Multimodal Emotion Recognition With Transformer-Based Self Supervised Feature Fusion
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Emotion Recognition is a challenging research area given its complex nature, and humans express emotional cues across various modalities such as language, facial expressions, and speech. Representation and fusion of features are the most crucial tasks in multimodal emotion recognition research. Self Supervised Learning (SSL) has become a prominent and influential research direction in representation learning, where researchers have access to pre-trained SSL models that represent different data modalities. For the first time in the literature, we represent three input modalities of text, audio (speech), and vision with features extracted from independently pre-trained SSL models in this paper. Given the high dimensional nature of SSL features, we introduce a novel Transformers and Attention-based fusion mechanism that can combine multimodal SSL features and achieve state-of-the-art results for the task of multimodal emotion recognition. We benchmark and evaluate our work to show that our model is robust and outperforms the state-of-the-art models on four datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Picard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., & Fidler, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.11 · Cited by 2,264 · cited 1×
“The model consists of 355M parameters and has been pre-trained on large English-language text datasets [35].”
MethodMultimodal Transformer for Unaligned Multimodal Language Sequences
Tsai, Y.-H. H., Bai, S., Liang, P. P., Kolter, J. Z., Morency, L.-P., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1656 · Cited by 2,259 · cited 11×
“Since the dataset is not uniformly distributed among the classes, we followed prior work [4], [40], and only”
BackgroundMethodInfluentialVoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
Jing, L., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2992393 · Cited by 2,036
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
Bagher Zadeh, A., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1208 · Cited by 1,433 · cited 9×
“Since the dataset is not uniformly distributed the classes, we followed prior work [4], [40], and only used the four most frequent labels, which are Happy, Sad, Anger, and Excitement.”
BackgroundMethodInfluentialMELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., & Mihalcea, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1050 · Cited by 1,416 · cited 6×
“MELD [3] dataset has more than 12000 utterances from Friends television series.”
BackgroundMethodInfluentialwav2vec: Unsupervised Pre-Training for Speech Recognition
Schneider, S., Baevski, A., Collobert, R., & Auli, M. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1873 · Cited by 1,290
Revisiting Self-Supervised Visual Representation Learning
Kolesnikov, A., Zhai, X., & Beyer, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00202 · Cited by 675
Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning
Ng, H.-W., Nguyen, V. D., Vonikakis, V., & Winkler, S. (2015) · Proceedings of the 2015 ACM on International Conference on Multimodal Interaction · doi:10.1145/2818346.2830593 · Cited by 657 · cited 1×
“techniques [8]–[10] to extract features from pre-trained DL models.”
MethodSun, Z., Sarma, P., Sethares, W., & Liang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6431 · Cited by 410
MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · arXiv · doi:10.48550/arxiv.1606.06259 · Cited by 350
Release Strategies and the Social Impacts of Language Models
Solaiman, I., Brundage, M., Clark, J., Askell, A., Herbert-Voss, A., Wu, J., Radford, A., Krueger, G., Kim, J. W., Kreps, S., et al. (2019) · arXiv · doi:10.48550/arxiv.1908.09203 · Cited by 292 · cited 1×
“Recent literature describes how bigger SSL models consist of billions of parameters like GPT-2, GPT-3 [30]–[32] that outperform baseline models in different NLP tasks.”
BackgroundSelf-Supervised Learning for ECG-Based Emotion Recognition
Sarkar, P., & Etemad, A. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053985 · Cited by 146
Self-supervised learning of a facial attribute embedding from video
Wiles, O., Koepke, A. S., & Zisserman, A. (2018) · arXiv · doi:10.48550/arxiv.1808.06882 · Cited by 111 · cited 3×
“We used the pre-trained Fabnet [16] model to obtain embed-dings for each frame in the video that contained the speaker’s face.”
MethodPretrained AI Models: Performativity, Mobility, and Change
Varshney, L. R., Keskar, N. S., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.03290 · Cited by 20
Research works printed but not linked: 24
- 10.1109/ACCESS.2019.2926751 · DOI
- 10.18653/v1/N19-4009 · DOI · Paper page
- 10.1109/CVPR.2018.00973 · DOI · Paper page
- goodfellow, 2016, Deep Learning
- 10.1007/s10772-018-9491-z · DOI · Paper page
- 10.1016/j.patcog.2010.09.020 · DOI · Paper page
- 10.1109/ICASSP40776.2020.9052937 · DOI
- 10.3758/s13428-017-0996-1 · DOI · Paper page
- 10.1109/ICRA.2018.8462891 · DOI · Paper page
- 10.18653/v1/W18-3307 · DOI
- knyazev, 2017, Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video, arXiv 1711 04598
- ezzeldin, 2019, Transfer learning from sound representations for anger detection in speech, arXiv 1902 02120
- 10.3389/fcomp.2020.00009 · DOI
- nagarajan, 2018, Deep net features for complex emotion recognition, arXiv 1811 00003
- 10.1109/ACCESS.2020.2984368 · DOI · Paper page
- vaswani, 2017, Attention is all you need, Proc Adv Neural Inf Process Syst, 5998
- ekman, 1997, What the Face Reveals Basic and Applied Studies of Spontaneous Expression using the Facial Action Coding System (FACS)
- 10.1109/ICASSP.2014.6853739 · DOI · Paper page
- 10.3115/v1/D14-1162 · DOI · Paper page
- 10.1109/BigDataSecurity-HPSC-IDS.2019.00027 · DOI
- zadeh, 2018, Multi-attention recurrent network for human communication comprehension, Proc 32nd AAAI Conf Artif Intell, 5642
- 10.24963/ijcai.2019/755 · DOI
- deng, 2019, Retinaface: Single-stage dense face localisation in the wild, arXiv 1905 00641
- 10.18653/v1/D19-1015 · DOI · Paper page
Cited by
A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face
Lian, H., Lu, C., Li, S., Zhao, Y., Tang, C., & Zong, Y. (2023) · Entropy · doi:10.3390/e25101440 · Cited by 224
Emotion classification for short texts: an improved multi-label method
Liu, X., Shi, T., Zhou, G., Liu, M., Yin, Z., Yin, L., & Zheng, W. (2023) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-01816-6 · Cited by 175
Robust Multimodal Emotion Recognition from Conversation with Transformer-Based Crossmodality Fusion
Xie, B., Sidulova, M., & Park, C. H. (2021) · Sensors · doi:10.3390/s21144913 · Cited by 108
Singh, P., Tripathi, M. K., Patil, M. B., Shivendra, & Neelakantappa, M. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19171-2 · Cited by 38
State-of-the-art Multimodal Emotion Recognition: A comprehensive survey and taxonomy
Yazici, A., Kucukyilmaz, T., Dokeroglu, T., Sharipbay, A., Lee, M.-H., & Tyler, B. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200642 · Cited by 11
Metadata
- Authors
- Siriwardhana, S., Kaluarachchi, T., Billinghurst, M., & Nanayakkara, S.
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 176274-176285
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3088631780
- Cited by
- 158
- References
- 26
- FWCI
- 15.96
- Type
- journal article
- Language
- en
- Open access
- gold
- Funders
- Assistive Augmentation Research Grant through the Entrepreneurial Universities (EU) initiative of New Zealand
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.