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
Items 101–200 of 222
Amel, O., Siebert, X., & Mahmoudi, S. A. (2024) · Electronics · doi:10.3390/electronics13122294 · Cited by 9
“The existing literature typically categorizes fusion into four distinct approaches: early, late, intermediate, and hybrid fusion [2,12].”
Taresh, M. M., Zhu, N., Ali, T. A. A., Alghaili, M., Hameed, A. S., & Mutar, M. L. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.694 · Cited by 8
ScrutinAI: A visual analytics tool supporting semantic assessments of object detection models
Haedecke, E., Möck, M., & Akila, M. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.06.010 · Cited by 13
IMAD: Image-Augmented Multi-Modal Dialogue
Moskvoretskii, V., Frolov, A., & Kuznetsov, D. (2024) · Journal of Mathematical Sciences · doi:10.1007/s10958-024-07434-0 · Cited by 9
“These problems are solved with multi-modal deep learning models, that are increasingly important today due to the exponential growth of multimedia data in various domains [19, 20, 21, 22].”
Chamara, N., Pan, Y., Taghvaeian, S., Walters, C., Proctor, C., Rudnick, D. R., Redfearn, D. D., Luck, J. D., & Ge, Y. (2026) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2026.03.008 · Cited by 8
Impact of Feature Encoding on Malware Classification Explainability
Manai, E., Mejri, M., & Fattahi, J. (2023) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai58194.2023.10193964 · Cited by 10
Skillful Short‐Term Forecasting of Clouds With a Cascade Diffusion Model
Chen, H., Zhong, X., Zhai, Q., Li, X., Chan, Y. W., Chan, P. W., Yang, M., Huang, Y., Li, H., & Shi, X. (2026) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2025jh000976 · Cited by 11
SRIF-RCNN: Sparsely represented inputs fusion of different sensors for 3D object detection
Li, X., & Kong, D. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03594-1 · Cited by 9
“To this end, Explanation AI (XAI) technique [74] should be further studied to explain the internal working mechanisms of AI models.”
Method“RNN-Driven Prognosis of Heart Disease Based on Health Parameters”
Rahi, P., Singh, I., Singh, A. P., & Kumar, A. (2024) · International Conference on Advanced Computing & Communication Technologies (ICACCTech) · doi:10.1109/icacctech65084.2024.00085 · Cited by 7
“Specificity and adaptability problems have to be resolved to guarantee RNN’s successful functioning with various kinds of populations [26].”
XAI-based Data Visualization in Multimodal Medical DataPreprint
Sharma, S., Singh, M., Mcdaid, L. J., & Bhattacharyya, S. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.11.664302 · Cited by 16
Guarrasi, V., Bertgren, A., Näslund, U., Wennberg, P., Soda, P., & Grönlund, C. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102617 · Cited by 6
Eckardt, J., Srivastava, I., Schulze, F., Winter, S., Schmittmann, T., Riechert, S., Schneider, M., Reichel, L., Gediga, M. E. H., Sockel, K., et al. (2025) · npj Precision Oncology · doi:10.1038/s41698-025-01222-y · Cited by 5
From imaging to omics: deep learning is bridging MRI and liquid biopsy in bone tumor diagnosis
Wang, F., Chen, J., Zheng, L., & Huang, X. (2026) · Journal of bone oncology · doi:10.1016/j.jbo.2026.100753 · Cited by 6
“” [ 273 – 275].”
Shrivastava, P., Tripathi, N., Dewangan, B., Singh, B., Choudhury, T., Kotecha, K., & Dewangan, S. (2023) · 2023 7th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit58785.2023.10304972 · Cited by 5
“Multimodal deep learning concepts also may be a good usage in the perspective of autonomic computing these days [48][49]. a. Distribution of records over the year For the period 2012 to 2022, the frequency of articles published each year was shown in Figure 4.”
BackgroundSelf-citationABIET: An explainable transformer for identifying functional groups in biological active molecules
Pereira, T., Abbasi, M., & Arrais, J. P. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109740 · Cited by 6
Jarmondi, K. D. S., Tarinejad, R., Pourali, H., Salehi, A. H., & Nourani, V. (2025) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2025.109237 · Cited by 6
Enhancing Trustworthiness in AI-Based Prognostics: A Comprehensive Review of Explainable AI for PHM
Nguyen, D. A., Nguyen, K. T. P., & Medjaher, K. (2024) · Springer series in reliability engineering · doi:10.1007/978-3-031-71495-5_6 · Cited by 8
Shen, Y., Luo, Z., Xu, M., Liang, Z., Fan, X., & Lu, X. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110461 · Cited by 6
Enhancing Explainability, Robustness, and Autonomy: A Comprehensive Approach in Trustworthy AI
Ahmed, M. U., Begum, S., Barua, S., Masud, A. N., Flumeri, G. D., & Navarin, N. (2025) · IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx) · doi:10.1109/citrex64975.2025.10974944 · Cited by 9
“Kulesza et al. [11] on interactive ML highlights the importance of user-centric design in explanation systems on interactive ML. Joshi et al. [12] explore multimodal approaches to explanation generation.”
Cross-modal consistency types in multimodal social data
Vaiani, L., Cagliero, L., Garza, P., & Ravagli, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113705 · Cited by 6
Ahmed, M. U., Barua, S., Begum, S., Jmoona, W., D’Cruze, R. S., Veyrié, A., Kebir, S., & Hurter, C. (2024) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3719384.3719389 · Cited by 10
“Joshi et al. (2021) explore multimodal approaches to explanation generation [26].”
Yang, F., Yu, B., Zhou, Y., Luo, X., Tu, Z., & Liu, C. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115186 · Cited by 6
Hybrid Neural Network Methods for the Detection of Credit Card Fraud
Al‐Khasawneh, M. A., Faheem, M., Alsekait, D. M., Abubakar, A., & Issa, G. F. (2025) · Security and Privacy · doi:10.1002/spy2.500 · Cited by 5
“The justification of adopting “Multimodal neural network” lies with the fact that it utilizes several sets of variables to analyses and identify more accurate and distinguishing patterns, resulting in notable benefits compared to current approaches in detecting instances of credit card fraud [11].”
Gupta, U. C., Pranav, A., Dubey, A., Modi, R. K., & Singh, A. (2025) · Springer eBooks · doi:10.1007/978-981-96-2355-6_15 · Cited by 5
Explainable AI in Military Training Applications
Khan, A., Jhanjhi, N. Z., Hamid, D. H. T. B. A. H., & Omar, H. A. H. B. H. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-6361-1.ch007 · Cited by 5
Jeon, G., Cho, C., Kim, K., & Choi, W. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103519 · Cited by 5
Chen, Y., Gunraj, H., Zeng, E. Z., Meyer, R., Gilles, M., & Wong, A. M. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00012 · Cited by 6
Advancement in CFD and Responsive AI to Examine Cardiovascular Pulsatile Flow in Arteries: A Review
Praharaj, P., Sonawane, C. R., & Bongale, A. M. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.056289 · Cited by 9
Hybrid Modeling Integrating Artificial Intelligence and Modeling & Simulation Paradigms
Tolk, A. (2024) · Winter Simulation Conference · doi:10.1109/wsc63780.2024.10838942 · Cited by 6
“But even overview articles on explainable approaches document that the approaches still fall short, particularly for users with domain expertise, but often with insufficient knowledge about how neural nets work(Samek et al. 2019; Joshi et al. 2021).”
Cross-Domain Adversarial Attacks and Robust Defense Mechanisms for Multimodal Neural Networks
Barach, J. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-83796-8_23 · Cited by 11
Explainable multimodal learning for predictive maintenance of steam generators
Nguyen, D. A., Jose, S., Nguyen, T. P. K., & Medjaher, K. (2023) · PHM Society Asia-Pacific Conference · doi:10.36001/phmap.2023.v4i1.3783 · Cited by 4
Muhitdinova, B., Abdullaev, R., Одилова, Г. К., Nigmatovna, T. S., Ne’matova, Y., Turdikulov, S., Makhkamova, N., & Sapaev, I. B. (2025) · Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications · doi:10.58346/jowua.2025.i1.035 · Cited by 4
Alalem, S., Zaghloul, M. S., & Badawy, O. M. (2023) · International Arab Conference on Information Technology (ACIT) · doi:10.1109/acit58888.2023.10453875 · Cited by 4
“This approach has the potential to provide a more comprehensive understanding of sentiment by combining information from different modalities [4].”
BackgroundNajm, A., Zakrani, A., & Marzak, A. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-7663-6_67 · Cited by 5
Explainable Machine Learning for Mental Health Detection Using NLP
Mushtaq, N. U. A., Narejo, S., Ali, S. A., & Jawaid, M. M. (2025) · ADCAIJ ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL · doi:10.14201/adcaij.32449 · Cited by 3
“In recent years, there has been significant growth in the development and deployment of explain-able AI (XAI), as noted by Joshi et al. (2021)”
Advancing adversarial and LLM robustness in trustworthy AI: a comprehensive survey
Tang, Q., Qian, J., Du, X., Wang, S., & Liu, H. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11558-x · Cited by 4
A survey on multimodal explainable Artificial Intelligence
Giovannoni, C., Metta, C., Monreale, A., & Rinzivillo, S. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200671 · Cited by 5
MoTIF: a Method for Trustworthy Dynamic Multimodal Learning on Omics
Lu, Y., Peng, R., Jiang, B., & Wang, J. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10386044 · Cited by 4
“Such insights enable more precise and comprehensive predictions [1], [2].”
BackgroundYuan, J., Wang, Q., Wang, J., Fan, Y., Jiao, W., & Li, A. (2024) · Electronics · doi:10.3390/electronics13234755 · Cited by 4
Martin, N., Nambayil, S. R., Devikrishna, U., Joel Jismon, P., & Fasila, K. A. (2024) · IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES) · doi:10.1109/spices62143.2024.10779815 · Cited by 4
Schlee, M., Kant, G., Ehrling, C., Säfken, B., & Kneib, T. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11188-9 · Cited by 3
“Finally, Attribute-based methods employ attributes for improved explanations and model understanding in visual reasoning tasks (Joshi et al. 2021 ).”
Vani, G., Kalyan, K., Karthik, R. N. V. S., Reddy, B. S., & Haritha, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-95540-2_16 · Cited by 3
Iqbal, M. T. B., Muqeet, A., & Bae, S. (2022) · IEEE Access · doi:10.1109/access.2022.3188394 · Cited by 5
“Lastly, such a visualization map can be utilized in various applications, such as, object localization, image captioning, visual question answering, knowledge distillation etc. (as also done in [9],[20], [29] and [43]), where we are yet to test the utility of our proposal.”
BackgroundPredicting the radiotherapeutic treatment response of non-small cell lung cancer
Das, S., Sasidharan, R., Ghosh, S., Chatterjee, S., Ray, S., Arunsingh, M. A., Bhattacharyya, T., & Mukherjee, J. (2022) · Computer Methods and Programs in Biomedicine Update · doi:10.1016/j.cmpbup.2022.100065 · Cited by 3
Investigation of Explainability Techniques for Multimodal Transformers
Ramesh, K., & Koh, Y. S. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-8746-5_7 · Cited by 3
Explainable Artificial Intelligence Techniques for Image Classification Models in Diverse Domains
Joshi, P. P., & Bagade, A. M. (2023) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea58933.2023.10392188 · Cited by 4
“…for these methods are discussed in terms of data representation format, data translation, and alignment, which is the procedure for locating a direct correlation between components from two or more distinct modes such as streaming video and its subtitles and audio-visual speech fusion [30].”
MethodQin, C. (2025) · Frontiers in Psychology · doi:10.3389/fpsyg.2025.1643076 · Cited by 2
“…student participation and ideological understanding in IPE, by means of a Transformer-based architecture paired with multimodal data processing and explainable AI techniques, the methodology provides instructors and students accurate forecasts and useful recommendations (Joshi et al., 2021).”
A coupled multi-task feature boosting method for remote sensing scene classification
Wang, T., Gu, Y., Gao, G., & Zeng, X. (2023) · Science China Technological Sciences · doi:10.1007/s11431-022-2187-8 · Cited by 2
“Massive research such as heatmap try to explain the deep features directly or indirectly, but they fail to improve the network by their explanation [27–29].”
BackgroundStar-Net: a Multi-Branch Convolutional Network for Multiple Source Image Segmentation
Placidi, G., Cinque, L., Nappi, M., Polsinelli, M., Sciarra, A., & Tortora, G. (2022) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis57111.2022.00034 · Cited by 3
“It is worth saying that the strategy used for the fusion is strongly task-dependent [6]–[8].”
BackgroundElectronic Equipment Waste Generated by Computers and its Effect on Public Health in India
Dewangan, S., Mundeja, P., Deshpande, B., Dewangan, B. K., Choudhury, T., & Kotecha, K. V. (2023) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit58785.2023.10304954 · Cited by 2
“In recent times, there has been a growing utilization of multimodal AI techniques [28][29] to examine the disposal of electronic equipment waste.”
BackgroundSelf-citationHalvorson, M., Moyers, N., Raghu, S. L., Rawlins, S. B., Sriman, P., Neal, T., Bentley, C., O’Neill, R., Lewis, R. P., Landberg, J., et al. (2024) · Conference on systems engineering research series · doi:10.1007/978-3-031-62554-1_9 · Cited by 2
MicroXercise: A Micro-Level Comparative and Explainable System for Remote Physical Therapy
Wang, H. D., Khan, N., Chen, A., Sarkar, N., Wiśniewski, P., & Ma, M. (2024) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase60773.2024.00017 · Cited by 6
“We present a quantitative evaluation that provides an empirical foundation for our approach with defined metrics that focus on the objectives of achieving both fidelity and interpretability in the realm of attribution-based methods [11], [17], [30], [31].”
MethodGOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
Guo, Y., & Zhong, R. (2025) · Mathematics · doi:10.3390/math13111791 · Cited by 2
Murumkar, S. (2024) · International Journal of Artificial Intelligence Data Science and Machine Learning · doi:10.63282/3050-9262.ijaidsml-v5i4p119 · Cited by 1
Genetic Algorithm for Interpretability in Vision Language Models
Barreto, M. H. L., Oliveira, C. L., Santos, F. A. O., Nováis, P., Matos, L. N., & Britto, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15987-8_40 · Cited by 1
CSI-Tuples-Based 3-D Channel Fingerprints Construction Assisted by Multimodal Learning
Xie, C., Li, Y., Chen, R., He, G., & Gao, X. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3693681 · Cited by 1
“It leverages the correlation and complementarity among different data to keep critical features and remove redundant ones, integrating various information into a stable multimodal representation [62].”
AN OVERVIEW OF MULTIMODAL LEARNING: CONCEPTS, CHALLENGES, APPLICATIONS AND DATASETS
Ateş, A. H., & Yurtsever, U. (2026) · Konya Journal of Engineering Sciences · doi:10.36306/konjes.1716813 · Cited by 1
Generic Multimodal Gradient-based Meta Learner Framework
Enamoto, L. M., Weigang, L., Filho, G. P. R., & Costa, P. (2023) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion52260.2023.10224143 · Cited by 1
“To address this problem, we should understand why the model achieved a particular prediction, which input features more contributed to that decision, and identify a possible model bias [47].”
BackgroundOn the Interpretability of a Tree-based Ensemble for Predicting Software Effort
Najm, A., & Zakrani, A. (2023) · IEEE Congress on Information Science and Technology (CiSt) · doi:10.1109/cist56084.2023.10410020 · Cited by 4
“The complex internal structure of machine learning models poses difficulties in understanding and interpreting their decision-making processes, classifying them as BlackBox models [5].”
BackgroundInterpreting Contrastive Embeddings in Specific Domains with Fuzzy Rules
Fumanal-Idocin, J., Jamalifard, M., & Andreu-Pérez, J. (2024) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee60900.2024.10611816 · Cited by 1
“Many other procedures have been used to understand the embeddings obtained with these models, which is useful both for Explainable AI (XAI) and to exploit this knowledge in a larger machine learning pipeline [15].”
Time for an Explanation: A Mini-Review of Explainable Physio-Behavioural Time-Series Classification
Schneider, J., Cheruvalath, S. S., & Hassan, T. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3679001 · Cited by 1
“Consequently, eXplainable Artificial Intelligence (XAI) has gained traction as a means to shed light on these models [15].”
Towards Interactive and Social Explainable Artificial Intelligence for Digital History
Albrecht, R., Hulstijn, J., Tchappi, I., & Najjar, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70074-3_11 · Cited by 1
Ensemble-Inspired Multi-Modal Fusion of Features for Fake News Detection on Social Media
Nikumbh, D. D., & Thakare, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-7839-3_7 · Cited by 1
Mane, T., Oza, P., & Phansalkar, S. (2024) · IEEE International Conference on ICT in Business Industry & Government (ICTBIG) · doi:10.1109/ictbig64922.2024.10911665 · Cited by 1
A Step towards Interpretable Multimodal AI Models with MultiFIX
Malafaia, M., Schlender, T., Alderliesten, T., & Bosman, P. A. N. (2025) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3712255.3734292 · Cited by 1
“Moreover, these promote vital and constant interaction between AI and domain experts, interpreting how models work, and providing input on if and how models should be adjusted [10].”
A Multimodal Multi-Drone Cooperation System for Real-Time Human Searching
Peng, J., Li, Q., Tan, Y., Zhao, D., Chen, J., & Jiang, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3619530 · Cited by 1
de México, T. N., Cuaya-Simbro, G., Tapia, W. G., Vargas, M. F. A., & Ávalos, P. A. H. (2025) · Científica · doi:10.46842/ipn.cien.v29n2a08 · Cited by 1
Mahlau, Y., & Nolde, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.01565 · Cited by 1
“[16] provide an overview of explainability in different machine learning fields.”
BackgroundAmbroise, C. (2024) · theses.fr (ABES) · doi:10.70675/d2529d35z93e6z4d60zb2c5z752d5f0edda3 · Cited by 2
Youtube Engagement Analytics via Deep Multimodal Fusion Model
Nguyen-Thi, M.-V., Le, H. H., Le, T., Le, T., & Nguyen, H. T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26431-3_5
Improving information fusion in deep learning
Don, D. P. M. K. (2023) · Queensland University of Technology · doi:10.5204/thesis.eprints.241291
A Short Review on XAI Techniques in Text Data
Ghosh, M., Das, A. K., & Chakrabarti, A. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-3656-4_36
Enhancing the Machine Vision Performance with Multi-Spectral Light SourcesPreprint
Zhang, F., Bao, R., Dai, C., Zhang, W., Shu, L., & Guo, R. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4658923
Kraken: An Open-Source RISC-V SoC for Ultra-Low Power Multi-Modal PerceptionPreprint
Potocnik, V., Mauro, A. D., Leitner, C., Scherer, M., Rutishauser, G., Lamberti, L., & Benini, L. (2024) · Research Square · doi:10.21203/rs.3.rs-4023416/v1 · Cited by 2
Post-hoc XAI Method for Visual Question Answering (VQA)
Muddamsetty, S. M., Schmidt, A. B., & Moeslund, T. B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8705-0_25
“However, these systems often exhibit poor explanatory capabilities and take shortcuts by focusing solely on simple visual concepts or question priors instead of finding the right answer for the correct reasons [14].”
A multimodal fusion method with interpretability for nozzle health online prediction
Xie, J., Guo, Y. H., Huang, S., Liu, D., Tao, Y., & Hu, J. (2025) · International Journal of Computer Integrated Manufacturing · doi:10.1080/0951192x.2025.2496887
“Multimodal interpretation techniques have shown potential in a number of domains such as healthcare, autonomous driving, vision and language tasks (Joshi, Walambe, and Kotecha 2021; Stahlschmidt, Ulfenborg, and Synnergren 2022; Steyaert et al. 2023).”
Multimodal Situational Awareness: Neuro-Symbolic AI for Real-Time HCI in the Classroom
Zhu, Y., Lai, K., Khebour, I., Verhagen, M., Krishnaswamy, N., & Pustejovsky, J. D. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94153-5_45
Sotubadi, S. V., Mahjourian, N., & Nguyen, V. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16028-2 · Cited by 1
“However, recent advancements in technology have facilitated data collection in multiple modalities [24].”
Liu, H. (2025) · International Conference on Computer Science and Technologies in Education (CSTE) · doi:10.1109/cste64638.2025.11092167
“However, ML pose certain challenges like missing modalities[23], lack of multimodal datasets, multimodal explainability[24], the robustness of multimodal applications[25], Some of the identified challenges are detailed below.”
Huang, Z. (2025) · Computer Speech & Language · doi:10.1016/j.csl.2025.101871
Responsible Artificial Intelligence for Healthcare: Trends, Challenges, and Opportunities
Baker, S., & Ahn, E. (2025) · Springer eBooks · doi:10.1007/978-3-031-88024-7_1
Frameworks for Replicating Human Depth Perception in Autonomous Systems
Anaokar, C. A., & Atalatti, S. (2025) · International Conference on Computing Technologies & Data Communication (ICCTDC) · doi:10.1109/icctdc64446.2025.11158754
Zhang, J., Lai, Y., Feng, H., Luo, X., Li, K., Wang, T., Chang, C., Yang, G., Lin, C., Li, T., et al. (2025) · Medical Physics · doi:10.1002/mp.70021
“33 To demonstrate the contribution of each modality to the Diff-MC prediction, the ablation study of the modality was performed.”
Attention Lattice Adapter: Visual Explanation Generation for Visual Foundation Models
Hirano, S., Wada, Y., Iida, T., & Sugiura, K. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4097-6_27 · Cited by 1
Detection and Classification of Alzheimer’s Disease Using Multimodal Approach
Kulkarni, M., Shrinivedhaa, R., Reddy, S., Peram, N., & Preethi, P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8796-1_43
Market Trend Prediction and Product Demand Analysis in E-commerce Using Transformer
Du, Z., & Li, P. (2025) · International Conference on Big Data and Digital Management (ICBDDM) · doi:10.1145/3768801.3768952
“Especially under multimodal input (such as price, promotional tags, user behavior), it is difficult for the model to automatically construct efficient semantic representation, which limits its generalization ability [7].”
Explaining Multimodal Features for Screening of Cognitive Impairment Using Shapley Values
Brauße, E., Koenen, N., Wright, M. N., & Schultz, T. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11251859
“Several works have attempted such explanations for Deep Neural Networks (DNNs) [10] and a growing number of publications has been striving to provide explanations for multimodal AD screening models.”
Ren, Z., Xiao, Z., & Sun, Y. (2024) · arXiv (Cornell University) · doi:10.13140/rg.2.2.32984.51202 · Cited by 1
On Memory for Everyday Symbols
Roberts, B. (2023) · UWSpace (University of Waterloo)
WAIT, I Can Explain! Introducing Weighted AI Integration for Tailored Explanations
Giovannoni, C. (2024) · CINECA IRIS Institutial research information system (University of Pisa)
Schrage, L. (2024) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2
Orenti, A., Adamoli, A., Zolin, A., & Ambrogi, F. (2023) · Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)
Can Multitask Learning Enhance Model Explainability?
Najjar, H., Alshbib, B., & Dengel, A. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-12840-9_38 · Cited by 1
Deep learning architectures for multimodal fusion
Savithri, M., & Gnanamonickam, A. A. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-27528-9.00004-8
Hu, J., Ma, A., Xiao, J., Wang, Y., & Wang, Y. (2026) · ACS ES&T Water · doi:10.1021/acsestwater.5c00925
A Comprehensive Review on Explainable AI: Where It Was, Is and Will
Wangkhem, K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9935-3_1
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.