114 citations · 357 across the 37 of their papers we have counts for
35 papers · 1 filter
Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering
Erika Mori, Yue Qiu, Hirokatsu Kataoka +1
Social intelligence, the ability to interpret emotions, intentions, and behaviors, is essential for effective communication and adaptive responses. As robots and AI systems become…
MoireDB: Formula-generated Interference-fringe Image Dataset
Yuto Matsuo, Ryo Hayamizu, Hirokatsu Kataoka +1
Image recognition models have struggled to treat recognition robustness to real-world degradations. In this context, data augmentation methods like PixMix improve robustness but re…
Traffic Incident Database with Multiple Labels Including Various Perspective Environmental Information
Shota Nishiyama, Takuma Saito, Ryo Nakamura +3
A large dataset of annotated traffic accidents is necessary to improve the accuracy of traffic accident recognition using deep learning models. Conventional traffic accident datase…
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
Risa Shinoda, Ryo Hayamizu, Kodai Nakashima +3
Pre-training is a strong strategy for enhancing visual models to efficiently train them with a limited number of labeled images. In semantic segmentation, creating annotation masks…
Pre-training Vision Transformers with Very Limited Synthesized Images
Ryo Nakamura, Hirokatsu Kataoka, Sora Takashima +3
Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has sho…
Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
Sora Takashima, Ryo Hayamizu, Nakamasa Inoue +2
Formula-driven supervised learning (FDSL) has been shown to be an effective method for pre-training vision transformers, where ExFractalDB-21k was shown to exceed the pre-training…
Neural Density-Distance Fields
Itsuki Ueda, Yoshihiro Fukuhara, Hirokatsu Kataoka +3
The success of neural fields for 3D vision tasks is now indisputable. Following this trend, several methods aiming for visual localization (e.g., SLAM) have been proposed to estima…
Pre-training Vision Transformers with Formula-driven Supervised Learning
Hirokatsu Kataoka, Sora Takashima, Ryo Hayamizu +6
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k and can approach that of the JFT-300M d…
Can Vision Transformers Learn without Natural Images?
Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto +2
Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale datas…
Describing and Localizing Multiple Changes with Transformers
Yue Qiu, Shintaro Yamamoto, Kodai Nakashima +4
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. Existing change ca…
Pre-training without Natural Images
Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto +5
Is it possible to use convolutional neural networks pre-trained without any natural images to assist natural image understanding? The paper proposes a novel concept, Formula-driven…
Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data
Nakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka
We propose a novel network initialization method using Perlin noise for training image classification networks with a limited amount of data. Our main idea is to initialize the net…
Alleviating Over-segmentation Errors by Detecting Action Boundaries
Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki +1
We propose an effective framework for the temporal action segmentation task, namely an Action Segment Refinement Framework (ASRF). Our model architecture consists of a long-term fe…
Retrieving and Highlighting Action with Spatiotemporal Reference
Seito Kasai, Yuchi Ishikawa, Masaki Hayashi +3
In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods. Our work tak…
Weakly Supervised Dataset Collection for Robust Person Detection
Munetaka Minoguchi, Ken Okayama, Yutaka Satoh +1
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. Through labor-i…
Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara +1
How can we collect and use a video dataset to further improve spatiotemporal 3D Convolutional Neural Networks (3D CNNs)? In order to positively answer this open question in video r…
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka +1
Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial ne…
What Do Adversarially Robust Models Look At?
Takahiro Itazuri, Yoshihiro Fukuhara, Hirokatsu Kataoka +1
In this paper, we address the open question: "What do adversarially robust models look at?" Recently, it has been reported in many works that there exists the trade-off between sta…
Automatic Paper Summary Generation from Visual and Textual Information
Shintaro Yamamoto, Yoshihiro Fukuhara, Ryota Suzuki +2
Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the expone…
Understanding Fake Faces
Ryota Natsume, Kazuki Inoue, Yoshihiro Fukuhara +3
Face recognition research is one of the most active topics in computer vision (CV), and deep neural networks (DNN) are now filling the gap between human-level and computer-driven p…
Neural Joking Machine : Humorous image captioning
Kota Yoshida, Munetaka Minoguchi, Kenichiro Wani +2
What is an effective expression that draws laughter from human beings? In the present paper, in order to consider this question from an academic standpoint, we generate an image ca…
Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Tomoyuki Suzuki, Hirokatsu Kataoka, Yoshimitsu Aoki +1
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 inciden…
Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
Hirokatsu Kataoka, Teppei Suzuki, Shoko Oikawa +2
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 (…
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
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…