Multimodal Machine Learning: A Survey and Taxonomy
Open accessThe DOI matches its Crossref record; 268 of the 281 references it cites were found in a registry or an index.
Abstract
Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors. Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities. In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together. Multimodal machine learning aims to build models that can process and relate information from multiple modalities. It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential. Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy. We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning. This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research.
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Early and late fusion have been the de-facto first-approach when tackling new multimodal problems.”
From MultiBench: Multiscale Benchmarks for Multimodal Representation Learning (2021) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the effective fusion of complementary modalities has been shown to improve model accuracy, robustness, and generalization, whereas suboptimal fusion strategies can lead to degraded performance, instability, and overfitting [6].”
From Benchmarking Multimodal Deep Fusion Strategies for Heterogeneous Neuroimaging and Cognitive Data Using a Controlled Sex Classification Task (2026) · cites this paper as [6]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent studies have proposed increasingly sophisticated fusion architectures, including attention-based models, variational autoencoders, and graph neural networks, often reporting improved predictive performance in complex biomedical and neuroimaging tasks [6,9,45,46,47].”
From Benchmarking Multimodal Deep Fusion Strategies for Heterogeneous Neuroimaging and Cognitive Data Using a Controlled Sex Classification Task (2026) · cites this paper as [6]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“multimodal data fusion—essential for integrating ultrasound, elastography, Doppler imaging, and metabolomics—is often superficial.”
From Placenta-pulmonary coupling-guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy (2026) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Convolutional neural networks (CNNs) enable basic feature concatenation but lack mechanisms for semantic alignment across heterogeneous data streams, limiting their ability to model spatiotemporal dynamics (11).”
From Placenta-pulmonary coupling-guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy (2026) · cites this paper as [11]
Experimental — accuracy not yet measured
8 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet 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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
Research works printed but not linked: 16
- [163] G. Potamianos, C. Neti, G. Gravier, A. Garg, and A. W. Senior, 'Recent advances in the automatic recognition of audio-visual speech,' Proceedings of the IEEE , 2003. -
- [175] A. Rohrbach, A. Torabi, M. Rohrbach, N. Tandon, C. Pal, H. Larochelle, A. Courville, and B. Schiele, 'Movie description,' International Journal of Computer Vision , 2017. -
- [60] S. Fidler, A. Sharma, and R. Urtasun, 'A Sentence is Worth a Thousand Pixels Holistic CRF model,' in CVPR , 2013. -
- [61] A. Frome, G. Corrado, and J. Shlens, 'DeViSE: A deep visualsemantic embedding model,' NIPS , 2013. -
- [90] N. Jaques, S. Taylor, A. Sano, and R. Picard, 'Multi-task , MultiKernel Learning for Estimating Individual Wellbeing,' in Multimodal Machine Learning Workshop in conjunction with NIPS , 2015. -
- [80] G. Hinton and R. S. Zemel, 'Autoencoders, minimum description length and Helmoltz free energy,' in NIPS , 1993. -
- [78] L. A. Hendricks, S. Venugopalan, M. Rohrbach, R. Mooney, K. Saenko, and T. Darrell, in CVPR , 2016. -
- [87] T.-H. K. Huang, F. Ferraro, N. Mostafazadeh, I. Misra, A. Agrawal, J. Devlin, R. Girshick, X. He, P. Kohli, D. Batra et al. , 'Visual storytelling.' NAACL, 2016. -
- [212] I. Vendrov, R. Kiros, S. Fidler, and R. Urtasun, 'OrderEmbeddings of Images and Language,' in ICLR , 2016.
- [220] W. Wang, R. Arora, K. Livescu, and J. Bilmes, 'On deep multiview representation learning,' in ICML , 2015.
- [215] --, 'Show and tell: A neural image caption generator,' in CVPR , 2015.
- [135] R. Mason and E. Charniak, 'Nonparametric Method for Datadriven Image Captioning,' in ACL , 2014. -
- [242] L. Yu, P. Poirson, S. Yang, A. C. Berg, and T. L. Berg, 'Modeling Context in Referring Expressions,' in ECCV , 2016.
- [105] R. Kiros, R. Salakhutdinov, and R. S. Zemel, 'Unifying VisualSemantic Embeddings with Multimodal Neural Language Models,' 2014. -
- [13] T. Baltruˇ saitis, N. Banda, and P. Robinson, 'Dimensional Affect Recognition using Continuous Conditional Random Fields,' in IEEE FG , 2013. -
- [17] L. W. Barsalou, 'Grounded cognition,' Annual review of psychology , 2008. -
Cited by
Items 1,001–1,036 of 1,036
Interpretable video-based tracking and quantification of Parkinsonism clinical motor states
Deng, D., Ostrem, J. L., Nguyen, V., Cummins, D. D., Sun, J., Pathak, A., Little, S., & Abbasi-Asl, R. (2024) · npj Parkinson's Disease · doi:10.1038/s41531-024-00742-x · Cited by 25
Transformer-based sensor fusion for autonomous vehicles: A comprehensive review
Abdulmaksoud, A., & Ahmed, R. (2025) · IEEE Access · doi:10.1109/access.2025.3545032 · Cited by 25
Quan, Z., Sun, T., Su, M., & Wei, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/4767437 · Cited by 25
PerturbNet predicts single-cell responses to unseen chemical and genetic perturbations
Yu, H., & Welch, J. D. (2022) · doi:10.1101/2022.07.20.500854 · Cited by 57
Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors
Lee, M. A., Tan, M., Zhu, Y., & Bohg, J. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561847 · Cited by 24
Multimodality in tourism and hospitality: a critical and narrative review
Yu, X., & Cheng, M. (2025) · Tourism Management · doi:10.1016/j.tourman.2025.105245 · Cited by 24
Audio description from image by modal translation network
Ning, H., Zheng, X., Yuan, Y., & Lu, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.10.053 · Cited by 23
Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment
Liang, P. P., Wu, P., Ziyin, L., Morency, L.-P., & Salakhutdinov, R. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475247 · Cited by 22
Self-citationDimitri, G. M. (2022) · Computers · doi:10.3390/computers11110163 · Cited by 22
Reducing annotation burden through multimodal learning
Lopez, K., Fodeh, S. J., Allam, A., Brandt, C. A., & Krauthammer, M. (2020) · Frontiers in Big Data · doi:10.3389/fdata.2020.00019 · Cited by 21
Beyond Text: Multimodal Credibility Assessment Approaches for Online User-Generated Content
Choudhary, M., Chouhan, S. S., & Rathore, S. S. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3673236 · Cited by 20
Modeling Uncertainty in Multi-Modal Fusion for Lung Cancer Survival Analysis
Wang, H., Subramanian, V., & Syeda-Mahmood, T. (2021) · 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9433823 · Cited by 26
Azher, Z. L., Suvarna, A., Chen, J.-Q., Zhang, Z., Christensen, B. C., Salas, L. A., Vaickus, L. J., & Levy, J. J. (2023) · BioData Mining · doi:10.1186/s13040-023-00338-w · Cited by 20
TS2ACT: Few-Shot Human Activity Sensing with Cross-Modal Co-Learning
Xia, K., Li, W., Gan, S., & Lu, S. (2023) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3631445 · Cited by 19
MRCA: metric-level root cause analysis for microservices via multi-modal data
Wang, Y., Zhu, Z., Fu, Q., Ma, Y., & He, P. (2024) · Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3691620.3695485 · Cited by 18
Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking
Akhtar, M., Cocarascu, O., & Simperl, E. (2023) · Findings of the Association for Computational Linguistics: EACL 2023 · doi:10.18653/v1/2023.findings-eacl.30 · Cited by 18
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511112 · Cited by 19
“Thus, it would be interesting to further explore whether the HM can support training a better ML model and achieve more efficient annotation after improving the technique of a multimodal machine learning [4] and fine-tuning the RB model.”
BackgroundMethodSharma, H., Drukker, L., Papageorghiou, A. T., & Noble, J. A. (2021) · 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9433863 · Cited by 15
Jiao, J., Sun, H., Huang, Y., Xia, M., Qiao, M., Ren, Y., Wang, Y., & Guo, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3278259 · Cited by 15
Beyond Medical Imaging - A Review of Multimodal Deep Learning in Radiology
Heiliger, L., Sekuboyina, A., Menze, B., Egger, J., & Kleesiek, J. (2022) · doi:10.36227/techrxiv.19103432 · Cited by 13
A Multi-Modal Fusion Method Based on Higher-Order Orthogonal Iteration Decomposition
Liu, F., Chen, J., Tan, W., & Cai, C. (2021) · Entropy · doi:10.3390/e23101349 · Cited by 13
Multimodal Fusion with Co-attention Mechanism
Li, P., & Li, X. (2020) · 2020 IEEE 23rd International Conference on Information Fusion (FUSION) · doi:10.23919/fusion45008.2020.9190483 · Cited by 14
Deep multi-modal fusion network with gated unit for breast cancer survival prediction
Yuan, H., & Xu, H. (2024) · Computer Methods in Biomechanics and Biomedical Engineering · doi:10.1080/10255842.2023.2211188 · Cited by 10
What BERT Sees: Cross-Modal Transfer for Visual Question Generation
Scialom, T., Bordes, P., Dray, P.-A., Staiano, J., & Gallinari, P. (2020) · Proceedings of the 13th International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.39 · Cited by 9
“Exercise difficulty prediction in online education systems,”
Fang, J., Zhao, W., & Jia, D. (2019) · 2019 International Conference on Data Mining Workshops (ICDMW) · doi:10.1109/icdmw.2019.00053 · Cited by 9
Multimodal Data Fusion based on the Global Workspace Theory
Bao, C., Fountas, Z., Olugbade, T., & Bianchi-Berthouze, N. (2020) · arXiv · doi:10.48550/arxiv.2001.09485 · Cited by 9
Vision to Language: Methods, Metrics and Datasets
Sharif, N., Nadeem, U., Shah, S. A. A., Bennamoun, M., & Liu, W. (2020) · Learning and Analytics in Intelligent Systems · doi:10.1007/978-3-030-49724-8_2 · Cited by 9
Unbiased Missing-Modality Multimodal Learning
Dai, R., Li, C., Yan, Y., Mo, L., Qin, K., & He, T. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02272 · Cited by 11
MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models
Liang, P. P., Lyu, Y., Chhablani, G., Jain, N., Deng, Z., Wang, X., Morency, L.-P., & Salakhutdinov, R. (2023) · Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544549.3585604 · Cited by 4
Self-citationLiang, C., Silva, R. F., Adali, T., Jiang, R., Zhang, D., Qi, S., & Calhoun, V. D. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3597045 · Cited by 3
“Increasing work has focused on combining functional and structural neuroimaging data to capture information hidden from a unimodal analysis [3], [4], [5].”
The role of multimodality in clinical disease diagnosis: advances, challenges, and opportunities
Nawaz, A., Edinat, A., Rana, M. R. R., Ali, T., Mustafa, G., Tahir, S., & Lee, S. W. (2026) · Frontiers in public health · doi:10.3389/fpubh.2026.1788454 · Cited by 3
Clustering of Temporal and Visual Data: Recent Advancements
Mudgal, P. (2026) · Data · doi:10.3390/data11010007 · Cited by 2
An adversarial scheme for integrating multi-modal data on protein function
(2025) · doi:10.1016/j.cels.2025.101444 · Cited by 2
Abi, R., & Adetunji, O. (2023) · International Journal of Medicine Sciences · doi:10.33545/26648881.2023.v5.i1a.69 · Cited by 2
Camastra, C., Pelagi, A., Quattrone, A., & Sarica, A. (2026) · Brain Sciences · doi:10.3390/brainsci16040405 · Cited by 1
Ma, B., Ran, J., Pan, T., Yan, F., Yue, Z., Yao, Y., Li, Y., & Nie, F. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1791481
Metadata
- Authors
- Baltrusaitis, T., Ahuja, C., & Morency, L.-P.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2019-02-01
- Volume
- 41
- Issue
- 2
- Pages
- 423-443
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W2619383789
- Cited by
- 5,018
- References
- 281
- Citations by year
- 2026: 1284 · 2025: 994 · 2024: 705 · 2023: 586 · 2022: 481 · 2021: 380 · 2020: 324 · 2019: 194
- FWCI
- 120.66
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Multisensory perception and integration
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- multimodal learning, multimodal fusion, feature-level fusion, decision fusion, representation learning, cross-modal translation, cross-modal alignment, co-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
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.