Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
ICM, IPSJ-IOT, IPSJ-CSEC |
2024-05-30 13:50 |
Tottori |
(Primary: On-site, Secondary: Online) |
Generative AI for Enhanced System Design and Evaluation Jayesh Guntupalli, Kentaro Watanabe (Hitachi Ltd.) |
(To be available after the conference date) [more] |
|
PRMU, IPSJ-CVIM |
2024-05-15 13:45 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Fine-tuning Large Language Models for Automatic Font Skeleton Generation: A First Attempt Yuxuan Liu (Tokyo Tech), Yasuhisa Fujii (Google Research), Xinru Zhu, Kayoko Nohara (Tokyo Tech) |
[more] |
|
PRMU, IPSJ-CVIM |
2024-05-16 15:10 |
Tokyo |
(Primary: On-site, Secondary: Online) |
A Proposal for Generating Incorrect Pairs for the CLIP Learning based on Image Clustering Rina Tagami, Hiroki Kobayashi, Shuichi Akizuki, Manabu Hashimoto (Chukyo Univ.) |
(To be available after the conference date) [more] |
|
PRMU, IPSJ-CVIM |
2024-05-16 15:25 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Integrating Global-Local Feature Embeddings for Open-Vocabulary Temporal Action Detection NguyenTrung Thanh (Nagoya Univ.), Yasutomo Kawanishi (RIKEN), Takahiro Komamizu, Ichiro Ide (Nagoya Univ.) |
(To be available after the conference date) [more] |
|
HIP, HCS, HI-SIGCOASTER [detail] |
2024-05-14 09:15 |
Okinawa |
Okinawa Industry Support Center |
Exploring Individuality in Sign Language using Japanese Sign Language Video Data Zixuan Dai, Shinji Sako (NITech) |
[more] |
|
ICM |
2024-03-22 09:10 |
Okinawa |
Okinawa Prefectural Museum and Art Museum (Primary: On-site, Secondary: Online) |
Proposal of an implication relationship estimation method for information security related regulatory documents Kouki Nakanishi, Tkakani ikuko, Sakamoto Masanobu, Ohishi Haruo (NTT) ICM2023-51 |
In recent years, internal controls regarding information security have become increasingly important from the perspectiv... [more] |
ICM2023-51 pp.35-40 |
WIT, IPSJ-AAC |
2024-03-18 10:50 |
Ibaraki |
Tsukuba University of Technology (Primary: On-site, Secondary: Online) |
Study on a Plain Japanese Translation Application using OCR Azusa Hosoda, Teppei Miura (NITTC) WIT2023-41 |
Japanese language is one of the most complex languages in the world. Although some plain language translation systems ex... [more] |
WIT2023-41 pp.13-18 |
WIT, IPSJ-AAC |
2024-03-19 12:10 |
Ibaraki |
Tsukuba University of Technology (Primary: On-site, Secondary: Online) |
A Study on the Relationship Between the Linguistic Features of Sign Language and the Accuracy of Imitation
-- Sign Language Imitation Experiment using Illustrations, Video, and HMD Learning Materials -- Tomoya Sato, Takeaki Shionome (Teikyo Univ.) WIT2023-54 |
In sign language learning using a head-mounted display (HMD), the hand-tracking function enables users to learn from a f... [more] |
WIT2023-54 pp.63-68 |
KBSE |
2024-03-14 11:50 |
Okinawa |
Okinawa Prefectual General Welfare Center (Primary: On-site, Secondary: Online) |
Structuring Methods for System Requirements Using Large Language Models Ryo Nakashima (UTokyo), Masaki Inokuchi, Masaharu Morimoto, Takayuki Kuroda (NEC) KBSE2023-70 |
Recently, there has been increasing interest in automatic design to reduce the costs associated with the development and... [more] |
KBSE2023-70 pp.31-36 |
KBSE |
2024-03-14 15:15 |
Okinawa |
Okinawa Prefectual General Welfare Center (Primary: On-site, Secondary: Online) |
A Method to Create Scenario by Large Language Model for Input Amount Simulation Yusuke Koyama, Shinpei Ogata, Kozo Okano (Shinshu Univ.) KBSE2023-75 |
One of the means to reasonably reduce the burden of user input to the UI (User Interface) is to introduce usability-enha... [more] |
KBSE2023-75 pp.61-66 |
KBSE |
2024-03-15 11:25 |
Okinawa |
Okinawa Prefectual General Welfare Center (Primary: On-site, Secondary: Online) |
Research on Automatic Dialogue Correction Considering Character's Distinctive Way of Speaking in Novels Mei Matsuura, Yutaka Matsuno (Nihon Univ.) KBSE2023-85 |
In scenario works such as novels, manga, and games, it is important to maintain consistent expression in order to mainta... [more] |
KBSE2023-85 pp.108-113 |
NLP, MSS |
2024-03-13 15:00 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Formal Concept Analysis of Traffic Accidents Factors using Traffic Accident Summaries Haruto Murakami, Kazutoshi Sakakibara, Masaki Nakamura, Tatsuro Motoyoshi, Keisuke Hoshikawa (Toyama Prefectural Univ.) MSS2023-79 NLP2023-131 |
The purpose of this study is to support police activities targeting elderly pedestrians and other vulnerable road users,... [more] |
MSS2023-79 NLP2023-131 pp.42-47 |
NLP, MSS |
2024-03-13 17:20 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Application of Data Augmentation in Japanese Foundation Models Kazuki Era, Hidehiro Nakano (Tokyo City Univ.) MSS2023-84 NLP2023-136 |
One of the recent topics is data augmentation. Data augmentation is a method of augmenting training data to improve the ... [more] |
MSS2023-84 NLP2023-136 pp.66-69 |
IE, MVE, CQ, IMQ (Joint) [detail] |
2024-03-14 16:20 |
Okinawa |
Okinawa Sangyo Shien Center (Primary: On-site, Secondary: Online) |
Impression of Character's Responding Behavior Corresponding to User's Speech Proactiveness Naoki Matsumura, Tomoko Yonezawa (Kansai Univ.) IMQ2023-51 IE2023-106 MVE2023-80 |
This study aimed to improve speech proactivity in foreign-language face-to-face dialogue. We have examined a system to e... [more] |
IMQ2023-51 IE2023-106 MVE2023-80 pp.208-213 |
SS |
2024-03-08 15:00 |
Okinawa |
(Primary: On-site, Secondary: Online) |
SS2023-72 |
Large language models (LLMs), which have made remarkable progress in recent years, are also being used in the software d... [more] |
SS2023-72 pp.139-143 |
SS |
2024-03-08 15:25 |
Okinawa |
(Primary: On-site, Secondary: Online) |
SS2023-73 |
(To be available after the conference date) [more] |
SS2023-73 pp.144-149 |
SS |
2024-03-09 11:25 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Developing Conversational Agents Using GPT-4 for Application in Information Security Education Atsuya Tsuda, Kazutaka Matsuzaki (Chuo Univ.) SS2023-80 |
In this paper, we report on the development of an interactive agent using a large language model, aimed at being introdu... [more] |
SS2023-80 pp.186-189 |
PRMU, IBISML, IPSJ-CVIM |
2024-03-03 09:36 |
Hiroshima |
Hiroshima Univ. Higashi-Hiroshima campus (Primary: On-site, Secondary: Online) |
Sign language recognition using subspace representations Ryota Sato, Suzana Rita Alves Beleza (Univ. of Tsukuba), Erica Kido Shimomoto (AIST), Matheus Silva de Lima (Univ. of Tsukuba), Nobuko Kato (Tsukuba Univ. of Technology), Kazuhiro Fukui (Univ. of Tsukuba) PRMU2023-54 |
This paper proposes a subspace-based method for sign language recognition in videos.
The proposed method represents a ... [more] |
PRMU2023-54 pp.19-24 |
AI |
2024-03-01 14:40 |
Aichi |
Room0221, Bldg.2-C, Nagoya Institute of Technology |
Request span extraction from dialog with Heterogeneous Graph Attention Networks Naoki Mizumoto, Katsuhide Fujita (TUAT) AI2023-41 |
In this study, we formulate the problem of extracting user requests from the dialogue history as a ``span extraction pro... [more] |
AI2023-41 pp.25-30 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-03-01 09:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Constructing and Evaluating a Batch Voice Input System for Electronic Medical Records Using Large Language Models Ryo Maejima, Norihide Kitaoka (TUT) EA2023-99 SIP2023-146 SP2023-81 |
This study aims to develop an electronic medical record with a voice input interface that lets users input several items... [more] |
EA2023-99 SIP2023-146 SP2023-81 pp.226-231 |