Search Results for author: Koichi Kise

Found 11 papers, 2 papers with code

Quantitative knowledge retrieval from large language models

1 code implementation12 Feb 2024 David Selby, Kai Spriestersbach, Yuichiro Iwashita, Dennis Bappert, Archana Warrier, Sumantrak Mukherjee, Muhammad Nabeel Asim, Koichi Kise, Sebastian Vollmer

Large language models (LLMs) have been extensively studied for their abilities to generate convincing natural language sequences, however their utility for quantitative information retrieval is less well understood.

Imputation Information Retrieval +2

Confidence-Aware Learning Assistant

no code implementations15 Feb 2021 Shoya Ishimaru, Takanori Maruichi, Andreas Dengel, Koichi Kise

(2) With the help of 20 participants, we observed that correct answer rates of questions were increased by 14% and 17% by giving feedback about correct answers without confidence and incorrect answers with confidence, respectively.


Distortion-Adaptive Grape Bunch Counting for Omnidirectional Images

no code implementations28 Aug 2020 Ryota Akai, Yuzuko Utsumi, Yuka Miwa, Masakazu Iwamura, Koichi Kise

Because conventional object counting methods cannot handle the distortion of omnidirectional images, we propose to process them using stereographic projection, which enables conventional methods to obtain a good approximation of the density function.

Data Augmentation Object Counting

Facial Landmark Detection for Manga Images

no code implementations8 Nov 2018 Marco Stricker, Olivier Augereau, Koichi Kise, Motoi Iwata

The topic of facial landmark detection has been widely covered for pictures of human faces, but it is still a challenge for drawings.

Facial Landmark Detection

A survey of comics research in computer science

no code implementations16 Apr 2018 Olivier Augereau, Motoi Iwata, Koichi Kise

We propose in this paper to review the previous research about comics in computer science, to state what have been done and to give some insights about the main outlooks.


ShakeDrop Regularization for Deep Residual Learning

5 code implementations7 Feb 2018 Yoshihiro Yamada, Masakazu Iwamura, Takuya Akiba, Koichi Kise

In this paper, to relieve the overfitting effect of ResNet and its improvements (i. e., Wide ResNet, PyramidNet, and ResNeXt), we propose a new regularization method called ShakeDrop regularization.

ShakeDrop regularization

no code implementations ICLR 2018 Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise

This paper proposes a powerful regularization method named \textit{ShakeDrop regularization}.

Deep Pyramidal Residual Networks with Separated Stochastic Depth

no code implementations5 Dec 2016 Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise

On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy.

Object Recognition

A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents

no code implementations4 May 2016 Sheraz Ahmed, Muhammad Imran Malik, Muhammad Zeshan Afzal, Koichi Kise, Masakazu Iwamura, Andreas Dengel, Marcus Liwicki

The method is generic, language independent and can be used for generation of labeled documents datasets (both scanned and cameracaptured) in any cursive and non-cursive language, e. g., English, Russian, Arabic, Urdu, etc.

Optical Character Recognition (OCR)

Scalable Solution for Approximate Nearest Subspace Search

no code implementations29 Mar 2016 Masakazu Iwamura, Masataka Konishi, Koichi Kise

The existing methods for the problem are, however, useless in a large-scale problem with a large number of subspaces and high dimensionality of the feature space.

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