Search Results for author: Yutaka Satoh

Found 17 papers, 7 papers with code

Describing and Localizing Multiple Changes with Transformers

2 code implementations ICCV 2021 Yue Qiu, Shintaro Yamamoto, Kodai Nakashima, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka, Yutaka Satoh

Change captioning tasks aim to detect changes in image pairs observed before and after a scene change and generate a natural language description of the changes.

Pre-training without Natural Images

2 code implementations21 Jan 2021 Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh

Is it possible to use convolutional neural networks pre-trained without any natural images to assist natural image understanding?

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

10 code implementations10 Apr 2020 Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh

Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy.

General Classification Open-Ended Question Answering +2

Weakly Supervised Dataset Collection for Robust Person Detection

1 code implementation27 Mar 2020 Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka

To construct an algorithm that can provide robust person detection, we present a dataset with over 8 million images that was produced in a weakly supervised manner.

Human Detection

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

no code implementations CVPR 2018 Tomoyuki Suzuki, Hirokatsu Kataoka, Yoshimitsu Aoki, Yutaka Satoh

In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation.

Accident Anticipation

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

no code implementations7 Apr 2018 Hirokatsu Kataoka, Teppei Suzuki, Shoko Oikawa, Yasuhiro Matsui, Yutaka Satoh

Because of their recent introduction, self-driving cars and advanced driver assistance system (ADAS) equipped vehicles have had little opportunity to learn, the dangerous traffic (including near-miss incident) scenarios that provide normal drivers with strong motivation to drive safely.

Self-Driving Cars

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

26 code implementations CVPR 2018 Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh

The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels.

Action Recognition

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

1 code implementation25 Aug 2017 Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh

The 3D ResNets trained on the Kinetics did not suffer from overfitting despite the large number of parameters of the model, and achieved better performance than relatively shallow networks, such as C3D.

Action Recognition Hand-Gesture Recognition +1

Illuminant-Camera Communication to Observe Moving Objects Under Strong External Light by Spread Spectrum Modulation

no code implementations CVPR 2017 Ryusuke Sagawa, Yutaka Satoh

In this paper, we propose a method of energy-efficient active illumination in an environment with severe external lights.

Collaborative Descriptors: Convolutional Maps for Preprocessing

no code implementations10 May 2017 Hirokatsu Kataoka, Kaori Abe, Akio Nakamura, Yutaka Satoh

The paper presents a novel concept for collaborative descriptors between deeply learned and hand-crafted features.

Object Recognition

Motion Representation with Acceleration Images

no code implementations30 Aug 2016 Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh

Information of time differentiation is extremely important cue for a motion representation.

Optical Flow Estimation

Dominant Codewords Selection with Topic Model for Action Recognition

no code implementations1 May 2016 Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic

Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities.

Action Recognition Temporal Action Localization

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

no code implementations25 Sep 2015 Hirokatsu Kataoka, Kenji Iwata, Yutaka Satoh

In this paper, we evaluate convolutional neural network (CNN) features using the AlexNet architecture and very deep convolutional network (VGGNet) architecture.

General Classification Object Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.