A Review on Explainability in Multimodal Deep Neural Nets
Open accessThe DOI matches its Crossref record; 267 of the 267 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
Items 201–267 of 267
Evaluating Explanations: How Much Do Explanations from the Teacher Aid Students?
Pruthi, D., Bansal, R., Dhingra, B., Soares, L. B., Collins, M., Lipton, Z. C., Neubig, G., & Cohen, W. W. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00465 · Cited by 55 · cited 1×
“In [219], Explanations are evaluated based on the novel metric from the student-teacher paradigm that measures the degree to which the explanations help the student model simulate a teacher model in an improved way for better”
BackgroundLee, H., Kim, S. T., & Ro, Y. M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33850-3_3 · Cited by 54
Challenges and Prospects in Vision and Language Research
Kafle, K., Shrestha, R., & Kanan, C. (2019) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2019.00028 · Cited by 52 · cited 1×
“With the development of new benchmarks, we can identify and handle the flaws in model evaluation metrics, dataset bias, robustness, and spurious correlations [87] in the multimodal data.”
Generating Counterfactual Explanations with Natural Language
Hendricks, L. A., Hu, R., Darrell, T. J., & Akata, Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.09809 · Cited by 49 · cited 2×
“In [18], a textual explanation model is proposed to investigate why the model predicted a class x instead of class X based on counterfactuals.”
BackgroundMethodExplaining Deep Neural NetworksPreprint
Camburu, O.-M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01496 · Cited by 49 · cited 1×
“The primary explainable goal for an opaque, black box explanatory system such as deep neural nets is to answer how and why the model makes a certain prediction by inspecting the driving factors behind their decisions [162].”
BackgroundPoint and Ask: Incorporating Pointing into Visual Question AnsweringPreprint
Mani, A., Yoo, N., Hinthorn, W., & Russakovsky, O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13681 · Cited by 48 · cited 1×
“In [173], a module for spatial grounding in VQA is proposed.”
MethodTrends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
Mogadala, A., Kalimuthu, M., & Klakow, D. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11688 · Cited by 47 · cited 1×
“INTRODUCTION Remarkable improvements of deep neural nets in the independent tasks based on several modalities such as vision, sensor data, textual data, and language have given rise to many new trends and applications in the integrated space of deep multimodal learning [1].”
BackgroundDeep Multimodal Fusion: A Hybrid Approach
Amer, M. R., Shields, T. J., Siddiquie, B., Tamrakar, A., Divakaran, A., & Chai, S. M. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-0997-7 · Cited by 45 · cited 1×
“Deep neural nets [45],kernelbased methods [46], and graphical models [47], [48] are employed for analysis and handling such data depending on the downstream task [40].”
MethodMultimodal Affect Recognition: Current Approaches and Challenges
Osman, H. A., & Falk, T. H. (2017) · InTech eBooks · doi:10.5772/65683 · Cited by 44
(2019) · doi:10.18653/v1/w19-4807 · Cited by 43 · cited 1×
“In [171], the authors used a supervised attention model that trains human rationales to generate explanations.”
MethodGraph-based multimodal fusion with metric learning for multimodal classification
Angelou, M., Solachidis, V., Vretos, N., & Daras, P. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.06.013 · Cited by 41 · cited 1×
“Deep neural nets [45],kernelbased methods [46], and graphical models [47], [48] are employed for analysis and handling such data depending on the downstream task [40].”
MethodChallenges in Multimodal Data Fusion
Lahat, D., Adalı, T., & Christian Jutten, B. (2014) · Cited by 39
Towards Transparent AI Systems: Interpreting Visual Question Answering Models
Goyal, Y., Mohapatra, A., Parikh, D., & Batra, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.08974 · Cited by 38 · cited 2×
“In [176], guided backpropagation and occlusion-based visualization techniques are employed to showcase vital regions on the image and text on which the VQA model focuses.”
BackgroundMethodLearning to Explain With Complemental Examples
Kanehira, A., & Harada, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00880 · Cited by 38 · cited 2×
“[183] developed a complementary explanation model by applying a joint training approach to generate a prediction and explanation, maximize the modality interaction information, and ensure that the explanations are complementary to each other.”
BackgroundMethodModularized Textual Grounding for Counterfactual Resilience
Fang, Z., Kong, S., Fowlkes, C. C., & Yang, Y. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00654 · Cited by 36 · cited 1×
“In [186], counterfactual resilience in image descriptions is obtained by parsing entities, semantic attributes, and color information separately.”
BackgroundInverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool
Liu, F., Xiang, T., Hospedales, T. M., Yang, W., & Sun, C. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2880185 · Cited by 36 · cited 1×
“In Visual Questioning Answering to diagnose the model’s performance, the inverse Visual Question Answering task is proposed in a multimodal setting [12].”
MethodEfficient Large-Scale Multi-Modal ClassificationPreprint
Kiela, D., Grave, É., Joulin, A., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.02892 · Cited by 35 · cited 1×
“Features are fused using simple concatenation [104], pooling, and gated units [105].”
MethodA Study on Multimodal and Interactive Explanations for Visual Question AnsweringPreprint
Alipour, K., Schulze, J. P., Yao, Y., Ziskind, A. J., & Burachas, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00431 · Cited by 35 · cited 2×
“[189], evaluated multimodal explanations for VQA with and without explanations and established that explanations improve accuracy if the VQA system is wrong.”
BackgroundMethodEvaluating Explanation Without Ground Truth in Interpretable Machine Learning
Yang, F., Du, M., & Hu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06831 · Cited by 34 · cited 1×
“Evaluation of explanations without ground truth based on generalizing ability, persuasibility is proposed in [212] with criteria for good explanation generalization performance, fidelity, faithfulness, relevance, per suability usability user satisfaction, and causality [213].”
BackgroundMultimodal Explanations by Predicting Counterfactuality in Videos
Kanehira, A., Takemoto, K., Inayoshi, S., & Harada, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00879 · Cited by 33 · cited 4×
“An interpretable prediction attention-based mechanism is recently used in [160] for predicting anticancer compound sensitivity using attentionbased convolution encoders for the task of drug discovery.”
BackgroundMethodInfluentialSemantically Interpretable Activation Maps: what-where-how explanations within CNNs
Marcos, D., Lobry, S., & Tuia, D. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00518 · Cited by 33 · cited 2×
“[193] proposed ‘‘Semantically Interpretable Activation Maps (SIAM).”
BackgroundSokol, K., & Flach, P. A. (2020) · Explore Bristol Research · doi:10.48550/arxiv.2001.09734 · Cited by 33 · cited 1×
“An interactive approach to explanation leverages transparency in machine learning systems [188].”
BackgroundRobust Explanations for Visual Question Answering
Patro, B. N., Patel, S., & Namboodiri, V. P. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093295 · Cited by 33 · cited 1×
“wherein the answers can be justified in both textual and visual formats [202].”
BackgroundExplanation Perspectives from the Cognitive Sciences---A Survey
Srinivasan, R., & Chander, A. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/670 · Cited by 32 · cited 1×
“The system's explanation should be human interpretable and understandable, mapping the human mental model to build trust, transparency, reliability for success and failure, robust, fair, and unbiased applications underlying ethical machine learning principles [139], [140].”
BackgroundExplainability of vision-based autonomous driving systems: Review and challenges.Preprint
Zablocki, É., Ben-younes, H., Pérez, P., & Cord, M. (2021) · arXiv (Cornell University) · Cited by 32
A Deep Multi-Modal Explanation Model for Zero-Shot Learning
Liu, Y., & Tuytelaars, T. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2975980 · Cited by 31 · cited 1×
“In [201], a model produces attribute-based textual and visual explanations improving user trust and model flaws by generating complementary multimodal explanations.”
BackgroundAchievements and Challenges in Explaining Deep Learning based Computer-Aided Diagnosis SystemsPreprint
Lucieri, A., Bajwa, M. N., Dengel, A. R., & Ahmed, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13169 · Cited by 31 · cited 1×
“[85] The paper highlights the advancement and”
TED: Teaching AI to Explain its DecisionsPreprint
Hind, M., Wei, D., Campbell, M. S., Codella, N., Dhurandhar, A., Mojsilović, A., Ramamurthy, K. N., & Varshney, K. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.04896 · Cited by 30
Contrastive Visual-Linguistic PretrainingPreprint
Shi, L., Shuang, K., Geng, S., Su, P., Jiang, Z., Gao, P., Fu, Z., de Melo, G., & Su, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13135 · Cited by 29 · cited 1×
“It improves multimodal representations in pretraining handling noise and bias in the data [187].”
BackgroundDeep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis
Verma, S., Wang, J., Ge, Z., Shen, R., Jin, F., Wang, Y., Chen, F., & Liu, W. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00065 · Cited by 29 · cited 1×
“mation is proposed for sentiment analysis that models the inter and intra modalities with no reliance on attention mechanism [127].”
BackgroundHow to Integrate Data from Multiple Biological Layers in Mental Health?
Silva, R. F., & Plis, S. (2019) · Springer eBooks · doi:10.1007/978-3-030-03553-2_8 · Cited by 28
Explaining Explanations to Society
Gilpin, L. H., Testart, C., Fruchter, N., & Adebayo, J. (2019) · arXiv · doi:10.48550/arxiv.1901.06560 · Cited by 28 · cited 2×
“They do not satisfy the needs of different stakeholders [131].”
BackgroundTAB-VCR: Tags and Attributes based Visual Commonsense Reasoning BaselinesPreprint
Lin, J., Jain, U., & Schwing, A. G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.14671 · Cited by 26 · cited 1×
“In [198], the authors proposed the multimodal approach for generating the textual justification from”
BackgroundCan You Explain That? Lucid Explanations Help Human-AI Collaborative Image Retrieval
Ray, A., Yao, Y., Kumar, R., Divakaran, A., & Burachas, G. (2019) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v7i1.5275 · Cited by 24 · cited 1×
“In real-world settings, justification, and introspection, both systems are desired [160] as the generation of lucid explanations improves human understanding and performance significantly [166].”
BackgroundSentiment Analysis of Turkish and English Twitter Feeds Using Word2Vec Model
Karcıoğlu, A. A., & Aydın, T. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806295 · Cited by 23 · cited 1×
“Multiple deep learning and embedding approaches are reported for NLP tasks such as text mining [35],[36], sentiment analysis [37],[38],sarcasm identification [39],[40], information extraction [41],[42],[43].”
BackgroundWhere is the Model Looking At? – Concentrate and Explain the Network Attention
Xu, W., Wang, J., Wang, Y., Xu, G., Lin, D., Dai, W., & Wu, Y. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987729 · Cited by 23
(2007) · Springer eBooks · doi:10.1007/978-1-84628-282-9_101 · Cited by 20
Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions
Kaya, H., & Salah, A. A. (2018) · The Springer series on challenges in machine learning · doi:10.1007/978-3-319-98131-4_10 · Cited by 19 · cited 1×
“Personality trait analysis [69] Text image, video Automatic analysis of job interview screening”
MethodClass Activation Map Generation by Representative Class Selection and Multi-Layer Feature FusionPreprint
Meng, F., Huang, K., Li, H., & Wu, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.07683 · Cited by 17 · cited 1×
“Activation maps are used in [200] by considering different class pairs as complementary.”
MethodCommonsense Justification for Action Explanation
Yang, S., Gao, Q., Saba-Sadiya, S., & Chai, J. Y. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1283 · Cited by 16 · cited 1×
“[4],[184],[178], [210],[177], [181],[79],[176] ,[188],[211], [212],[19],[123] ,[213],[214], [215] Attentionbased approach Explanations based on attention to capture the important visual and textual regions that contribute to a prediction.”
BackgroundGenerating User-friendly Explanations for Loan Denials using GANsPreprint
Srinivasan, R., Chander, A., & Pezeshkpour, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.10244 · Cited by 16 · cited 1×
“Finance [89] Tabular, Temporal Paper generates userfriendly explanations for loan denials using GAN”
MethodMultimodal Deep Learning for Advanced Driving Systems
Aranjuelo, N., Unzueta, L., Arganda‐Carreras, I., & Otaegui, O. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-94544-6_10 · Cited by 15
Explaining with Counter Visual Attributes and Examples
Gulshad, S., & Smeulders, A. W. M. (2020) · International Conference on Multimedia Retrieval · doi:10.1145/3372278.3390672 · Cited by 15 · cited 2×
“In [197], the authors proposed an explanation model using attributes, counter attributes with examples and counter visual exam-”
BackgroundMethodFLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions
Wickramanayake, S., Hsu, W., & Lee, M. L. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33012539 · Cited by 14 · cited 1×
“In [199], the FLEXmodel is introduced that generates faithful language explanation for CNN decisions even for unseen class and provides a rationale.”
BackgroundThe Impact of Explanations on AI Competency Prediction in VQA
Alipour, K., Ray, A., Lin, X., Schulze, J. P., Yao, Y., & Burachas, G. (2020) · doi:10.1109/hccai49649.2020.00010 · Cited by 14
Towards Good Practices for Multi-modal Fusion in Large-Scale Video Classification
Liu, J., Yuan, Z., & Wang, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11018-5_26 · Cited by 13
Yang, G. Z., Ye, Q., & Xia, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.01998 · Cited by 13
Explaining Visual Classification using Attributes
Hassan, M. U., Mulhem, P., Pellerin, D., & Quenot, G. M. (2019) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2019.8877393 · Cited by 12 · cited 1×
“[217],[209] ,[218],[201], [205],[219], [220],[206].”
Integration of “omics” Data and Phenotypic Data Within a Unified Extensible Multimodal Framework
Das, S., Boucher, X. L., Rogers, C., Makowski, C., Chouinard-Decorte, F., Klein, K., Beck, N., Rioux, P., Brown, S. T., Mohades, Z., et al. (2018) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2018.00091 · Cited by 11 · cited 1×
“[88] Medical image analysis Genetics and biomedicine for the integration of omics data.”
BackgroundMultimodal Data Fusion based on the Global Workspace Theory
Bao, C., Fountas, Z., Olugbade, T., & Bianchi‐Berthouze, N. (2020) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3382507.3418849 · Cited by 11 · cited 1×
“A neural network-based model architecture based on global workspace theory from cognitive science is proposed to cope with uncertainties in data fusion with attention models across different modalities [126].”
BackgroundSoftware Engineering Methods in Intelligent Algorithms
(2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-19807-7 · Cited by 11
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 · cited 1×
“A neural network-based model architecture based on global workspace theory from cognitive science is proposed to cope with uncertainties in data fusion with attention models across different modalities [126].”
BackgroundA Survey on Multimodal Biometrics Authentication and Template Protection
Natarajan, A., & Shanthi, N. (2018) · International Conference on Intelligent Computing and Communication for Smart World (I2C2SW) · doi:10.1109/i2c2sw45816.2018.8997125 · Cited by 8
Improving VQA and its Explanations \\ by Comparing Competing Explanations
Wu, J., Chen, L., & Mooney, R. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.15631 · Cited by 8 · cited 1×
“In [178], authors have proposed an approach to enhance VQA performance by comparing competing explanations.”
Background(2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58577-8 · Cited by 8
Kamath, U., & Liu, J. (2021) · Springer eBooks · doi:10.1007/978-3-030-83356-5_6 · Cited by 6
Attention-based Information Fusion using Multi-Encoder-Decoder Recurrent Neural NetworksPreprint
Baier, S., Spieckermann, S., & Volker Tresp, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04679 · Cited by 4 · cited 1×
“[4],[184],[178], [210],[177], [181],[79],[176] ,[188],[211], [212],[19],[123] ,[213],[214], [215] Attentionbased approach Explanations based on attention to capture the important visual and textual regions that contribute to a prediction.”
BackgroundMultimodal explanations for AI-based multisensor fusion
Braines, D., Preece, A. D., & Harborne, D. (2018) · ORCA Online Research @Cardiff (Cardiff University) · Cited by 4
Dynamic Fusion for Multimodal Data.Preprint
Sahu, G., & Vechtomova, O. (2019) · arXiv (Cornell University) · Cited by 4
Challenges and Prospects in Vision and Language ResearchPreprint
Kafle, K., Shrestha, R., & Kanan, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.09317 · Cited by 3 · cited 1×
“With the development of new benchmarks, we can identify and handle the flaws in model evaluation metrics, dataset bias, robustness, and spurious correlations [87] in the multimodal data.”
Emerging Trends of Multimodal Research in Vision and Language.Preprint
Uppal, S., Bhagat, S., Hazarika, D., Majumder, N., Poria, S., Zimmermann, R., & Zadeh, A. (2020) · arXiv (Cornell University) · Cited by 3
XFlow: Cross-Modal Deep Neural Networks for Audiovisual Classification
Cangea, C., Veličković, P., & Lió, P. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2945992 · Cited by 2
Beyond VQA: Generating Multi-word Answer and Rationale to Visual QuestionsPreprint
Dua, R., Kancheti, S. S., & Balasubramanian, V. N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12852 · Cited by 2 · cited 1×
“In [179], the multiword answer and rationale model for ViQAR are generated that goes beyond VQA in abstraction and reasoning abilities.”
MethodEvaluating Explanations: How much do explanations from the teacher aid students?Preprint
Pruthi, D., Bansal, R., Dhingra, B., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00893 · Cited by 2 · cited 1×
“In [219], Explanations are evaluated based on the novel metric from the student-teacher paradigm that measures the degree to which the explanations help the student model simulate a teacher model in an improved way for better”
BackgroundMultimedia Information Retrieval
Bourlard, H., & Popescu-Belis, A. (2014) · EPFL Press eBooks · doi:10.1201/b15535-10 · Cited by 1
XAlgo: Explaining the Internal States of Algorithms via Question Answering.Preprint
Rebanal, J., Tang, Y., Combitsis, J., Chang, K.-W., & Chen, X. (2020) · arXiv (Cornell University) · Cited by 1
Language-Driven Video Understanding
Zhou, L. (2020) · Deep Blue (University of Michigan) · Cited by 1
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].”
Background
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.