Shuang Gao This email address is being protected from spambots. You need JavaScript enabled to view it.1

1College of Music, Anhui Normal University, Wuhu, 241000, Anhui, China


Received: March 2, 2022
Accepted: May 3, 2022
Publication Date: June 17, 2022

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||  


In recent years, dance emotion recognition has become a hot research issue in the field of human-computer interaction and art design. However, multi-modal dimension emotion recognition can detect subtle action emotion changes. In multi-modal dimension emotion recognition, it is necessary to consider how to effectively fuse different modal emotion information. Aiming at the problem of effective feature extraction and modal synchronization in feature layer fusion, and the correlation problem of different modal feature information in decision layer fusion, we propose a new method for multi-modal dimension dance emotion recognition. It takes the lightweight network structure MobileNetV2 as the benchmark network architecture and introduces an independently designed attention module to increase the weight of the saliency feature graph learned by the convolutional layer, so as to improve the classification accuracy. The spatial information of the proposed model is input in parallel with the channel information. By defining the small convolution of 1×1 and 3×3, the computational amount and complexity are reduced while ensuring the lightweight of the structure. The audio model, video model and multi-modal fusion model are respectively constructed to carry out deep feature learning for information flow. Finally, they are input to the two-channel bi-directional long short term memory to obtain the final motion emotion prediction value. Compared with other state-of-the-art methods, the proposed method can effectively capture emotion information in the high-level dimension and obtain the better recognition effect, so it can better fuse audio and video information.

Keywords: Dance emotion recognition, multi-modal dimension, MobileNetV2, two-channel bidirectional long short memory network, spatial information


  1. [1] R. Jeen Retna Kumar, M. Sundaram, N. Arumugam, and V. Kavitha, (2021) “Face feature extraction for emotion recognition using statistical parameters from subband selective multilevel stationary biorthogonal wavelet transform" Soft Computing 25(7): 5483–5501. DOI: 10.1007/s00500-020-05550-y.
  2. [2] J. Kacur, B. Puterka, J. Pavlovicova, and M. Oravec, (2021) “On the speech properties and feature extraction methods in speech emotion recognition" Sensors 21(5): 1–27. DOI: 10.3390/s21051888.
  3. [3] Z. Peng, J. Dang, M. Unoki, and M. Akagi, (2021) “Multi-resolution modulation-filtered cochleagram feature for LSTM-based dimensional emotion recognition from speech" Neural Networks 140: 261–273. DOI: 10.1016/j.neunet.2021.03.027.
  4. [4] C. Guanghui and Z. Xiaoping, (2021) “Multi-Modal Emotion Recognition by Fusing Correlation Features of Speech-Visual" IEEE Signal Processing Letters 28: 533–537. DOI: 10.1109/LSP.2021.3055755.
  5. [5] W. Xiaohua, P. Muzi, P. Lijuan, H. Min, J. Chunhua, and R. Fuji, (2019) “Two-level attention with two-stage multi-task learning for facial emotion recognition" Journal of Visual Communication and Image Representation 62: 217–225. DOI: 10.1016/j.jvcir.2019.05.009.
  6. [6] Y. Kwak, K. Kong, W.-J. Song, B.-K. Min, and S.-E. Kim, (2020) “Multilevel Feature Fusion with 3D Convolutional Neural Network for EEG-Based Workload Estimation" IEEE Access 8: 16009–16021. DOI: 10.1109/aCCESS.2020.2966834.
  7. [7] H. Xu, H. Zhang, K. Han, Y. Wang, Y. Peng, and X. Li. “Learning alignment for multimodal emotion recognition from speech”. In: 2019-September. Cited by: 34; All Open Access, Green Open Access. 2019, 3569–3573. DOI: 10.21437/Interspeech.2019-3247.
  8. [8] H. Li, W. Ding, Z. Wu, and Z. Liu, (2020) “Learning Fine-Grained Cross Modality Excitement for Speech Emotion Recognition" arXiv preprint arXiv:2010.12733:
  9. [9] R. Basnet, M. T. Islam, T. Howlader, S. M. Rahman, and D. Hatzinakos. “Statistical Selection of CNN-based Audiovisual Features for Instantaneous Estimation of Human Emotional States”. In: 2018-January. Cited by: 3; All Open Access, Green Open Access. 2017, 50–54. DOI: 10.1109/ICTCS.2017.14.
  10. [10] A. Samareh, Y. Jin, Z.Wang, X. Chang, and S. Huang, (2018) “Detect depression from communication: how computer vision, signal processing, and sentiment analysis join forces" IISE Transactions on Healthcare Systems Engineering 8(3): 196–208. DOI: 10.1080/24725579.2018.1496494.
  11. [11] S. Poria, E. Cambria, N. Howard, G.-B. Huang, and A. Hussain, (2016) “Fusing audio, visual and textual clues for sentiment analysis from multimodal content" Neurocomputing 174: 50–59.
  12. [12] G. Castellano, I. Leite, A. Pereira, C. Martinho, A. Paiva, and P.W. McOwan, (2010) “Affect recognition for interactive companions: Challenges and design in real world scenarios" Journal on Multimodal User Interfaces 3(1): 89–98. DOI: 10.1007/s12193-009-0033-5.
  13. [13] T. Chen, H. Yin, X. Yuan, Y. Gu, F. Ren, and X. Sun, (2021) “Emotion recognition based on fusion of long short term memory networks and SVMs" Digital Signal Processing: A Review Journal 117: DOI: 10.1016/j.dsp.2021.103153.
  14. [14] J. Zhang, X. Chen, A. Khan, Y.-k. Zhang, X. Kuang, X. Liang, M. L. Taccari, and J. Nuttall, (2021) “Daily runoff forecasting by deep recursive neural network" Journal of Hydrology 596: DOI: 10.1016/j.jhydrol.2021.126067.
  15. [15] M. M. Morgan, I. Bhattacharya, R. J. Radke, and J. Braasch, (2021) “Classifying the emotional speech content of participants in group meetings using convolutional long short-term memory network" Journal of the Acoustical Society of America 149(2): 885–894. DOI: 10.1121/10.0003433.
  16. [16] D. Huang, X. Feng, H. Zhang, Z. Yu, J. Peng, G. Zhao, and Z. Xia, (2021) “Spatio-Temporal Pain Estimation Network with Measuring Pseudo Heart Rate Gain" IEEE Transactions on Multimedia:
  17. [17] D. Huang, Z. Xia, J. Mwesigye, and X. Feng, (2020) “Pain-attentive network: a deep spatio-temporal attention model for pain estimation" Multimedia Tools and Applications 79(37-38): 28329–28354. DOI: 10.1007/s11042-020-09397-1.
  18. [18] M. Arora, S. Garg, and A. Srivani, (2021) “Face mask detection system using Mobilenetv2" International Journal of Engineering and Advanced Technology 10(4): 127–129.
  19. [19] C. Tan, M. Šarlija, and N. Kasabov, (2021) “NeuroSense: Short-term emotion recognition and understanding based on spiking neural network modelling of spatiotemporal EEG patterns" Neurocomputing 434: 137–148. DOI: 10.1016/j.neucom.2020.12.098.
  20. [20] K. Zaporojets, G. Bekoulis, J. Deleu, T. Demeester, and C. Develder, (2021) “Solving arithmetic word problems by scoring equations with recursive neural networks" Expert Systems with Applications 174: DOI: 10.1016/j.eswa.2021.114704.
  21. [21] A. Jisi and S. Yin, (2021) “A new feature fusion network for student behavior recognition in education" Journal of Applied Science and Engineering (Taiwan) 24(2): 133–140. DOI: 10.6180/jase.202104_24(2).0002.
  22. [22] H. Dong and S.-B. Tsai, (2021) “An Empirical Study on Application of Machine Learning and Neural Network in English Learning" Mathematical Problems in Engineering 2021: DOI: 10.1155/2021/8444858.
  23. [23] X. Ma, J. Guo, A. Sansom, M. McGuire, A. Kalaani, Q. Chen, S. Tang, Q. Yang, and S. Fu, (2021) “Spatial Pyramid Attention for Deep Convolutional Neural Networks" IEEE Transactions on Multimedia 23: 3048–3058. DOI: 10.1109/TMM.2021.3068576.
  24. [24] S.-H.Wang, S. Fernandes, Z. Zhu, and Y.-D. Zhang, (2021) “AVNC: Attention-based VGG-style network for COVID-19 diagnosis by CBAM" IEEE Sensors Journal: DOI: 10.1109/JSEN.2021.3062442.
  25. [25] D. Liu, L. Shan, L. Wang, S. Yin, H. Wang, and C. Wang, (2021) “P3OI-MELSH: Privacy Protection Target Point of Interest Recommendation Algorithm Based on Multi-Exploring Locality Sensitive Hashing" Frontiers in Neurorobotics 15: DOI: 10.3389/fnbot.2021.660304.
  26. [26] Y. DONG, H. SU, and B. e. a. LIU, (2021) “Model level fusion dimension emotion recognition method based on Transformer" Journal of Signal Processing 37(5): 885–892. DOI: 10.16798/j.issn.10030530.2021.05.023.


42nd percentile
Powered by  Scopus

SCImago Journal & Country Rank

Enter your name and email below to receive latest published articles in Journal of Applied Science and Engineering.