag...
01/09/2021 ∙ by Liang Xu, et al. ∙ 8 ∙ share

read it
Bridging In- and Out-of-distribution Samples for Their Better Discriminability

This paper proposes a method for OOD detection. Questioning the premise ...
01/07/2021 ∙ by Engkarat Techapanurak, et al. ∙ 0 ∙ share

read it
Practical Evaluation of Out-of-Distribution Detection Methods for Image Classification

We reconsider the evaluation of OOD detection methods for image recognit...
01/07/2021 ∙ by Engkarat Techapanurak, et al. ∙ 0 ∙ share

read it
How Can CNNs Use Image Position for Segmentation?

Convolution is an equivariant operation, and image position does not aff...
05/07/2020 ∙ by Rito Murase, et al. ∙ 0 ∙ share

read it
Efficient Attention Mechanism for Handling All the Interactions between Many Inputs with Application to Visual Dialog

It has been a primary concern in recent studies of vision and language t...
11/26/2019 ∙ by Van-Quang Nguyen, et al. ∙ 28 ∙ share

read it
Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method

In this paper, we consider adversarial attacks against a system of monoc...
11/20/2019 ∙ by Junjie Hu, et al. ∙ 0 ∙ share

read it
Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors

The employment of convolutional neural networks has led to significant p...
10/21/2019 ∙ by Yusuke Hosoya, et al. ∙ 13 ∙ share

read it
Joint Learning of Multiple Image Restoration Tasks

Convolutional neural networks have recently been successfully applied to...
07/10/2019 ∙ by Xing Liu, et al. ∙ 4 ∙ share

read it
Evaluating Artificial Systems for Pairwise Ranking Tasks Sensitive to Individual Differences

Owing to the advancement of deep learning, artificial systems are now ri...
05/30/2019 ∙ by Xing Liu, et al. ∙ 0 ∙ share

read it
Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity

The ability of detecting out-of-distribution (OOD) samples is important ...
05/25/2019 ∙ by Engkarat Techapanurak, et al. ∙ 0 ∙ share

read it
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment

We address a problem of estimating pose of a person's head from its RGB ...
05/14/2019 ∙ by Mingzhen Shao, et al. ∙ 0 ∙ share

read it
Visualization of Convolutional Neural Networks for Monocular Depth Estimation

Recently, convolutional neural networks (CNNs) have shown great success ...
04/06/2019 ∙ by Junjie Hu, et al. ∙ 17 ∙ share

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...
03/21/2019 ∙ by Xing Liu, et al. ∙ 2 ∙ share

read it
Toward Explainable Fashion Recommendation

Many studies have been conducted so far to build systems for recommendin...
01/15/2019 ∙ by Pongsate Tangseng, et al. ∙ 0 ∙ share

read it
Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions

Many studies have been conducted so far on image restoration, the proble...
12/03/2018 ∙ by Masanori Suganuma, et al. ∙ 0 ∙ share

read it
Multi-task Learning of Hierarchical Vision-Language Representation

It is still challenging to build an AI system that can perform tasks tha...
12/03/2018 ∙ by Duy-Kien Nguyen, et al. ∙ 0 ∙ share

read it
Recommending Outfits from Personal Closet

We consider grading a fashion outfit for recommendation, where we assume...
04/26/2018 ∙ by Pongsate Tangseng, et al. ∙ 0 ∙ share

read it
Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering

A key solution to visual question answering (VQA) exists in how to fuse ...
04/03/2018 ∙ by Duy-Kien Nguyen, et al. ∙ 0 ∙ share

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...
03/23/2018 ∙ by Junjie Hu, et al. ∙ 4 ∙ share

read it
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search

Researchers have applied deep neural networks to image restoration tasks...
03/01/2018 ∙ by Masanori Suganuma, et al. ∙ 0 ∙ share

read it
Deep Structured Energy-Based Image Inpainting

In this paper, we propose a structured image inpainting method employing...
01/24/2018 ∙ by Fazil Altinel, et al. ∙ 0 ∙ share

read it
A vision based system for underwater docking

Autonomous underwater vehicles (AUVs) have been deployed for underwater ...
12/12/2017 ∙ by Shuang Liu, et al. ∙ 0 ∙ share

read it
HyperNetworks with statistical filtering for defending adversarial examples

Deep learning algorithms have been known to be vulnerable to adversarial...
11/06/2017 ∙ by Zhun Sun, et al. ∙ 0 ∙ share

read it
End-to-end learning potentials for structured attribute prediction

We present a structured inference approach in deep neural networks for m...
08/06/2017 ∙ by Kota Yamaguchi, et al. ∙ 0 ∙ share

read it
Linear Discriminant Generative Adversarial Networks

We develop a novel method for training of GANs for unsupervised and clas...
07/25/2017 ∙ by Zhun Sun, et al. ∙ 0 ∙ share

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...
07/25/2017 ∙ by Zhun Sun, et al. ∙ 0 ∙ share

read it
Information Potential Auto-Encoders

In this paper, we suggest a framework to make use of mutual information ...
06/14/2017 ∙ by Yan Zhang, et al. ∙ 0 ∙ share

read it
Truncating Wide Networks using Binary Tree Architectures

Recent study shows that a wide deep network can obtain accuracy comparab...
04/03/2017 ∙ by Yan Zhang, et al. ∙ 0 ∙ share

read it
Optimization on Product Submanifolds of Convolution Kernels

Recent advances in optimization methods used for training convolutional ...
01/22/2017 ∙ by M. Ozay, et al. ∙ 0 ∙ share

read it
Self-calibration-based Approach to Critical Motion Sequences of Rolling-shutter Structure from Motion

In this paper we consider critical motion sequences (CMSs) of rolling-sh...
11/16/2016 ∙ by Eisuke Ito, et al. ∙ 0 ∙ share

read it
Optimization on Submanifolds of Convolution Kernels in CNNs

Kernel normalization methods have been employed to improve robustness of...
10/22/2016 ∙ by M. Ozay, et al. ∙ 0 ∙ share

read it
Automatic Attribute Discovery with Neural Activations

How can a machine learn to recognize visual attributes emerging out of o...
07/25/2016 ∙ by Sirion Vittayakorn, et al. ∙ 0 ∙ share

read it
Design of Kernels in Convolutional Neural Networks for Image Classification

Despite the effectiveness of Convolutional Neural Networks (CNNs) for im...
11/30/2015 ∙ by Zhun Sun, et al. ∙ 0 ∙ share

read it

Takayuki Okatani

Featured Co-authors