Deep convolutional BiLSTM fusion network for facial expression recognition

Liang, Dongfang; Liang, Huagang; Yu, Zhenbo; Zhang, Yipu

doi:10.1007/s00371-019-01636-3

Cited by 72 publications

(36 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 7 illustrates the comparison of previous work. The result of our model on CK+ and MMI databases achieves relatively same accuracy obtained by Liang et al [54] and Zhang et al [56]. Compared to other databases, the recognition performance shows a significant degradation on SFEW database due to large variations of pose and illumination.…”

Section: Experimental Analysissupporting

confidence: 75%

Novel deep learning model for facial expression recognition based on maximum boosted CNN and LSTM

Rajan¹,

Chenniappan²,

Devaraj

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

Section: Experimental Analysissupporting

confidence: 75%

Novel deep learning model for facial expression recognition based on maximum boosted CNN and LSTM

Rajan¹,

Chenniappan²,

Devaraj

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

“…The Bi-LSTM [43] model consists of forward LSTM and reverse LSTM, which are used to extract forward and reverse context features respectively. For the input x t at time t, the hidden states obtained by the forward LSTM and the reverse LSTM are h t and h t , respectively.…”

Section: Crf Layermentioning

confidence: 99%

Post Text Processing of Chinese Speech Recognition Based on Bidirectional LSTM Networks and CRF

et al. 2019

View full text Add to dashboard Cite

With the rapid development of Internet of Things Technology, speech recognition has been applied more and more widely. Chinese Speech Recognition is a complex process. In the process of speech-to-text conversion, due to the influence of dialect, environmental noise, and context, the accuracy of speech-to-text in multi-round dialogues and specific contexts is still not high. After the general speech recognition technology, the text after speech recognition can be detected and corrected in the specific context, which is helpful to improve the robustness of text comprehension and is a beneficial supplement to the speech recognition technology. In this paper, a text processing model after Chinese Speech Recognition is proposed, which combines a bidirectional long short-term memory (LSTM) network with a conditional random field (CRF) model. The task is divided into two stages: text error detection and text error correction. In this paper, a bidirectional long short-term memory (Bi-LSTM) network and conditional random field are used in two stages of text error detection and text error correction respectively. Through verification and system test on the SIGHAN 2013 Chinese Spelling Check (CSC) dataset, the experimental results show that the model can effectively improve the accuracy of text after speech recognition.

show abstract

“…There are also studies conducted with CNN architecture in the FER field [37][38][39][40][41][42][43][44][45][46]. FER studies consist of three phases.…”

Section: Introductionmentioning

confidence: 99%

“…In this network consisting of 3 parts, Deep Spatial Network (DSN) is used for spatial display features, Deep Temporal Network (DTN) is used to benefit from temporal information, and BiLSTM network is used for the formation of six basic expressions. Comparative experiments with 13 different methods on CK+, Oulu-CASIA and MMI datasets showed that the proposed method can achieve high performance[42].Bargal et al proposed an architecture to classify 8 emotional expressions (including contempt). The Acted Facial Expressions in the Wild (AFEW) 6.0 cropped video dataset combinations were used to train the architecture.…”

mentioning

confidence: 99%