Presentation | 2021-08-26 A study on the selection of thumbnail images considering a genre of TV programs Momoko Maezawa, Rei Endo, Naotsuna Fujimori, Takahiro Mochizuki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Broadcasting stations are enriching their TV program websites with the aim of improving the TV program contact rate of viewers. On TV program websites and social media, there are many cases where some representative still images selected from videos are posted so that viewers can easily grasp the outline of program contents. However, the image selection work requires a great deal of labor. Therefore, there are needs for technologies that automatically extract representative still images from video. In this paper, we propose a method for selecting representative still image candidates from video by scoring images using a neural network learned images with program genres. By taking the program genre into learning process, we aim to realize a mechanism that can select candidates for the representative still image in consideration of the tendency of the representative still image for each genre. Furthermore, we verify the effectiveness of the proposed method by experimental comparisons. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Representative still image / Thumbnail image / Neural network |
Paper # | PRMU2021-15 |
Date of Issue | 2021-08-19 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2021/8/26(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | CV/PR techniques for human-robot cooperation |
Chair | Seiichi Uchida(Kyushu Univ.) |
Vice Chair | Masakazu Iwamura(Osaka Pref. Univ.) / Mitsuru Anpai(Denso IT Lab.) |
Secretary | Masakazu Iwamura(NTT) / Mitsuru Anpai(Tottori Univ.) |
Assistant | Kouta Yamaguchi(CyberAgent) / Yusuke Matsui(Univ. of Tokyo) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A study on the selection of thumbnail images considering a genre of TV programs |
Sub Title (in English) | |
Keyword(1) | Representative still image |
Keyword(2) | Thumbnail image |
Keyword(3) | Neural network |
1st Author's Name | Momoko Maezawa |
1st Author's Affiliation | NHK Science & Technology Research Laboratories(NHK) |
2nd Author's Name | Rei Endo |
2nd Author's Affiliation | NHK Science & Technology Research Laboratories(NHK) |
3rd Author's Name | Naotsuna Fujimori |
3rd Author's Affiliation | NHK Science & Technology Research Laboratories(NHK) |
4th Author's Name | Takahiro Mochizuki |
4th Author's Affiliation | NHK Science & Technology Research Laboratories(NHK) |
Date | 2021-08-26 |
Paper # | PRMU2021-15 |
Volume (vol) | vol.121 |
Number (no) | PRMU-155 |
Page | pp.pp.48-51(PRMU), |
#Pages | 4 |
Date of Issue | 2021-08-19 (PRMU) |