Presentation | 2019-03-13 [Poster Presentation] A Consideration on Spatio-Temporal Feature Learning for Video Forgery Detection Shoken Ohshiro, Kazuhiro Kono, Noboru Babaguchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The purpose of our work is to detect objects tampered in the spatial domain of videos including dynamic scenes such as a video taken with a smartphone. We use forgery detection models based on spatio-temporal Convolutional Neural Networks (CNN) to consider spatial and temporal aspects of videos. In this paper, we adopt (2+1)D CNN, which is one of the CNNs and calculates each convolution individually. We investigate the influences of spatial and temporal features on video forgery detection. We also report that our proposed forgery detection system based on (2+1)D CNN achieved higher accuracy than a detection system based on 3D CNN. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Video Analysis / Video Forgery Detection / Passive Approach / Spatio-Temporal Convolutional Neural Network / Object Modification |
Paper # | EMM2018-104 |
Date of Issue | 2019-03-06 (EMM) |
Conference Information | |
Committee | EMM |
---|---|
Conference Date | 2019/3/13(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | TBD |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image and Sound Quality, Metrics for Perception and Recognition, Human Auditory and Visual System, etc. |
Chair | Keiichi Iwamura(TUC) |
Vice Chair | Minoru Kuribayashi(Okayama Univ.) / Tetsuya Kojima(NIT,Tokyo College) |
Secretary | Minoru Kuribayashi(NIT, Tokyo) / Tetsuya Kojima(Tyukyo Univ.) |
Assistant | Hiroko Akiyama(NIT, Nagano College) / キタヒロ カネダ(CANON) |
Paper Information | |
Registration To | Technical Committee on Enriched MultiMedia |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] A Consideration on Spatio-Temporal Feature Learning for Video Forgery Detection |
Sub Title (in English) | |
Keyword(1) | Video Analysis |
Keyword(2) | Video Forgery Detection |
Keyword(3) | Passive Approach |
Keyword(4) | Spatio-Temporal Convolutional Neural Network |
Keyword(5) | Object Modification |
1st Author's Name | Shoken Ohshiro |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Kazuhiro Kono |
2nd Author's Affiliation | Kansai University(Kansai Univ.) |
3rd Author's Name | Noboru Babaguchi |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2019-03-13 |
Paper # | EMM2018-104 |
Volume (vol) | vol.118 |
Number (no) | EMM-494 |
Page | pp.pp.67-72(EMM), |
#Pages | 6 |
Date of Issue | 2019-03-06 (EMM) |