Micro-Expression Recognition by Regression Model and Group Sparse Spatio-Temporal Feature Learning

Lü, Ping; Zheng, Wenming; Wang, Ziyan; Li, Qiang; Zong, Yuan; Xin, Minghai; Wu, Lenan

doi:10.1587/transinf.2015edl8221

Cited by 15 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, micro-expression recognition is still one of recent a ractive research topics among a ective computing, multimedia information processing and pa ern recognition communities [26] due to its potential values. e micro-expression recognition research can be early traced to the work of [29], in which P ster et al proposed to use temporal interpolation model (TIM) and local binary pa ern from three orthogonal planes (LBP-TOP) [44] to deal with micro-expression arXiv:1707.08645v1 [cs.CV] 26 Jul 2017 recognition problem. eir experimental results show that LBP-TOP is e ective for micro-expression recognition problem.…”

Section: Introductionmentioning

confidence: 99%

Learning a Target Sample Re-Generator for Cross-Database Micro-Expression Recognition

Zong

Huang

Zheng

et al. 2017

Proceedings of the 25th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate the cross-database micro-expression recognition problem, where the training and testing samples are from two di erent micro-expression databases. Under this setting, the training and testing samples would have di erent feature distributions and hence the performance of most existing microexpression recognition methods may decrease greatly. To solve this problem, we propose a simple yet e ective method called Target Sample Re-Generator (TSRG) in this paper. By using TSRG, we are able to re-generate the samples from target micro-expression database and the re-generated target samples would share same or similar feature distributions with the original source samples. For this reason, we can then use the classi er learned based on the labeled source samples to accurately predict the micro-expression categories of the unlabeled target samples. To evaluate the performance of the proposed TSRG method, extensive cross-database micro-expression recognition experiments designed based on SMIC and CASME II databases are conducted. Compared with recent state-of-the-art cross-database emotion recognition methods, the proposed TSRG achieves more promising results. * Yuan Zong is also with the

show abstract

Section: Introductionmentioning

confidence: 99%

Learning a Target Sample Re-Generator for Cross-Database Micro-Expression Recognition

Zong

Huang

Zheng

et al. 2017

Proceedings of the 25th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…Method Accuracy HOG [11] 57.9% LBP-TOP+Nearest Neighbor [5] 65.8% LBP-TOP+GSLSR [13] 70.1% TIM+DCNN+SVM [16] 65.9% LOSO (train from scratch) 65.2% LOSO (with transfer learning) 66.3% LBP-TOP+Nearest Neighbor [5] 53.7% Fivefold (train from scratch) 95.8% Fivefold (with transfer learning) 97.4%…”

Section: Smicmentioning

confidence: 99%

Combining 3D Convolutional Neural Networks with Transfer Learning by Supervised Pre-Training for Facial Micro-Expression Recognition

Zhi

Wan

et al. 2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Facial micro-expression is momentary and subtle facial reactions, and it is still challenging to automatically recognize facial micro-expression with high accuracy in practical applications. Extracting spatiotemporal features from facial image sequences is essential for facial micro-expression recognition. In this paper, we employed 3D Convolutional Neural Networks (3D-CNNs) for self-learning feature extraction to represent facial micro-expression effectively, since the 3D-CNNs could well extract the spatiotemporal features from facial image sequences. Moreover, transfer learning was utilized to deal with the problem of insufficient samples in the facial micro-expression database. We primarily pretrained the 3D-CNNs on normal facial expression database Oulu-CASIA by supervised learning, then the pre-trained model was effectively transferred to the target domain, which was the facial micro-expression recognition task. The proposed method was evaluated on two available facial micro-expression datasets, i.e. CASME II and SMIC-HS. We obtained the overall accuracy of 97.6% on CASME II, and 97.4% on SMIC, which were 3.4% and 1.6% higher than the 3D-CNNs model without transfer learning, respectively. And the experimental results demonstrated that our method achieved superior performance compared to state-of-the-art methods.

show abstract

“…For deep features, frame-level static facial expression features are not sufficient. Previous studies for expression recognition [24], [25] show that sequence-level dynamic spatiotemporal features of facial expressions significantly improve the recognition performance. Therefore, we use the deep 3-dimensional convolutional network (C3D) [26], which takes a continuous sequence of video frames as input, to extract spatiotemporal facial features.…”

Section: Introductionmentioning

confidence: 99%

Pain Intensity Estimation Using Deep Spatiotemporal and Handcrafted Features

Wang

Sun

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Automatically recognizing pain and estimating pain intensity is an emerging research area that has promising applications in the medical and healthcare field, and this task possesses a crucial role in the diagnosis and treatment of patients who have limited ability to communicate verbally and remains a challenge in pattern recognition. Recently, deep learning has achieved impressive results in many domains. However, deep architectures require a significant amount of labeled data for training, and they may fail to outperform conventional handcrafted features due to insufficient data, which is also the problem faced by pain detection. Furthermore, the latest studies show that handcrafted features may provide complementary information to deep-learned features; hence, combining these features may result in improved performance. Motived by the above considerations, in this paper, we propose an innovative method based on the combination of deep spatiotemporal and handcrafted features for pain intensity estimation. We use C3D, a deep 3-dimensional convolutional network that takes a continuous sequence of video frames as input, to extract spatiotemporal facial features. C3D models the appearance and motion of videos simultaneously. For handcrafted features, we propose extracting the geometric information by computing the distance between normalized facial landmarks per frame and the ones of the mean face shape, and we extract the appearance information using the histogram of oriented gradients (HOG) features around normalized facial landmarks per frame. Two levels of SVRs are trained using spatiotemporal, geometric and appearance features to obtain estimation results. We tested our proposed method on the UNBC-McMaster shoulder pain expression archive database and obtained experimental results that outperform the current state-of-the-art.

show abstract

Micro-Expression Recognition by Regression Model and Group Sparse Spatio-Temporal Feature Learning

Cited by 15 publications

References 18 publications

Learning a Target Sample Re-Generator for Cross-Database Micro-Expression Recognition

Learning a Target Sample Re-Generator for Cross-Database Micro-Expression Recognition

Combining 3D Convolutional Neural Networks with Transfer Learning by Supervised Pre-Training for Facial Micro-Expression Recognition

Pain Intensity Estimation Using Deep Spatiotemporal and Handcrafted Features

Contact Info

Product

Resources

About