Presentation | 2017-10-12 [Short Paper] Research of Automatic Scene Segmentation for Video Summary Generation based on Deep Learning Yuki Futami, Masayuki Kashima, Shinya Fukumoto, Kiminori Sato, Mutsumi Watanabe, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Huge amount of video contents are handled routinely. The video is divided into scenes that consists of semantic clusters and, it becomes larger the necessity to present the scene user wants from the huge amount of videos. In recent years, the efficacy of deep learning in image recognition has been shown.The purpose of this study was automatic segmentation of scenes based on deep learning, and to generate summary sentences of divided scenes. In the first step, shots of videos are segmented. In this paper, we propose the extraction method of shot points by comparing the similarity of the images based on feature vector extracted by CNNExperimental results using a plurality of video contents have shown the effectiveness of the proposed method |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Deep Learning / Shot Detection / Scene Segmentation / Convolutional Neural Network |
Paper # | PRMU2017-78 |
Date of Issue | 2017-10-05 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2017/10/12(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) |
Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) |
Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) |
Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) |
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) | [Short Paper] Research of Automatic Scene Segmentation for Video Summary Generation based on Deep Learning |
Sub Title (in English) | |
Keyword(1) | Deep Learning |
Keyword(2) | Shot Detection |
Keyword(3) | Scene Segmentation |
Keyword(4) | Convolutional Neural Network |
1st Author's Name | Yuki Futami |
1st Author's Affiliation | Kagoshima University(Kagoshima Univ.) |
2nd Author's Name | Masayuki Kashima |
2nd Author's Affiliation | Kagoshima University(Kagoshima Univ.) |
3rd Author's Name | Shinya Fukumoto |
3rd Author's Affiliation | Kagoshima University(Kagoshima Univ.) |
4th Author's Name | Kiminori Sato |
4th Author's Affiliation | Kagoshima University(Kagoshima Univ.) |
5th Author's Name | Mutsumi Watanabe |
5th Author's Affiliation | Kagoshima University(Kagoshima Univ.) |
Date | 2017-10-12 |
Paper # | PRMU2017-78 |
Volume (vol) | vol.117 |
Number (no) | PRMU-238 |
Page | pp.pp.91-92(PRMU), |
#Pages | 2 |
Date of Issue | 2017-10-05 (PRMU) |