Research Article
3DCNN Backed Conv-LSTM Auto Encoder for Micro Facial Expression Video Recognition
@INPROCEEDINGS{10.1007/978-3-031-04409-0_9, author={Md. Sajjatul Islam and Yuan Gao and Zhilong Ji and Jiancheng Lv and Adam Ahmed Qaid Mohammed and Yongsheng Sang}, title={3DCNN Backed Conv-LSTM Auto Encoder for Micro Facial Expression Video Recognition}, proceedings={Machine Learning and Intelligent Communications. 6th EAI International Conference, MLICOM 2021, Virtual Event, November 2021, Proceedings}, proceedings_a={MLICOM}, year={2022}, month={5}, keywords={Micro-expression Recognition Deep learning Transfer learning Spatio-temporal}, doi={10.1007/978-3-031-04409-0_9} }- Md. Sajjatul Islam
Yuan Gao
Zhilong Ji
Jiancheng Lv
Adam Ahmed Qaid Mohammed
Yongsheng Sang
Year: 2022
3DCNN Backed Conv-LSTM Auto Encoder for Micro Facial Expression Video Recognition
MLICOM
Springer
DOI: 10.1007/978-3-031-04409-0_9
Abstract
Facial Micro-Expression recognition in the field of emotional information processing has become an inexorable necessity for its exotic attributes. It is a non-verbal, spontaneous, and involuntary leakage of true emotion in disguise of most expressive intentional prototypical facial expressions. However, it persists only for a split-second duration and possesses fainted facial muscle movements that make the recognition task more difficult with naked eyes. Besides, there are a limited number of video samples and wide-span domain shifting among datasets. Considering these challenges, several video-based works have been done to improve the classification accuracy but still lack high accuracy. This works addresses these issues and presents an approach with a deep 3D Convolutional Residual Neural Network as a backbone followed by a Long-Short-Term-Memory auto-encoder with 2D convolutions model for automatic Spatio-temporal feature extractions, fine-tuning, and classifications from videos. Also, we have done transfer learning on three standard macro-expression datasets to reduce over-fitting. Our work has shown a significant accuracy gain with extensive experiments on composite video samples from five publicly available micro-expression benchmark datasets, CASME, CASMEII, CAS(ME)2, SMIC, and SAMM. This outweighs the state-of-the-art accuracy. It is the first attempt to work with five datasets and rational implication of LSTM auto-encoder for micro-expression recognition.
