The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis
Open accessAbstract
Multimodal sentiment analysis is an important research area that predicts speaker’s sentiment tendency through features extracted from textual, visual and acoustic modalities. The central challenge is the fusion method of the multimodal information. A variety of fusion methods have been proposed, but few of them adopt end-to-end translation models to mine the subtle correlation between modalities. Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis. We assume that translation between modalities contributes to a better joint representation of speaker’s utterance. With Transformer, the learned features embody the information both from the source modality and the target modality. We validate our model on multiple multimodal datasets: CMU-MOSI, MELD, IEMOCAP. The experiments show that our proposed method achieves the state-of-the-art performance.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The recent cross-modality sequential translation-based methods proposed in (Pham et al., 2019; Wang et al., 2020) learn the joint multimodal representations via translating a source modality to multiple target modalities, which improves the performance of the source modality as input at the test time.”
From Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities (2021) · cites this paper as Wang et al., 2020
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Motivated by the residual skip connection network [8], all encoded features are concatenated to obtain the nal joint features Fi which embodies information from all modalities available.”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 3×
“Most approaches focused on textual materials and used CNN [11, 12] or RNN [1, 4, 9, 15] to deal with the task. ese approaches achieve some progress in this area and provide experience and inspiration for later research.”
MethodHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 3×
“Most approaches focused on textual materials and used CNN [11, 12] or RNN [1, 4, 9, 15] to deal with the task. ese approaches achieve some progress in this area and provide experience and inspiration for later research.”
MethodConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 3×
“Most approaches focused on textual materials and used CNN [11, 12] or RNN [1, 4, 9, 15] to deal with the task. ese approaches achieve some progress in this area and provide experience and inspiration for later research.”
MethodEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 1×
“Most approaches focused on textual materials and used CNN [11, 12] or RNN [1, 4, 9, 15] to deal with the task.”
MethodMining and summarizing customer reviews
Hu, M., & Liu, B. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014073 · Cited by 7,793 · cited 1×
“Most traditional methods are based on texts [10, 14, 18], since textural materials are easy to get.”
MethodIEMOCAP: 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
Sentiment Analysis and Opinion Mining
Liu, B. (2012) · Synthesis Lectures on Human Language Technologies · doi:10.1007/978-3-031-02145-9 · Cited by 3,281 · cited 1×
“Most traditional methods are based on texts [10, 14, 18], since textural materials are easy to get.”
MethodOpensmile: the munich versatile and fast open-source audio feature extractor
Eyben, F., Wöllmer, M., & Schuller, B. (2010) · Proceedings of the 18th ACM international conference on Multimedia · doi:10.1145/1873951.1874246 · Cited by 2,642 · cited 1×
“ese features are pre-trained through CNN, 3D-CNN and openSMILE [6] for textual, visual and acoustic features, respectively.”
MethodTensor Fusion Network for Multimodal Sentiment Analysis
Zadeh, A., Chen, M., Poria, S., Cambria, E., & Morency, L.-P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1115 · Cited by 2,102 · cited 1×
“[24] explicitly models the unimodal, bimodal and trimodal interactions using a 3-fold Cartesian product from modality embeddings to create a new joint feature.”
Method
Research works printed but not linked: 4
- Zheng Lian Ya Li Jianhua Tao and Jian Huang. 2018. Investigation of Multimodal Features Classifiers and Fusion Methods for Emotion Recognition. arXiv preprint arXiv:1809.06225(2018). Zheng Lian Ya Li Jianhua Tao and Jian Huang. 2018. Investigation of Multimodal Features Classifiers and Fusion Methods for Emotion Recognition. arXiv preprint arXiv:1809.06225(2018). · arXiv
- Pengfei Liu Xipeng Qiu and Xuanjing Huang. 2016. Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101(2016). Pengfei Liu Xipeng Qiu and Xuanjing Huang. 2016. Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101(2016). · arXiv
- Saif M Mohammad Svetlana Kiritchenko and Xiaodan Zhu. 2013. NRC-Canada: Building the state-of-the-art in sentiment analysis of tweets. arXiv preprint arXiv:1308.6242(2013). Saif M Mohammad Svetlana Kiritchenko and Xiaodan Zhu. 2013. NRC-Canada: Building the state-of-the-art in sentiment analysis of tweets. arXiv preprint arXiv:1308.6242(2013). · arXiv
- Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Łukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998–6008. Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Łukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998–6008.
Cited by
Zhang, S., Yang, Y., Chen, C., Zhang, X., Leng, Q., & Zhao, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121692 · Cited by 251
Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities
Zhao, J., Li, R., & Jin, Q. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.203 · Cited by 275
“The recent cross-modality sequential translation-based methods proposed in (Pham et al., 2019; Wang et al., 2020) learn the joint multimodal representations via translating a source modality to multiple target modalities, which improves the performance of the source modality as input at the test…”
BackgroundMethodInfluentialMulti-source information fusion: Progress and future
LI, X., DUNKIN, F., & DEZERT, J. (2024) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2023.12.009 · Cited by 204
“For sentiment analysis tasks, Wang et al. 129 introduced a novel fusion method called TransModality based on Transformer.”
MethodA 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
CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation
Sun, H., Wang, H., Liu, J., Chen, Y.-W., & Lin, L. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3548025 · Cited by 162
“With the significant progress of Transformer [34] in natural language processing and computer vision, some works [4, 11, 35] applied its self-attention mechanism to perform modality interactions.”
BackgroundMethod
Metadata
- Authors
- Wang, Z., Wan, Z., & Wan, X.
- Affiliations
- Peking University (CN)
- Venue
- Proceedings of The Web Conference 2020
- Publisher
- ACM
- Published
- 2020-04-20
- Pages
- 2514-2520
- OpenAlex
- W3012721484
- Cited by
- 156
- References
- 17
- Citations by year
- 2026: 17 · 2025: 24 · 2024: 40 · 2023: 32 · 2022: 30 · 2021: 11 · 2020: 2
- FWCI
- 7.16
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International World Wide Web Conference (WWW) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- multimodal sentiment analysis, multimodal fusion, end-to-end fusion, transformer models, cross-modal translation, joint representation learning
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis. https://app.cochat.ai/papers/10.1145/3366423.3380000
- The paper
- Wang, Z., Wan, Z., & Wan, X. (2020). TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis. Proceedings of The Web Conference 2020. https://doi.org/10.1145/3366423.3380000
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.