Corpus ID: 237532789

Deep Learning for Micro-expression Recognition: A Survey

  title={Deep Learning for Micro-expression Recognition: A Survey},
  author={Yante Li and Jinsheng Wei and Yang Liu and Janne Kauttonen and Guoying Zhao},
Micro-expressions (MEs) are involuntary facial movements revealing people’s hidden feelings in high-stake situations and have practical importance in medical treatment, national security, interrogations and many human-computer interaction systems. Early methods for micro-expression recognition (MER) mainly based on traditional appearance and geometry features. Recently, with the success of deep learning (DL) in various fields, neural networks have received increasing interests in MER. Different… Expand

Figures and Tables from this paper


MERASTC: Micro-expression Recognition using Effective Feature Encodings and 2D Convolutional Neural network
Facial micro-expression (ME) can disclose genuine and concealed human feelings. It makes MEs extensively useful in real-world applications pertaining to affective computing and psychology.Expand
Micro-expression recognition based on 3D flow convolutional neural network
This article proposes applying the 3D flow-based CNNs model for video-based micro-expression recognition, which extracts deeply learned features that are able to characterize fine motion flow arising from minute facial movements. Expand
Dynamic image for micro-expression recognition on region-based framework
  • T. Le, Thuong-Khanh Tran, M. Rege
  • Computer Science
  • 2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI)
  • 2020
A compact framework where a rank pooling concept called dynamic image is employed as a descriptor to extract informative features on certain regions of interests along with a convolutional neural network deployed on elicited dynamic images to recognize micro-expressions therein is presented. Expand
AU-assisted Graph Attention Convolutional Network for Micro-Expression Recognition
A novel micro-expression recognition approach by combining Action Units (AUs) and emotion category labels is proposed, based on facial muscle movements, which outperforms other state-of-the-art methods on both single database and cross-database micro- expression recognition. Expand
Image Based Facial Micro-Expression Recognition Using Deep Learning on Small Datasets
  • M. Takalkar, M. Xu
  • Computer Science
  • 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
  • 2017
Experimental results demonstrate the effectiveness of the proposed CNN approach in image based micro- expression recognition and present comparable results with the best-related works. Expand
An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge
To mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data and the state-of-the-art spotting works are introduced. Expand
LARNet: Real-Time Detection of Facial Micro Expression Using Lossless Attention Residual Network
The aim and motivation of this paper are to provide an end-to-end architecture that accurately detects the actual expressions at the micro-scale features in facial micro expressions with the proposed Lossless Attention Residual Network (LARNet). Expand
Recognizing Spontaneous Micro-Expression Using a Three-Stream Convolutional Neural Network
This paper proposes a three-stream convolutional neural network (TSCNN) to recognize MEs by learning ME-discriminative features in three key frames of ME videos, and designs a dynamic-temporal stream, static-spatial stream, and local- Spatial stream module for the TSCNN. Expand
Facial micro-expression recognition based on the fusion of deep learning and enhanced optical flow
This research proposed a novel algorithm for automatic micro-expression recognition which combined a deep multi-task convolutional network for detecting the facial landmarks and a fused deep convolutionan network for estimating the optical flow features of the micro- expression. Expand
A Convolutional Neural Network for Compound Micro-Expression Recognition
The deep network framework designed in this study can well recognize the emotional information of basic micro-expressions and compound micro- expressions. Expand