A Review on Explainability in Multimodal Deep Neural Nets
Open accessThe DOI matches its Crossref record; 268 of the 268 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence techniques powered by deep neural nets have achieved much success in several application domains, most significantly and notably in the Computer Vision applications and Natural Language Processing tasks. Surpassing human-level performance propelled the research in the applications where different modalities amongst language, vision, sensory, text play an important role in accurate predictions and identification. Several multimodal fusion methods employing deep learning models are proposed in the literature. Despite their outstanding performance, the complex, opaque and black-box nature of the deep neural nets limits their social acceptance and usability. This has given rise to the quest for model interpretability and explainability, more so in the complex tasks involving multimodal AI methods. This paper extensively reviews the present literature to present a comprehensive survey and commentary on the explainability in multimodal deep neural nets, especially for the vision and language tasks. Several topics on multimodal AI and its applications for generic domains have been covered in this paper, including the significance, datasets, fundamental building blocks of the methods and techniques, challenges, applications, and future trends in this domain.
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
“The black box and opaque nature of deep neural networks precludes their usefulness despite excellent performance of multimodal methods [288].”
From Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks (2023) · cites this paper as [288]
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
“AI systems can profit significantly from assimilating multimodal data into prediction and classification models to imitate integrative human clinical decision-making.”
From Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging (2024) · cites this paper as [17]
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
“This can boost their robustness and accuracy, enable the discovery of new biomarkers and therapeutic targets6,14, as well as improve model performance15–17.”
From Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging (2024) · cites this paper as [17]
Experimental — accuracy not yet measured
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“[165] Attention Mechanism Focuses and attends the regions that are important for making”
BackgroundHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“BERT Transformer (B2T2) [98], UnicodeText Unidirectional long short term memory(LSTM)[104], Bidirectional LSTM (BiLSTM), Unidirectional Gated Recurrent Units (GRU)[105],bidirectional GRU (BiGRU) VL [99], VLBERT[100], UNITER [101], ViLBert [102], LXMERT [103]”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · cited 3×
“Individual conditional expectation (ICE) plot [145] visualize the dependence of features on the final prediction for unique data points, providing more insights than the PDP approach of averaging on all data points.”
BackgroundA Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 1×
“Shapley values [146] are used when each data point’s contribution is variable in the final prediction.”
MethodBLEU: 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 · cited 2×
“Automated evaluation metrics such as BLEU-4 [215] is used for automatic evaluation of machine translation that is”
Method"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 1×
“Deep learning-based explanatory systems are broadly classified into justification [17] or introspection-based systems [155], [165].”
Background
Research works printed but not linked: 13
- [179] J. Strout, Y. Zhang, and R. J. Mooney, 'Do Human Rationales Improve Machine Explanations?,' arXiv Prepr. arXiv1905.13714 , 2019. -
- [184] S. Vidya Sagar Appaji, P. V. Lakshmi, and P. Srinivasa Rao, 'Maximizing joint probability in visual question answering models,' Int. J. Adv. Sci. Technol. , vol. 29, no. 3, pp. 39143923, 2020. -
- [84] T. Showcases, 'Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion :' -
- [206] J. Lin, U. Jain, and A. G. Schwing, 'TAB-VCR: Tags and attributes based VCR baselines,' arXiv , no. NeurIPS, 2019. -
- [100] W. Su et al. , 'VL-BERT: Pre-training of generic visuallinguistic representations,' arXiv , pp. 1-16, 2019. -
- [199] D. Braines and D. Harborne, 'Multimodal Explanations for AIbased Multisensor Fusion,' pp. 1-13. -
- tharwat, 2020, Appl Comput Inform
- [219] M. ul Hassan, P. Mulhem, D. Pellerin, and G. Quénot, 'Explaining Visual Classification using Attributes,' in 2019 International Conference on Content-Based Multimedia Indexing (CBMI) , 2019, pp. 1-6. -
- [230] U. E. Ai, 'Can we do better explanations ? A proposal of.' -
- [232] P. Welinder, S. Branson, T. Mita, C. Wah, and F. Schroff, 'Caltech-ucsd Birds 200,' Caltech-UCSD Tech. Rep. , vol. 200, pp. 1-15, 2010, [Online]. Available: http://www.flickr.com/. -
- [236] V. Sharma, A. Kalra, S. Chaudhary, L. Patel, and L. P. Morency, 'Attend and Attack : Attention Guided Adversarial Attacks on Visual Question Answering Models,' 32nd Conf. Neural Inf. Process. Syst. , no. NeurIPS, pp. 1-6, 2018. -
- [142] O. Biran and C. Cotton, 'Explanation and justification in 18. machine learning: A survey,' in IJCAI-17 workshop on explainable AI (XAI) , 2017, vol. 8, no. 1, pp. 8-13. -
- [112] D. Kiela, E. Grave, A. Joulin, and T. Mikolov, 'Efficient largescale multi-modal classification,' 32nd AAAI Conf. Artif. Intell. AAAI 2018 , pp. 5198-5204, 2018. -
Cited by
Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities
Saeed, W., & Omlin, C. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110273 · Cited by 783
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590
“Some surveys discuss evaluation as part of a broader review of XAI methods [1, 29, 32, 59, 81, 120, 170, 173, 175, 182, 303], or mainly discuss evaluation with user studies [52, 100, 136, 170].”
BackgroundA., S., & R., S. (2023) · Decision Analytics Journal · doi:10.1016/j.dajour.2023.100230 · Cited by 432
ŞAHiN, E., Arslan, N. N., & Özdemir, D. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 278
Nazir, S., Dickson, D. M., & Akram, M. U. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106668 · Cited by 283
“The black box and opaque nature of deep neural networks precludes their usefulness despite excellent performance of multimodal methods [288].”
BackgroundTowards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
Rong, Y., Leemann, T., Nguyen, T.-T., Fiedler, L., Qian, P., Unhelkar, V., Seidel, T., Kasneci, G., & Kasneci, E. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3331846 · Cited by 278
“For instance, [136, 137, 138] investigate explanations for Deep Neural Networks (DNNs), where models often take images as input [136, 137].”
BackgroundLarge language models in law: A survey
Lai, J., Gan, W., Wu, J., Qi, Z., & Yu, P. S. (2024) · AI Open · doi:10.1016/j.aiopen.2024.09.002 · Cited by 362
Review of multimodal machine learning approaches in healthcare
Krones, F., Marikkar, U., Parsons, G., Szmul, A., & Mahdi, A. (2025) · Information Fusion · doi:10.1016/j.inffus.2024.102690 · Cited by 235
Rahate, A., Walambe, R., Ramanna, S., & Kotecha, K. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.12.003 · Cited by 214
“Multimodal explainability, challenges, methods to achieve explainability, datasets, and tools are covered in [132].”
BackgroundMethodInfluentialSelf-citationExplainable AI for Medical Data: Current Methods, Limitations, and Future Directions
Hossain, M. I., Zamzmi, G., Mouton, P. R., Salekin, M. S., Sun, Y., & Goldgof, D. B. (2025) · ACM Computing Surveys · doi:10.1145/3637487 · Cited by 185
“” Hence, explainability or interpretability can be defined as the additional information to reason the decision process, feature relevance, or identifying influential features generated by the ML model itself or another algorithm.”
Explainable Artificial Intelligence for Tabular Data: A Survey
Sahakyan, M., Aung, Z., & Rahwan, T. (2021) · IEEE Access · doi:10.1109/access.2021.3116481 · Cited by 135
“Several applications of multimodal AI were proposed in the literature [215], [216], but despite their outstanding performance, there is a lack of social acceptance due to their black-box nature [217].”
BackgroundAdvancing 6G: Survey for Explainable AI on Communications and Network Slicing
Sun, H., Liu, Y., Al-Tahmeesschi, A., Nag, A., Soleimanpour-Moghadam, M., Canberk, B., Arslan, H., & Ahmadi, H. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3534626 · Cited by 158
“Achieving this objective involves challenges such as effectively handling heterogeneous data within a unified framework and the need for advanced algorithms and computational capabilities for cross-domain data fusion [219], [224], [225].”
Deep leaning in food safety and authenticity detection: An integrative review and future prospects
Wang, Y., Gu, H., Yin, X., Geng, T., Long, W., Fu, H., & She, Y. (2024) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2024.104396 · Cited by 126
Toward Trustworthy Artificial Intelligence (TAI) in the Context of Explainability and Robustness
chander, B., John, C., Warrier, L., & Gopalakrishnan, K. (2025) · ACM Computing Surveys · doi:10.1145/3675392 · Cited by 108
“…privacy challenges is essential to build long-term successive AI applications because an appropriate balance among technological innovations and privacy considerations will march towards the development of socially responsible AI that can assist in creating public value in the long term.”
Rodis, N., Sardianos, C., Grammatikis, P. I. R., Sarigiannidis, P. G., Varlamis, I., & Papadopoulos, G. T. (2024) · IEEE Access · doi:10.1109/access.2024.3467062 · Cited by 123
“Aiming at systematically analyzing the MXAI literature, an initial categorization can be made based on the classes of methods that have been widely adopted for the unimodal XAI case [94, 9, 8, 7, 95, 17].”
BackgroundMethodInfluentialAn overview of large AI models and their applications
Tu, X., He, Z., Huang, Y., Zhang, Z., Yang, M., & Zhao, J. C. (2024) · Visual Intelligence · doi:10.1007/s44267-024-00065-8 · Cited by 134
“These models often exhibit high complexity, making it difficult to explain their internal decision-making processes and feature representation [140].”
A systematic review of intermediate fusion in multimodal deep learning for biomedical applications
Guarrasi, V., Aksu, F., Caruso, C. M., Di Feola, F., Rofena, A., Ruffini, F., & Soda, P. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105509 · Cited by 95
Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production
Verdone, A., Scardapane, S., & Panella, M. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.122151 · Cited by 112
Pahud de Mortanges, A., Luo, H., Shu, S. Z., Kamath, A., Suter, Y., Shelan, M., Pöllinger, A., & Reyes, M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01190-w · Cited by 93
“Thiscanboosttheirrobustnessand accuracy,enablethediscoveryofnewbiomarkersandtherapeutictargets 6,14 , as well as improve model performance 15 – 17 .”
Explainable AI: A review of applications to neuroimaging data
Farahani, F. V., Fiok, K., Lahijanian, B., Karwowski, W., & Douglas, P. K. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.906290 · Cited by 98
Tactile-Sensing Technologies: Trends, Challenges and Outlook in Agri-Food Manipulation
Mandil, W., Rajendran, V., Nazari, K., & E., A. M. G. (2023) · Sensors · doi:10.3390/s23177362 · Cited by 106
Toward Explainable Affective Computing: A Review
Cortiñas-Lorenzo, K., & Lacey, G. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3270027 · Cited by 112
“Several surveys exist covering recent advances in affective computing [5], [6], explainable AI (XAI) [35], [36], [37], [38], [39], and multimodal learning [29], [40].”
BackgroundBhatt, P. R., Sethi, A., Tasgaonkar, V., Shroff, J., Pendharkar, I., Desai, A., Sinha, P., Deshpande, A., Joshi, G., Rahate, A., et al. (2023) · Brain Informatics · doi:10.1186/s40708-023-00196-6 · Cited by 96
“However, they pose certain challenges like missing modalities [88], lack of multimodal datasets, multimodal explain-ability [89], the robustness of multimodal applications [90], etc.”
BackgroundSelf-citationAn evolutionary explainable deep learning approach for Alzheimer's MRI classification
Shojaei, S., Abadeh, M. S., & Momeni, Z. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119709 · Cited by 92
“From another perspective, Visualization methods can be divided into Perturbation and Backpropagation methods (Joshi et al., 2021).”
Employing Multimodal Machine Learning for Stress Detection
Walambe, R. A., Nayak, P., Bhardwaj, A., & Kotecha, K. V. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/9356452 · Cited by 86
“Furthermore, using the power of artificial intelligence in healthcare that goes beyond our supervision will go a long way [46].”
BackgroundSelf-citationRetractedROULETTE: A neural attention multi-output model for explainable Network Intrusion Detection
Andresini, G., Appice, A., Caforio, F. P., Malerba, D., & Vessio, G. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117144 · Cited by 78
HEROHE Challenge: Predicting HER2 Status in Breast Cancer from Hematoxylin–Eosin Whole-Slide Imaging
Conde‐Sousa, E., Vale, J., Feng, M., Xu, K., Wang, Y., Mea, V. D., Barbera, D. L., Montahaei, E., Baghshah, M. S., Turzynski, A., et al. (2022) · Journal of Imaging · doi:10.3390/jimaging8080213 · Cited by 70
“Unfortunately, although deep-learning networks perform better than humans in several domains, the complex and opaque black box nature of these networks limits its interpretability [63,64].”
BackgroundExplainable Misinformation Detection Across Multiple Social Media Platforms
Joshi, G., Srivastava, A., Yagnik, B., Hasan, M. M., Saiyed, Z., Gabralla, L. A., Abraham, A., Walambe, R. A., & Kotecha, K. V. (2023) · IEEE Access · doi:10.1109/access.2023.3251892 · Cited by 74
Self-citationSurvey on multimodal approaches to emotion recognition
Aruna Gladys, A., & Vetriselvi, V. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126693 · Cited by 82
Industrial Expert Systems Review: A Comprehensive Analysis of Typical Applications
Yang, X., & Zhu, C. (2024) · IEEE Access · doi:10.1109/access.2024.3419047 · Cited by 70
“To overcome these issues, researchers are delving into the interpretability of neural networks, aiming to provide more insights into their decision-making processes while maintaining performance [31], [32].”
BackgroundKaddoura, S., & Gumaei, A. (2022) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2022.200153 · Cited by 77
El–Sappagh, S., Alonso, J. M., Abuhmed, T., Ali, F., & Bugarín, A. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10415-5 · Cited by 70
Chen, J., Seng, K. P., Smith, J. S., & Ang, L.-M. (2024) · IEEE Access · doi:10.1109/access.2024.3416370 · Cited by 72
“…to interpreting unimodal modalities in multimodal systems, such as the use of Grad-CAM in vision to achieve attention-based interpretation, interpreting the complementarities between different modalities can help to understand the mechanisms of multimodal enhancement of system performance [156].”
BackgroundA Multiscale Graph Convolutional Neural Network Framework for Fault Diagnosis of Rolling Bearing
Yin, P., Nie, J., Liang, X., Yu, S., Wang, C., Nie, W., & Ding, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3291768 · Cited by 68
“Convolutional neural networks (CNNs) [7], deep neural networks (DNNs) [12], and recurrent neural networks (RNNs) [2] are widely used.”
BackgroundMMTFN : Multi‐modal multi‐scale transformer fusion network for Alzheimer's disease diagnosis
Miao, S., Xu, Q., Li, W., Yang, C., Sheng, B., Liu, F., Bezabih, T. T., & Xiao, Y. (2023) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22970 · Cited by 55
“12 Multi-modal fusion learning methods have been used by many scholars in the field of imaging.”
Al‐qaness, M. A. A., Helmi, A. M., Dahou, A., & Elaziz, M. A. (2022) · Biosensors · doi:10.3390/bios12100821 · Cited by 55
“Deep learning models have been widely utilized in different fields [32] including HAR and fall detection.”
MethodRajendran, S., Pan, W., Sabuncu, M. R., Chen, Y., Zhou, J., & Wang, F. (2024) · Patterns · doi:10.1016/j.patter.2023.100913 · Cited by 47
“107 Simple approaches that have seen some success involve treating each modality separately when determining the post hoc interpretability of the modality.”
BackgroundTAI-PRM: trustworthy AI—project risk management framework towards Industry 5.0
Vyhmeister, E., & Castañé, G. G. (2024) · AI and Ethics · doi:10.1007/s43681-023-00417-y · Cited by 49
“However, specific cases can require detailed processes [28, 37, 48].”
Explainability and vision foundation models: A survey
Kazmierczak, R., Berthier, É., Frehse, G., & Franchi, G. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103184 · Cited by 61
Alsharif, A. H., Wang, J., Isa, S. M., Salleh, N. Z. M., Dawas, H. A., & Alsharif, M. H. (2025) · Future Business Journal · doi:10.1186/s43093-025-00591-x · Cited by 50
“Processing sensitive data with AI models brings implications for data security, consent, and potential biases, amplifying existing inequalities [179].”
Deep Learning Approaches to Image Texture Analysis in Material Processing
Liu, X., & Aldrich, C. (2022) · Metals · doi:10.3390/met12020355 · Cited by 45
A novel EEG-based major depressive disorder detection framework with two-stage feature selection
Li, Y., Shen, Y., Fan, X., Huang, X., Yu, H., Zhao, G., & Ma, W. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-01956-w · Cited by 49
“Furthermore, we will consider using interpretable deep learning models [52] to improve the interpretability of our framework, to better assist clinical diagnosis.”
MethodReal-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies
Manssor, S. A. F., Sun, S., & Elhassan, M. A. M. (2021) · Sensors · doi:10.3390/s21134323 · Cited by 44
“Surpassing human-level performance propelled the research in applications where different modalities amongst language, vision, sensory, text play an essential role inaccurate predictions and identification [45].”
BackgroundThe Usefulness of Gradient-Weighted CAM in Assisting Medical Diagnoses
Chien, J.-C., Lee, J.-D., Hu, C.-S., & Wu, C. (2022) · Applied Sciences · doi:10.3390/app12157748 · Cited by 39
“Among these, the most promising approaches seek to provide some form of visual heat-maps with higher intensity values around the input image regions containing important features and information that the CNN network used in determining its results [8,9].”
BackgroundRequirements for Explainability and Acceptance of Artificial Intelligence in Collaborative Work
Theis, S., Jentzsch, S. F., Deligiannaki, F., Berro, C., Raulf, A., & Bruder, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35891-3_22 · Cited by 47
Review of stance detection for rumor verification in social media
Alsaif, H. F., & Al-Dossari, H. Z. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105801 · Cited by 39
Meas, M., Machlev, R., Köse, A., Tepljakov, A., Loo, L., Levron, Y., Petlenkov, E., & Belikov, J. (2022) · Sensors · doi:10.3390/s22176338 · Cited by 39
Multi-Modal Biometric Authentication: Leveraging Shared Layer Architectures for Enhanced Security
Vatchala, S., Yogesh, C. K., Govindarajan, Y., Raja, M., Ganesan, V. P. A., Arul, A. V., & Ramesh, D. (2025) · IEEE Access · doi:10.1109/access.2025.3534223 · Cited by 39
“…Advancements in multimodal systems also include novel approaches for target tracking using deep learning-aided algorithms that minimize response delays in multimodal systems [16], and a deep reinforcement learning method for action recognition, which optimizes fusion weights dynamically [10].”
BackgroundMultimodal explainability via latent shift applied to COVID-19 stratification
Guarrasi, V., Tronchin, L., Albano, D., Faiella, E., Fazzini, D., Santucci, D., & Soda, P. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110825 · Cited by 31
“The only available review on MXAI [23] surveys its applications in computer vision and natural language processing, showing that MXAI lacks in the medical field.”
InfluentialTowards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
Palit, V., Pandey, R., Arora, A., & Liang, P. P. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00307 · Cited by 86
“[18] present a comprehensive survey of interpretability in multimodal machine learning until early 2021.”
BackgroundGuarrasi, V., & Soda, P. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106625 · Cited by 28
Wang, K., Hou, W., Hong, L., & Guo, J. (2025) · Electronics · doi:10.3390/electronics14030420 · Cited by 40
A Multi-Lingual Speech Recognition-Based Framework to Human-Drone Interaction
Choutri, K., Lagha, M., Meshoul, S., Batouche, M., Kacel, Y., & Mebarkia, N. (2022) · Electronics · doi:10.3390/electronics11121829 · Cited by 28
“Another component that might be included to explain the predictions produced by algorithms, as stated in [39], is the explainability of the settings.”
BackgroundMansouri, M. M., Attouri, K., & Refaat, S. S. (2025) · IEEE Access · doi:10.1109/access.2025.3602914 · Cited by 33
“Complex deep multimodal models are often regarded as ‘‘black boxes,’’ limiting user understanding of their decision processes and hampering acceptance by grid operators and energy stakeholders [132].”
Ali, F., Barukab, O., Gadicha, A. B., Patil, S., Alghushairy, O., & Sarhan, A. Y. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/2987407 · Cited by 27
Exploring deep learning approaches for video captioning: A comprehensive review
Yousif, A. J., & Al-Jammas, M. H. (2023) · e-Prime - Advances in Electrical Engineering Electronics and Energy · doi:10.1016/j.prime.2023.100372 · Cited by 35
Qiu, Z., Chen, X., Xie, D., Ren, Y., Wang, Y., Yang, Z., Guo, M., Song, Y., Guo, J., Feng, Y., et al. (2024) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2024.104797 · Cited by 29
Li, F., & Xu, J. (2025) · IEEE Access · doi:10.1109/access.2025.3552039 · Cited by 43
“Big data analytics might aid businesses extract meaningful insights from their data, enhance functional effectiveness, invent novel services and goods, and attain a competitive benefit in nowadays data-driven business world [20].”
A Survey on Safe Multi-Modal Learning Systems
Zhao, T., Zhang, L., Ma, Y., & Cheng, L. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671462 · Cited by 45
“One of the major challenges in this endeavor involves tackling the intricate interactions between different modalities.”
BackgroundExplainable Image Captioning to Identify Ergonomic Problems and Solutions for Construction Workers
Yong, G., Liu, M., & Lee, S. H. (2024) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-5744 · Cited by 25
Trust Management for Artificial Intelligence: A Standardization Perspective
Um, T., Kim, J., Lim, S., & Lee, G. M. (2022) · Applied Sciences · doi:10.3390/app12126022 · Cited by 25
Ghimire, A., Kakani, V., & Kim, H. (2023) · IEEE Access · doi:10.1109/access.2023.3278974 · Cited by 26
“Efficiently complementing heterogeneous modalities such as RGB and skeleton modality presents challenges, as mentioned by Joshi et al. [57].”
BackgroundWavFace: A Multimodal Transformer-Based Model for Depression Screening
Flores, R., Tlachac, M., Shrestha, A., & Rundensteiner, E. A. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3529348 · Cited by 28
“The most important challenges have been identi-fied [26], [27] as representation , alignment , and fusion . a) Representation: Good representation properties for mul-timodalities is important [28].”
Liu, Y., Li, P., Si, Y., & Ma, L. (2025) · Energies · doi:10.3390/en18184983 · Cited by 22
Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations
Oneaţă, D., & Cucu, H. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00504 · Cited by 36
Feature based analysis of thermal images for emotion recognition
Rooj, S., Routray, A., & Mandal, M. K. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105809 · Cited by 23
Zuo, Z., Mu, J., Li, W., Bu, Q., Mao, H., Zhang, X., Han, L., & Ni, J. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1094142 · Cited by 22
“Multimodal data fusion can be mainly divided into three main types: early fusion, late fusion and hybrid fusion (Bayoudh et al., 2021; Joshi et al., 2021; Zhang Y. et al., 2021).”
BackgroundManifestations of xenophobia in AI systems
Tomašev, N., Maynard, J. L., & Gabriel, I. (2024) · AI & Society · doi:10.1007/s00146-024-01893-4 · Cited by 25
“Notable advances have also been made in improving explainability of computer vision systems (Chefer et al. 2021), multimodal AI systems (Joshi et al. 2021), and concept discovery in super-human narrow AI systems (McGrath et al. 2022; Schut et al. 2023).”
Yang, H., Zhu, D., He, S., Xu, Z., Liu, Z., Zhang, W., & Cai, J. (2024) · Psychiatry Research · doi:10.1016/j.psychres.2024.115896 · Cited by 24
Khani, P., Moeinaddini, E., Abnavi, N. D., & Shahraki, A. (2024) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4970 · Cited by 31
“36 2.”
Exploiting Distance-Based Structures in Data Using an Explainable AI for Stock Picking
Thrun, M. C. (2022) · Information · doi:10.3390/info13020051 · Cited by 22
Principles of artificial intelligence in radiooncology
Huang, Y., Gomaa, A., Höfler, D., Schubert, P., Gaipl, U. S., Frey, B., Fietkau, R., Bert, C., & Putz, F. (2024) · Strahlentherapie und Onkologie · doi:10.1007/s00066-024-02272-0 · Cited by 22
Chen, R., Zhou, W., Hu, H., Fei, Z., Fei, M., & Zhou, H. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112372 · Cited by 20
Employing Co-Learning to Evaluate the Explainability of Multimodal Sentiment Analysis
Jain, D. K., Rahate, A., Joshi, G., Walambe, R. A., & Kotecha, K. V. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3176403 · Cited by 26
“Explainability for multimodal models is still an evolving field and not a widely addressed area with known challenges [3] in terms of lack of datasets with manual explanation anno-2329-924X tations, difference and variability in generated explanations, and unsuitability of currently available…”
BackgroundSelf-citationGupta, S., Saini, N., Kundu, S., & Das, D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_2 · Cited by 19
Rashid, H.-A., Kallakuri, U., & Mohsenin, T. (2024) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3595633 · Cited by 27
“Using slow or gradual fusion, several modalities can be integrated [17, 40].”
BackgroundAssessing deep learning: a work program for the humanities in the age of artificial intelligence
Segessenmann, J., Stadelmann, T., Davison, A., & Dürr, O. M. (2023) · AI and Ethics · doi:10.1007/s43681-023-00408-z · Cited by 24
Sotubadi, S. V., Pallissery, S. S., & Nguyen, V. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110141 · Cited by 21
Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-Modal Fake News Detection
Chen, J., Jia, C., Zheng, H., Chen, R., & Fu, C. (2023) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2023.3249290 · Cited by 17
“Unlike traditional unfair bias issues, Joshi et al. [56] summarized the modality bias.”
BackgroundAlzheimer’s disease diagnosis using genetic programming based on higher order spectra features
Nasrolahzadeh, M., Rahnamayan, S., & Haddadnia, J. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100225 · Cited by 24
Tertiary Review on Explainable Artificial Intelligence: Where Do We Stand?
van Mourik, F., Jutte, A., Berendse, S. E., Bukhsh, F. A., & Ahmed, F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030098 · Cited by 19
Editorial: Interpretable and explainable machine learning models in oncology
Hrinivich, W. T., Wang, T., & Wang, C. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1184428 · Cited by 16
“Finally, limited MEI poses challenges for investigators pursuing improved performance by hindering interpretation of factors impacting model accuracy and generalizability.”
BackgroundInfluentialIntrinsic explainability of multimodal learning for crop yield simulation
Najjar, H., Pathak, D., Nuske, M., & Dengel, A. R. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111003 · Cited by 21
Zhao, J., Shangguan, S., & Wang, Y. (2025) · Journal of Computer Assisted Learning · doi:10.1111/jcal.70110 · Cited by 14
Explainable Multimodal Learning in Remote Sensing: Challenges and Future Directions
Günther, A., Najjar, H., & Dengel, A. R. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3404596 · Cited by 14
“Aligning with the categorization in [7], we distinguish among early fusion (data-or feature-level fusion), late fusion (decision-level fusion), and hybrid fusion (intermediate or joint fusion).”
BackgroundMethodKumar, A., Salim, M. M., Camacho, D., & Park, J. H. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111379 · Cited by 15
COVID-19 respiratory sound analysis and classification using audio textures
Silva, L. R., Valadão, C., Lampier, L., Delisle-Rodríguez, D., Caldeira, E. M. D. O., Bastos-Filho, T., & Krishnan, S. (2022) · Frontiers in Signal Processing · doi:10.3389/frsip.2022.986293 · Cited by 13
“, 2021), and interpretable deep learning models (Joshi et al., 2021) to improve the interpretability and usability of our framework to help COVID-19 diagnosis.”
BackgroundA Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical ApplicationsPreprint
Guarrasi, V., Aksu, F., Caruso, C. M., Feola, F. D., Rofena, A., Ruffini, F., & Soda, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4952813 · Cited by 21
Empirical mode decomposition in clinical signal analysis: A systematic review
Yang, S., Wu, H., Liao, X., Lin, Y., & Chen, J.-J. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110566 · Cited by 12
Software bug prediction using graph neural networks and graph-based text representations
Siachos, I., Kanakaris, N., & Karacapilidis, N. I. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125290 · Cited by 15
Multi-modal AI for Ultra-Precision Agriculture
Ayanlade, T. T., Jones, S. E., der Laan, L. V., Chattopadhyay, S., Elango, D., Raigne, J., Saxena, A., Singh, A., Ganapathysubramanian, B., Singh, A. K., et al. (2024) · Studies in big data · doi:10.1007/978-981-97-7762-4_13 · Cited by 15
El–Sappagh, S., Nazih, W., Alharbi, M., & Abuhmed, T. (2025) · Journal of Disability Research · doi:10.57197/jdr-2024-0101 · Cited by 13
“…quantification and mitigation (Zhang et al., 2022a; Lofstrom et al., 2023; Mehdiyev et al., 2023), multimodal XAI fusion including time series data (Joshi et al., 2021; Rojat et al., 2021; Lucieri et al., 2022), semantic (ontology-based) XAI (Panigutti et al., 2020; Rožanec and Mladeni ć , 2021;…”
Luo, L., Wu, Y., Li, S., Li, F., Wang, X., & Wei, X. (2025) · Journal of Nursing Management · doi:10.1155/jonm/5578698 · Cited by 12
“With the advancement of machine learning techniques, particularly in complex models such as deep neural networks, a mounting concern arises regarding their less interpretability nature [47, 48].”
Ghosh, I., Sanyal, M. K., & Pamucar, D. S. (2022) · International Journal of Information Technology & Decision Making · doi:10.1142/s0219622022500602 · Cited by 11
Deep Learning-Based Education Decision Support System for Student E-learning Performance Prediction
Jakkaladiki, S. P., Janečková, M., Krunčík, J., Malý, F., & Otčenášková, T. (2023) · Scalable Computing Practice and Experience · doi:10.12694/scpe.v24i3.2188 · Cited by 15
“[10] proposed an automatic method for cheating detection in online exams by processing the students’ webcam images.”
MethodInterpretable multi-modal data integration
Osorio, D. (2022) · Nature Computational Science · doi:10.1038/s43588-021-00186-w · Cited by 11
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
“Therefore, such methods are often challenging to predict the survival of breast cancer patients effectively and accurately (Huang et al., 2019; Joshi et al., 2021; Tan et al., 2022).”
BackgroundOn the Robustness of Explanations of Deep Neural Network Models: A SurveyPreprint
Jyoti, A., Ganesh, K. B., Gayala, M., Tunuguntla, N. L., Kamath, S., & Balasubramanian, V. N. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.04780 · Cited by 15
“or for specific domains refer to: medical [115], embedded systems [117], multimodal [56], time series [90], cybersecurity [23], and tabular data [94].”
BackgroundNguyen, D.-P., Berg, P., Debbabi, B., Nguyen, T., Tran, V. D., Nguyen, H. Q., Dakpé, S., & Dao, T. T. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105832 · Cited by 9
Naser, M. Z. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100259 · Cited by 9
Metadata
- Authors
- Joshi, G., Walambe, R., & Kotecha, K.
- Affiliations
- Symbiosis International University (IN)
- Venue
- IEEE Access
- Published
- 2021
- Volume
- 9
- Pages
- 59800-59821
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3148438775
- Semantic Scholar
- 6bda005a727969356a012e177cd600e7fdf80c96
- Cited by
- 204
- References
- 261
- Citations by year
- 2026: 26 · 2025: 49 · 2024: 45 · 2023: 50 · 2022: 25 · 2021: 9
- FWCI
- 11.40
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- Ministry of Human Resource Development (MHRD) Scheme for Promotion of Academic and Research Collaboration (SPARC) of the Government of India (P104)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- explainability, multimodal deep neural networks, multimodal fusion, model interpretability, vision-language tasks, black-box models
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.