Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
ITS, IE, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2024-02-19 13:45 |
Hokkaido |
Hokkaido Univ. |
CLIP-based Zero-shot In-Distribution Detection Atsuyuki Miyai, Qing Yu (UTokyo), Go Irie (TUS), Kiyoharu Aizawa (UTokyo) ITS2023-53 IE2023-42 |
Extracting in-distribution (ID) images from noisy images scraped from the Internet is an important preprocessing for con... [more] |
ITS2023-53 IE2023-42 pp.40-45 |
IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2023-02-21 10:15 |
Hokkaido |
Hokkaido Univ. |
Text - Image Fashion Retrieval with Textural Features Daichi Suzuki (Tokyo Univ.), Go Irie (Tokyo Univ of Science), Kiyoharu Aizawa (Tokyo Univ.) ITS2022-43 IE2022-60 |
In this study, we propose a method of pre-processing on a dataset and deep learning to perform fashion retrieval conside... [more] |
ITS2022-43 IE2022-60 pp.11-16 |
IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2023-02-22 10:00 |
Hokkaido |
Hokkaido Univ. |
ITS2022-60 IE2022-77 |
Unsupervised domain adaptation (UDA) is extremely effective for transferring knowledge from a label-rich source domain t... [more] |
ITS2022-60 IE2022-77 pp.101-106 |
MVE, IPSJ-CVIM, VRSJ-SIG-MR |
2023-01-26 16:35 |
Nara |
Nara Institute of Science and Technology (Primary: On-site, Secondary: Online) |
MVE2022-35 |
(To be available after the conference date) [more] |
MVE2022-35 pp.3-8 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-21 13:00 |
Online |
Online |
Domain Incremental Leaning with Adaptive Loss Functions Takumi Kawashima (UTokyo), Go Irie, Daiki Ikami (NTT), Kiyoharu Aizawa (UTokyo) ITS2021-30 IE2021-39 |
During domain incremental learning of image classification task, the distribution of images continually change, and mode... [more] |
ITS2021-30 IE2021-39 pp.31-36 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-22 10:45 |
Online |
Online |
ITS2021-46 IE2021-55 |
There has been a tremendous progress in unsupervised domain adaptation (UDA), which aims to transfer knowledge acquired ... [more] |
ITS2021-46 IE2021-55 pp.127-132 |
PRMU |
2020-12-17 10:30 |
Online |
Online |
Simultaneous learning of object foreground, pose and class using only class teacher Shunsuke Yoneda (Tottori Univ.), Go Irie (NTT), Masashi Nisiyama, Yoshio Iwai (Tottori Univ.) PRMU2020-40 |
(To be available after the conference date) [more] |
PRMU2020-40 pp.12-17 |
ITE-HI, IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2020-02-28 15:40 |
Hokkaido |
Hokkaido Univ. (Cancelled but technical report was issued) |
Multi-Task Curriculum Learning for Open-Set Semi-Supervised Recognition Qing Yu (Tokyo Univ.), Go Irie (NTT), Kiyoharu Aizawa (Tokyo Univ.) ITS2019-54 IE2019-92 |
[more] |
ITS2019-54 IE2019-92 pp.323-328 |
ITE-HI, IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2020-02-28 11:40 |
Hokkaido |
Hokkaido Univ. (Cancelled but technical report was issued) |
[Special Invited Talk]
Toward Real-World Scene Understanding & Search Go Irie (NTT) |
[more] |
|
PRMU, BioX |
2019-03-18 10:00 |
Tokyo |
|
A Generative Self-Ensemble Approach to Simulated+Unsupervised Learning Yu Mitsuzumi (Kyoto Univ.), Go Irie (NTT), Atsushi Nakazawa (Kyoto Univ.), Akisato Kimura (NTT) BioX2018-52 PRMU2018-156 |
The simulated and unsupervised (S+U) learning framework is an effective approach in computer vision since it solves vari... [more] |
BioX2018-52 PRMU2018-156 pp.137-142 |
ITS, IE, ITE-MMS, ITE-HI, ITE-ME, ITE-AIT [detail] |
2019-02-19 14:45 |
Hokkaido |
Hokkaido Univ. |
Data Augmentation via Transformer and Diverse QA Generation for Visual Question Answering Masao Tsukiyama, Daiki Ikami (Tokyo Univ.), Go Irie (NTT), Kiyoharu Aizawa (Tokyo Univ.) ITS2018-68 IE2018-89 |
[more] |
ITS2018-68 IE2018-89 pp.91-96 |
ITS, IE, ITE-MMS, ITE-HI, ITE-ME, ITE-AIT [detail] |
2018-02-16 10:45 |
Hokkaido |
Hokkaido Univ. |
Parallel feature pooling without information loss Akito Takeki, Daiki Ikami (Univ. Tokyo), Go Irie (NTT), Kiyoharu Aizawa (Univ. Tokyo) ITS2017-80 IE2017-112 |
In convolutional neural networks for image recognition, the pooling layer plays a important role.
The pooling layer pe... [more] |
ITS2017-80 IE2017-112 pp.239-244 |
IE, ITE-AIT, ITE-ME [detail] |
2014-11-07 11:40 |
Kagoshima |
|
Attribute Detection with Position Prior Takayuki Umeda, Go Irie, Hiroyuki Arai, Yukinobu Taniguchi (former NTT) |
[more] |
|
IE, ITE-AIT, ITE-ME [detail] |
2014-11-07 12:10 |
Kagoshima |
|
On Object Retrieval from Similar Instances Yukito Watanabe, Go Irie, Hiroyuki Arai, Yukinobu Taniguchi (NTT) |
[more] |
|
PRMU |
2014-03-14 09:30 |
Tokyo |
|
Dynamic Attribute Discovery via Incremental Category Learning Takayuki Umeda, Yongqing Sun, Go Irie, Kyoko Sudo, Yukinobu Taniguchi (NTT) PRMU2013-196 |
In recent years, attribute has shown promising results in image classication and object recognition.
However, it is di... [more] |
PRMU2013-196 pp.169-172 |
IPSJ-DC, LOIS (Joint) |
2011-07-21 14:10 |
Hokkaido |
Future Univ. Hakodate |
Generating Personalized Travel Plan with Social Media Takeshi Kurashima, Tomoharu Iwata, Go Irie, Ko Fujimura (NTT) LOIS2011-10 |
We have proposed a travel route recommendation method considering the user’s current location, user’s spare time and use... [more] |
LOIS2011-10 pp.7-12 |
LOIS, IPSJ-DC, IPSJ-FI (Joint) |
2010-03-04 18:15 |
Okinawa |
Okinawaken-Seinen-Kaikan |
Travel Route Recommendation using Geotags on Photo Sharing Service Takeshi Kurashima, Tomoharu Iwata, Go Irie, Ko Fujimura (NTT Corp.) LOIS2009-88 |
(To be available after the conference date) [more] |
LOIS2009-88 pp.55-60 |
PRMU |
2008-12-19 10:00 |
Kumamoto |
Kumamoto Univ. |
Degree-of-Edit Order Estimation for Consumer Genrated Video Retrieval Go Irie, Kota Hidaka, Takashi Sato (NTT Cyber Solutions Laboratories/Nippon Telegraph and Telepone C), Akira Kojima (NTT Corp.), Kiyoharu Aizawa (Tokyo Univ.) PRMU2008-172 |
In this paper, we consider about introducing {\em degree-of-edit order} which represents ``how much a CGV is edited'' as... [more] |
PRMU2008-172 pp.147-152 |
ITE-HI, ITE-AIT, ITE-ME, IE, ITS |
2008-02-19 14:10 |
Hokkaido |
Graduate School of Information Science and Technology Hokkaido Univ |
A New video editing interface based on the automatic extraction of emphasized speech and “laughter” scenes Thi NhatThanh Nguyen (Vietnam National University Hanoi), Kota Hidaka, Uwe Kowalik, Go Irie, Takashi Sato, Yukinobu Taniguchi (NTT) ITS2007-77 IE2007-260 |
Most current video skimming engines create a video digest automatically with fixed and closed algorithms and do not real... [more] |
ITS2007-77 IE2007-260 pp.83-86 |