| Presentation | 2019-08-29 A Proposal of Facial Expression Recognition Method from Video Using Enhanced ConvLSTM Ryo Miyoshi, Noriko Nagata, Manabu Hashimoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose an enhanced convolutional long short-term memory (ConvLSTM) algorithm, i.e., Enhanced ConvLSTM, by adding skip connections in the spatiotemporal directions to conventional ConvLSTM to suppress gradient vanishing and use older information and We propose a method that uses this algorithm to automatically recognize facial expressions from videos. The proposed facial expression recognition method consists of two Enhanced ConvLSTM streams and two ResNet streams. The Enhanced ConvLSTM streams extract features for fine movements, and the ResNet streams extract features for rough movements. We conducted experiments to compare a method using ConvLSTM with skip connections and a method without them. A method using Enhanced CovnLSTM had a 4.44% higher accuracy than the a method using conventional ConvLSTM. Also the proposed facial expression recognition method achieved 45.29% accuracy, which is 2.31% higher than that of the conventional facial expression recognition method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | facial expression recognition / convolutional LSTM / skip connection |
| Paper # | MVE2019-12 |
| Date of Issue | 2019-08-22 (MVE) |
| Conference Information | |
| Committee | MVE |
|---|---|
| Conference Date | 2019/8/29(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Kenji Mase(Nagoya Univ.) |
| Vice Chair | Masayuki Ihara(NTT) |
| Secretary | Masayuki Ihara(Nagoya Univ.) |
| Assistant | Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) / Shogo Fukushima(Univ. of ToKyo) |
| Paper Information | |
| Registration To | Technical Committee on Media Experience and Virtual Environment |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Proposal of Facial Expression Recognition Method from Video Using Enhanced ConvLSTM |
| Sub Title (in English) | |
| Keyword(1) | facial expression recognition |
| Keyword(2) | convolutional LSTM |
| Keyword(3) | skip connection |
| 1st Author's Name | Ryo Miyoshi |
| 1st Author's Affiliation | Chukyo University(Chukyo Univ.) |
| 2nd Author's Name | Noriko Nagata |
| 2nd Author's Affiliation | Kwansei Gakuin University(Kwansei Gakuin Univ.) |
| 3rd Author's Name | Manabu Hashimoto |
| 3rd Author's Affiliation | Chukyo University(Chukyo Univ.) |
| Date | 2019-08-29 |
| Paper # | MVE2019-12 |
| Volume (vol) | vol.119 |
| Number (no) | MVE-190 |
| Page | pp.pp.37-42(MVE), |
| #Pages | 6 |
| Date of Issue | 2019-08-22 (MVE) |