Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, MVE, VRSJ-SIG-MR, IPSJ-CVIM |
2024-01-26 10:30 |
Kanagawa |
Keio Univ. (Hiyoshi Campus) |
Body Parts Motion Guided Deformable Attention for Action Recognition Yuji Sato, Umihiro Kamoto, Takeo Ueta (Panasonic Connect), Yasunori Ishii (Panasonic Holdings), Takayoshi Yamashita (Chubu Univ.) PRMU2023-44 |
In recent years, video transformers for action recognition have been
proposed and achieve high performance. Most of the... [more] |
PRMU2023-44 pp.26-31 |
NC, MBE, NLP, MICT (Joint) [detail] |
2024-01-25 16:00 |
Tokushima |
Naruto University of Education |
Design of an Efficient Activity Classification Model Focusing on the Characteristics of Egocentric Videos Kohei Baba, Kantaro Fujiwara (University of Tokyo), Gouhei Tanaka (Nagoya Institute of Technology) NLP2023-116 MICT2023-71 MBE2023-62 |
There are situations where egocentric videos have to be processed on wearable devices with limited computational resourc... [more] |
NLP2023-116 MICT2023-71 MBE2023-62 pp.153-157 |
HCGSYMPO (2nd) |
2023-12-11 - 2023-12-13 |
Fukuoka |
Asia pacific Import Mart (Kitakyushu) (Primary: On-site, Secondary: Online) |
Discrepancy of perceived speed of conversation on video call
-- Effects of camera position and its on/off -- Hakudai Makino (Chuo Univ.), Yu Kasagi (Rissho Univ.), Atsunori Ariga (Chuo Univ.) |
Miscommunication often occurs in conversation, in which contents of the verbally (mis)conveyed message have been of inte... [more] |
|
MIKA (3rd) |
2023-10-11 14:30 |
Okinawa |
Okinawa Jichikaikan (Primary: On-site, Secondary: Online) |
[Poster Presentation]
VR Surveillance System Assisted by Face Recognition in a Private 5G Environment Takumi Senaha, Yuki Norimatsu, Takuya Asaka (Tokyo Metropolitan Univ.) |
Research and development of an 8K full-sphere video surveillance system using a private 5G network is underway. In this ... [more] |
|
WIT, IPSJ-AAC |
2023-03-22 13:25 |
Online |
Online |
On promoting understanding of tunnel vision through short movie Masayo Tsurumi, Madoka Yasome (NTUT) WIT2022-19 |
While social recognition is progressing that there are visually impaired people who have low vision in addition to total... [more] |
WIT2022-19 pp.7-12 |
LOIS |
2023-03-14 10:10 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Creating Conversation Opportunities for Elderly People at Home by Coordinating Virtual Agents and Video Conferencing Services Hiro Okamoto, Sinan Chen, Masahide Nakamura (Kobe Univ), Sachio Saiki (Kochi Univ of Technology) LOIS2022-60 |
The increase in single-person households and the onset of "corona frailty" due to the new coronavirus have become proble... [more] |
LOIS2022-60 pp.95-101 |
IMQ |
2022-12-16 15:55 |
Chiba |
Nishi-Chiba Campus, Chiba Univ. |
Improving Pedestrian Attribute Recognition with Spatial Attention and Attribute Correlation Yichen Chen, Tetsuya Matsumoto (Nagoya Univ.), Yoshinori Takeuchi (Daido Univ.), Hiroaki Kudo (Nagoya Univ.) IMQ2022-18 |
In the field of video surveillance, pedestrian attribute recognition is a focus technical thema of study. To predict cer... [more] |
IMQ2022-18 pp.16-21 |
NS, ICM, CQ, NV (Joint) |
2022-11-24 13:50 |
Fukuoka |
Humanities and Social Sciences Center, Fukuoka Univ. + Online (Primary: On-site, Secondary: Online) |
Investigation of power consumption optimization method for distributed video analysis systems Hideyuki Shimonishi, Masayuki Murata (Osaka Univ.), Go Hasegawa (Tohoku Univ.) CQ2022-52 |
For the future cyber-physical society, it will be necessary to construct digital twins of real-world in large scale and ... [more] |
CQ2022-52 pp.28-33 |
PRMU |
2022-10-21 15:40 |
Tokyo |
Miraikan - The National Museum of Emerging Science and Innovation (Primary: On-site, Secondary: Online) |
Action Recognition of Anime Ayako Sakuma, Naoshi Kaneko, Kazuhiko Sumi (Aoyama Gakuin Univ.) PRMU2022-28 |
This paper presents an action recognition method for anime characters.
Since existing action recognition datasets focus... [more] |
PRMU2022-28 pp.35-40 |
PRMU |
2022-10-21 15:55 |
Tokyo |
Miraikan - The National Museum of Emerging Science and Innovation (Primary: On-site, Secondary: Online) |
Fine-grained Action Recognition Using Hand Trajectory Features for First-Person Cooking Videos Sota Miyamoto (Tokyo Tech), Yagi Takuma (UTokyo), Ushiku Yoshitaka, Atsushi Hashimoto (OSX), Nakamasa Inoue (Tokyo Tech) PRMU2022-29 |
Action recognition in kitchen environments is a crucial topic in computer vision and robotics
with application toward f... [more] |
PRMU2022-29 pp.41-46 |
IMQ |
2022-05-27 14:00 |
Tokyo |
|
Animal Video Retrieval System Using Image Recognition Chinatsu Watanabe (Kogakuin Univ.), Mayu Kaneko (Mizuho Research & Technologies), Atsumu Harada, Naiwala P. Chandrasiri (Kogakuin Univ.) IMQ2022-2 |
In general, the search function in a video sharing service site evaluates the relevance of a search query to the title, ... [more] |
IMQ2022-2 pp.7-11 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-21 14:40 |
Online |
Online |
A Note on Inspection Action Classification Using First and Third Person Video of Engineers Inspecting Bridges Tsuyoshi Masuda, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we propose an inspection action classification method using first and third person videos of engineers in... [more] |
|
SWIM |
2022-02-18 16:00 |
Online |
Online |
Training Data Generation Method for Object Recognition from Free Direction
-- Two Approaches Utilizing Video and CG -- Masatomo Ozeki, Ayaka Kumeta, Tsukasa Kudo (SIST) SWIM2021-38 |
Object recognition utilizing deep learning is widely applied in various fields. On the other hand, the preparation of tr... [more] |
SWIM2021-38 pp.51-58 |
PRMU |
2021-12-16 11:15 |
Online |
Online |
A Dataset for Work Instruction Deviation Detection from Field Work Videos Ryosuke Furuta (UTokyo), Motohiro Takagi (NTT), Yusuke Sugano, Yoichi Sato (UTokyo) PRMU2021-30 |
It is important to follow the work instruction manuals for field workers in order to protect them from accidents. In thi... [more] |
PRMU2021-30 pp.37-42 |
PRMU |
2021-12-16 16:45 |
Online |
Online |
Supervoxel-based Explanation for Action Recognition Ying Ji (Nagoya Univ.), Yu Wang (Ritsumeikan Univ.), Kensaku Mori (Nagoya Univ.), Jien Kato (Ritsumeikan Univ.) PRMU2021-42 |
Deep neural network has shown remarkable performance in various areas, including image classification, action recognitio... [more] |
PRMU2021-42 pp.98-100 |
PRMU |
2021-12-17 10:45 |
Online |
Online |
Analysis of Recognition Grounds of Models for Social Relationship Recognition Using Spatial-temporal TCAV Runa Sugiyama (Ritsumeikan Univ.), Ying JI (Nagoya Univ.), Yu Wang, Jien Kato (Ritsumeikan Univ.) PRMU2021-45 |
Social relationships between people in videos are difficult to recognize with high accuracy using traditional methods. I... [more] |
PRMU2021-45 pp.113-117 |
PRMU |
2021-12-17 11:15 |
Online |
Online |
Automatic Video Summarization Using Archive of Edited Videos Haruna Watanabe, Soma Shiraishi, Jun Piao, Katsuhiko Takahashi (NEC), Yu Nabeto (NEC Solution Innovators) PRMU2021-47 |
For the video summarization model, especially in the case of supervised learning methods, it is necessary to have the tr... [more] |
PRMU2021-47 pp.124-129 |
MVE |
2021-09-17 14:30 |
Online |
Online |
Improving Mask Generation Accuracy Exploiting Optical Flow in Weakly Supervised Instance Segmentation Jun Ikeda, Junichiro Mori (UTokyo) MVE2021-15 |
Weakly supervised instance segmentation is important because it reduces the huge pixel-level annotation cost required to... [more] |
MVE2021-15 pp.38-43 |
PRMU, IPSJ-CVIM |
2021-03-04 14:25 |
Online |
Online |
Leveraging Human Pose Estimation Model for Sports Video Classification Soichiro Sato, Masaki Aono (TUT) PRMU2020-76 |
In this paper, we propose a motion classification method of sports videos based on a posture estimation model.Specifical... [more] |
PRMU2020-76 pp.41-46 |
MVE, IMQ, IE, CQ (Joint) [detail] |
2021-03-01 11:35 |
Online |
Online |
Examination of voice input and treatment detection by video analysis for endoscopic findings creation support Chihiro Takigami, Mai Fujie (Chiba Univ.), Yuichiro Yoshimura (Toyama Univ.), Toshiya Nakaguchi (Chiba Univ.) IMQ2020-12 IE2020-52 MVE2020-44 |
Currently, endoscopy findings are mainly recorded by manual entry after the examination, which is burdensome due to the ... [more] |
IMQ2020-12 IE2020-52 MVE2020-44 pp.13-16 |