| Presentation | 2018-03-05 [Poster Presentation] Video Forgery Detection Considering Spatio-Temporal Consistency Takaaki Yoshida, Kazuhiro Kono, Noboru Babaguchi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes a video forgery detection method in dynamic scenes such as dynamic background or dynamic perspectives. In order to adapt to dynamic scenes, we use Convolutional Neural Network and Recurrent Neural Network together. This enables as to consider spatio-temporal consistency of videos. We also construct new video forgery databases for object modification as well as object removal. Our proposed method using Convolutional LSTM achieved Area-Under-Curve (AUC) 0.970 and Equal-Error-Rate (EER) 0.078 on the object addition databaseand AUC 0.872 and EER 0.219 on the object modification database. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Video Forgery Detection / Dynamic scene / Convolutional LSTM / CNN / RNN / Modification Dataset |
| Paper # | EMM2017-81 |
| Date of Issue | 2018-02-26 (EMM) |
| Conference Information | |
| Committee | EMM |
|---|---|
| Conference Date | 2018/3/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Naze Community Center (Amami-Shi, Kagoshima) |
| 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(TUS) |
| Vice Chair | Hirohisa Hioki(Kyoto Univ.) / Minoru Kuribayashi(Okayama Univ.) |
| Secretary | Hirohisa Hioki(Shizuoka Univ.) / Minoru Kuribayashi(Tokyo Metropolitan Univ.) |
| Assistant | Kan Hyonho(NIT, Tokyo) / Harumi Murata(Chukyo Univ.) |
| 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] Video Forgery Detection Considering Spatio-Temporal Consistency |
| Sub Title (in English) | |
| Keyword(1) | Video Forgery Detection |
| Keyword(2) | Dynamic scene |
| Keyword(3) | Convolutional LSTM |
| Keyword(4) | CNN |
| Keyword(5) | RNN |
| Keyword(6) | Modification Dataset |
| 1st Author's Name | Takaaki Yoshida |
| 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 | 2018-03-05 |
| Paper # | EMM2017-81 |
| Volume (vol) | vol.117 |
| Number (no) | EMM-476 |
| Page | pp.pp.23-28(EMM), |
| #Pages | 6 |
| Date of Issue | 2018-02-26 (EMM) |