Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18 16:25 |
Hokkaido |
Hokkaido Univ. (Hokkaido) |
Trial for Recognizing Hazards in Traffic Scene Using a Vision-Language Model Kazuma Nishimura, Kazuto Nakagawa, Temma Okamoto, Osamu Sugiyama, Masahiro Tada (Kindai Univ.) |
(To be available after the conference date) [more] |
|
ME, IST, IEICE-BioX, IEICE-SIP, IEICE-MI, IEICE-IE [detail] |
2024-06-06 14:10 |
Niigata |
Nigata University (Ekinan-Campus "TOKIMATE") (Niigata) |
A trial for recognizing traffic scene using a Vision-Language Model Kazuto Nakagawa, Kazuma Nishimura, Osamu Sugiyama, Masahiro Tada (Kindai Univ.) |
For the societal implementation of autonomous driving systems, it is essential that these systems understand the behavio... [more] |
IST2024-25 ME2024-50 pp.15-18 |
AIT, IIEEJ, AS, CG-ARTS |
2024-03-05 12:00 |
Tokyo |
Tokyo University of Technology (Tokyo) |
Semiautomatic Cutout of Objects from 3D Scene Reconstructed with Gaussian Splatting Yuya Matsumoto, Issei Fujishiro (Keio Univ.) |
With advances in extended reality technologies, there is an increasing demand for three-dimensional (3D) scene reconstru... [more] |
AIT2024-36 pp.19-22 |
AIT, IIEEJ, AS, CG-ARTS |
2024-03-05 14:30 |
Tokyo |
Tokyo University of Technology (Tokyo) |
Proposal of a Method for Extracting Scoring Display Scenes in a Broadcast Ball Game Video Naoya Inagaki, Takeshi Masuda, Hiroaki Sawano (AIT) |
In the analysis of video footage of ball sports, it is necessary for the analyst to watch all of the game footage and re... [more] |
AIT2024-118 pp.297-300 |
AIT, IIEEJ, AS, CG-ARTS |
2023-03-06 13:50 |
Tokyo |
Tokyo Polytechnic Univ. (Nakano) (Tokyo, Online) (Primary: On-site, Secondary: Online) |
Structural Analysis of Cut editing in Japanese Robot Anime Battle Scenes Based on Visual Information Hiroki Jyo, Yoshihisa Kanematsu, Koji Mikami (TUT) |
In Japanese robot animation battle scenes, the atmosphere of robot battles, the situation, and the tempo of battles vary... [more] |
AIT2023-61 pp.97-100 |
AIT, IIEEJ, AS, CG-ARTS |
2023-03-06 12:40 |
Tokyo |
Tokyo Polytechnic Univ. (Nakano) (Tokyo, Online) (Primary: On-site, Secondary: Online) |
A Research on Minimum Quality Level of Edits Required for High-Rating Posted Videos Toranosuke Kubokawa, Suguru Matsuyoshi (TUT) |
The object of this work is to clarify minimum quality level of edits required for high-rating posted videos. We targeted... [more] |
AIT2023-124 pp.315-318 |
AIT, IIEEJ, AS, CG-ARTS |
2022-03-08 13:04 |
Online |
Online (Online) |
Study on Scene Extraction Method from Table Tennis Video based on Body Movements Ryosuke Ishikawa, Kohjiro Hashimoto, Tadashi Miyosawa (Suwa Univ.) |
In this research, we propose a scene extraction method focusing on table tennis competition. Table tennis players set up... [more] |
AIT2022-76 pp.147-148 |
IIEEJ, AIT |
2021-10-27 15:20 |
Osaka |
(Osaka, Online) (Primary: On-site, Secondary: Online) |
Scene Segmentation for Instruction Videos by Learning Similarity between Videos and Sentence Jumpei Hayashi, Yota Yamamoto, Yukinobu Taniguchi (TUS) |
In industry such as manufacturing or restaurant, many companies use videos of experts’ work to efficiently transfer thei... [more] |
AIT2021-144 pp.13-16 |
ME |
2021-07-16 14:50 |
Online |
Online (Online) |
Implementation of a scene description player that displays a combination of volumetric video and omni-directional video Yuma Wakahara, Shuichi Aoki, Yoshiro Takiguchi (NHK) |
We have developed a scene description that combines 360° video and volumetric video to form a 3D space by describing the... [more] |
ME2021-64 pp.13-16 |
AIT, IIEEJ, AS, CG-ARTS |
2021-03-08 13:30 |
Online |
Online (Online) |
Multiple scene search of movies from ambiguous memory Yuya Iino, Ikuko Tsubaki (Tokyo University of Technology) |
It takes time to reach the content of the scene that the user wants to watch from the video, and the content is not alwa... [more] |
AIT2021-100 pp.237-240 |
IEICE-IE, IEICE-ITS, MMS, ME, AIT [detail] |
2021-02-18 17:05 |
Online |
Online (Online) |
A Note on Prediction of Important Scenes in Baseball Videos via Multimodal Variational Autoencoder Using Tweets and Videos Kaito Hirasawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
This paper presents a prediction method of important scenes in baseball videos based on multimodal variational autoencod... [more] |
MMS2021-14 ME2021-14 AIT2021-14 pp.71-75 |
AIT, IIEEJ, AS, CG-ARTS |
2019-03-12 11:15 |
Tokyo |
Waseda Univ. (Tokyo) |
Application of image recognition technology for movie scene search Yuya Iino, Meeko Kuwahara, Kazuya Ueki (Meisei Univ.) |
Various methods can be considered for scene search, but in this paper we propose application of image recognition techno... [more] |
AIT2019-52 pp.9-12 |
AIT, IIEEJ, AS, CG-ARTS |
2019-03-12 13:00 |
Tokyo |
Waseda Univ. (Tokyo) |
Diminished Reality in Textureless Scenes Yuka Namboku, Hiroki Takahashi (UEC) |
Diminished Reality (DR), which removes real objects visually, is expected in various scenes. It is, however, difficult t... [more] |
AIT2019-70 pp.81-84 |
SIP, ME |
2017-11-26 15:30 |
Kagoshima |
NIFS (Kagoshima) |
A Study on Detection of Similar Scenes based on Player Positions in Soccer Videos Sho Takahashi, Miki Haseyama (Hokkaido Univ.) |
This paper proposes a method for detecting similar scenes in soccer videos. In soccer games, the pass and players' forma... [more] |
ME2017-114 pp.5-8 |
IST |
2017-06-23 14:40 |
Tokyo |
(Tokyo) |
[Poster Presentation]
Acquisition of Appropriate Images for Scene Understanding Based on Brightness and Motion Using Interleave Exposure Control Tomohiro Aratani, Takayuki Hamamoto (TUS) |
We propose the method of acquisition of appropriate images for scene understanding. We acquire images with various expos... [more] |
IST2017-37 pp.13-16 |
AIT, IIEEJ, AS, CG-ARTS |
2017-03-14 13:00 |
Tokyo |
Ochanomizu Univ. (Tokyo) |
Design support of scene in character joint struggle scene Shouhei Miyagi (TUT), Yoshihisa Kanematsu (TMU), Koji Mikami, Kunio Kondo (TUT) |
In this research, we develop a struggle scene design support system that accumulates the technology and know-how of exis... [more] |
AIT2017-113 pp.241-244 |
AIT, IIEEJ, AS, CG-ARTS |
2017-03-14 14:45 |
Tokyo |
Ochanomizu Univ. (Tokyo) |
Computer-Assisted Colorization to Freehand Line Drawing by Tablet for Sketch Scene. Shohei Usami, Saori Kurata, Hiroshi Mori, Fubito Toyama, Kenji Shoji (Utsunomiya Univ) |
We propose a method for computer-assisted colorization to freehand line drawings with reference to a photograph taken b... [more] |
AIT2017-139 pp.323-326 |
ME, SIP [detail] |
2016-12-05 14:00 |
Tokyo |
Waseda Univ. (Tokyo) |
A Study on Detection of Similar Scenes based on Pass Regions in Soccer Videos Sho Takahashi, Miki Haseyama (Hokkaido Univ.) |
This paper proposes a pass region-based method for detecting similar scenes in soccer videos. In the soccer games, since... [more] |
ME2016-127 pp.9-12 |
ME, IEICE-IE, IEICE-EMM, IEICE-LOIS, IEE-CMN [detail] |
2016-09-15 13:00 |
Aichi |
Aichi Prefectural University (Aichi) |
An Effectiveness of tags in finding broadcasting contents on Time Associate Zapping System Shinya Takeuchi, Yutaka Kaneko, Kazushige Hiramatsu, Masahide Naemura (NHK) |
We proposed a content delivery service by which users can select viewing program contents by the on-air time in addition... [more] |
ME2016-116 pp.1-5 |
HI, IEICE-IE, AIT, IEICE-ITS, ME, MMS, CE [detail] |
2016-02-22 11:30 |
Hokkaido |
Hokudai (Hokkaido) |
Text Line Formation Method using Stroke-width of Character Candidates in Scene Images Rei Endo, Yoshihiko Kawai, Hideki Sumiyoshi (NHK) |
Broadcasters have huge amount of video archive. An image retrieval system based on name of person/place which reflected ... [more] |
MMS2016-1 CE2016-1 HI2016-1 ME2016-34 AIT2016-1 pp.47-50 |