Hirokatsu Kataoka

research

∙ 06/18/2022

Replacing Labeled Real-image Datasets with Auto-generated Contours

In the present work, we show that the performance of formula-driven supe...

Hirokatsu Kataoka, et al. ∙

research

∙ 03/25/2021

Describing and Localizing Multiple Changes with Transformers

Change captioning tasks aim to detect changes in image pairs observed be...

Yue Qiu, et al. ∙

research

∙ 03/24/2021

Can Vision Transformers Learn without Natural Images?

Can we complete pre-training of Vision Transformers (ViT) without natura...

Kodai Nakashima, et al. ∙

research

∙ 01/21/2021

Pre-training without Natural Images

Is it possible to use convolutional neural networks pre-trained without ...

Hirokatsu Kataoka, et al. ∙

research

∙ 01/19/2021

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data

We propose a novel network initialization method using Perlin noise for ...

Nakamasa Inoue, et al. ∙

research

∙ 07/14/2020

Alleviating Over-segmentation Errors by Detecting Action Boundaries

We propose an effective framework for the temporal action segmentation t...

Yuchi Ishikawa, et al. ∙

research

∙ 05/19/2020

Retrieving and Highlighting Action with Spatiotemporal Reference

In this paper, we present a framework that jointly retrieves and spatiot...

Seito Kasai, et al. ∙

research

∙ 04/10/2020

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

How can we collect and use a video dataset to further improve spatiotemp...

Hirokatsu Kataoka, et al. ∙

research

∙ 03/27/2020

Weakly Supervised Dataset Collection for Robust Person Detection

To construct an algorithm that can provide robust person detection, we p...

Munetaka Minoguchi, et al. ∙

research

∙ 02/29/2020

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

Unpaired image-to-image (I2I) translation has received considerable atte...

Takehiko Ohkawa, et al. ∙

research

∙ 05/19/2019

What Do Adversarially Robust Models Look At?

In this paper, we address the open question: "What do adversarially robu...

Takahiro Itazuri, et al. ∙

research

∙ 11/16/2018

Automatic Paper Summary Generation from Visual and Textual Information

Due to the recent boom in artificial intelligence (AI) research, includi...

Shintaro Yamamoto, et al. ∙

research

∙ 09/22/2018

Understanding Fake Faces

Face recognition research is one of the most active topics in computer v...

Ryota Natsume, et al. ∙

research

∙ 05/30/2018

Neural Joking Machine : Humorous image captioning

What is an effective expression that draws laughter from human beings? I...

Kota Yoshida, et al. ∙

research

∙ 04/08/2018

Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB

In this paper, we propose a novel approach for traffic accident anticipa...

Tomoyuki Suzuki, et al. ∙

research

∙ 04/07/2018

Drive Video Analysis for the Detection of Traffic Near-Miss Incidents

Because of their recent introduction, self-driving cars and advanced dri...

Hirokatsu Kataoka, et al. ∙

research

∙ 11/27/2017

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

The purpose of this study is to determine whether current video datasets...

Kensho Hara, et al. ∙

research

∙ 08/25/2017

Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition

Convolutional neural networks with spatio-temporal 3D kernels (3D CNNs) ...

Kensho Hara, et al. ∙

research

∙ 07/20/2017

cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey

The paper gives futuristic challenges disscussed in the cvpaper.challeng...

Hirokatsu Kataoka, et al. ∙

research

∙ 05/10/2017

Collaborative Descriptors: Convolutional Maps for Preprocessing

The paper presents a novel concept for collaborative descriptors between...

Hirokatsu Kataoka, et al. ∙

research

∙ 04/07/2017

Could you guess an interesting movie from the posters?: An evaluation of vision-based features on movie poster database

In this paper, we aim to estimate the Winner of world-wide film festival...

Yuta Matsuzaki, et al. ∙

research

∙ 03/23/2017

Changing Fashion Cultures

The paper presents a novel concept that analyzes and visualizes worldwid...

Kaori Abe, et al. ∙

research

∙ 08/30/2016

Motion Representation with Acceleration Images

Information of time differentiation is extremely important cue for a mot...

Hirokatsu Kataoka, et al. ∙

research

∙ 08/29/2016

Human Action Recognition without Human

The objective of this paper is to evaluate "human action recognition wit...

Yun He, et al. ∙

research

∙ 05/26/2016

cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey

The "cvpaper.challenge" is a group composed of members from AIST, Tokyo ...

Hirokatsu Kataoka, et al. ∙

research

∙ 04/26/2016

Semantic Change Detection with Hypermaps

Change detection is the study of detecting changes between two different...

Teppei Suzuki, et al. ∙

research

∙ 09/25/2015

Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection

In this paper, we evaluate convolutional neural network (CNN) features u...

Hirokatsu Kataoka, et al. ∙

Hirokatsu Kataoka

Featured Co-authors

Xinyu Zhang

Yutaka Satoh

Nakamasa Inoue

Asako Kanezaki

Rio Yokota

Yun He

Akio Nakamura

Teppei Suzuki

Shigeo Morishima

Kaori Abe

Takehiko Ohkawa

Replacing Labeled Real-image Datasets with Auto-generated Contours

Describing and Localizing Multiple Changes with Transformers

Can Vision Transformers Learn without Natural Images?

Pre-training without Natural Images

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data

Alleviating Over-segmentation Errors by Detecting Action Boundaries

Retrieving and Highlighting Action with Spatiotemporal Reference

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

Weakly Supervised Dataset Collection for Robust Person Detection

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

What Do Adversarially Robust Models Look At?

Automatic Paper Summary Generation from Visual and Textual Information

Understanding Fake Faces

Neural Joking Machine : Humorous image captioning

Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB

Drive Video Analysis for the Detection of Traffic Near-Miss Incidents

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition

cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey

Collaborative Descriptors: Convolutional Maps for Preprocessing

Could you guess an interesting movie from the posters?: An evaluation of vision-based features on movie poster database

Changing Fashion Cultures

Motion Representation with Acceleration Images

Human Action Recognition without Human

cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey

Semantic Change Detection with Hypermaps

Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection