{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T09:21:54Z","timestamp":1784366514239,"version":"3.55.0"},"reference-count":230,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004541","name":"Ministry of Human Resource Development (MHRD) Scheme for Promotion of Academic and Research Collaboration (SPARC) of the Government of India","doi-asserted-by":"publisher","award":["P104"],"award-info":[{"award-number":["P104"]}],"id":[{"id":"10.13039\/501100004541","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3070212","type":"journal-article","created":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T19:45:02Z","timestamp":1617219902000},"page":"59800-59821","source":"Crossref","is-referenced-by-count":191,"title":["A Review on Explainability in Multimodal Deep Neural Nets"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5460-8116","authenticated-orcid":false,"given":"Gargi","family":"Joshi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1745-5231","authenticated-orcid":false,"given":"Rahee","family":"Walambe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2653-3780","authenticated-orcid":false,"given":"Ketan","family":"Kotecha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","article-title":"Faithful multimodal explanation for visual question answering","volume":"abs 1809 2805","author":"wu","year":"2018","journal-title":"CoRR"},{"key":"ref172","first-page":"10003","article-title":"SQuINTing at VQA models: Introspecting VQA models with sub-questions","author":"vqa","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4807"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/HCCAI49649.2020.00010"},{"key":"ref173","article-title":"Point and ask: Incorporating pointing into visual question answering","author":"mani","year":"2020","journal-title":"arXiv 2011 13681"},{"key":"ref176","first-page":"3914","article-title":"Maximizing joint probability in visual question answering models","volume":"29","author":"vidya sagar appaji","year":"2020","journal-title":"Int J Adv Sci Technol"},{"key":"ref175","first-page":"1","article-title":"Self-critical reasoning for robust visual question answering","volume":"32","author":"wu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref178","article-title":"Improving VQA and its explanations by comparing competing explanations","author":"wu","year":"2020","journal-title":"arXiv 2006 15631"},{"key":"ref177","article-title":"Language-driven video understanding","author":"zhou","year":"2020"},{"key":"ref168","article-title":"Towards transparent AI systems: Interpreting visual question answering models","author":"goyal","year":"2016","journal-title":"arXiv 1608 08974"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33850-3_3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2843369"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6060052"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref31","article-title":"Explainable deep learning: A field guide for the uninitiated","author":"xie","year":"2020","journal-title":"arXiv 2004 14545"},{"key":"ref30","article-title":"Towards a rigorous science of interpretable machine learning","author":"doshi-velez","year":"2017","journal-title":"arXiv 1702 08608"},{"key":"ref37","article-title":"A survey of the state of explainable AI for natural language processing","author":"danilevsky","year":"2020","journal-title":"arXiv 2010 00711"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.01.008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3400051.3400058"},{"key":"ref34","article-title":"A survey on explainable artificial intelligence (XAI): Toward medical xai","author":"toward","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref181","article-title":"Algorithmic recourse: From counterfactual explanations to interventions","author":"karimi","year":"2020","journal-title":"arXiv 2002 06278"},{"key":"ref180","first-page":"11","article-title":"Attention is not not explanation","author":"wiegreffe","year":"2020","journal-title":"Proc Conf Empircal Methods Nat Lang Process 9th Int Joint Conf Nat Lang Process Conf (EMNLP-IJCNLP)"},{"key":"ref185","article-title":"Counterfactual VQA: A cause-effect look at language bias","author":"niu","year":"2020","journal-title":"arXiv 2006 04315"},{"key":"ref184","first-page":"4254","article-title":"Counterfactual visual explanations","author":"goyal","year":"2019","journal-title":"Proc 36th Int Mach Learn (ICML)"},{"key":"ref183","article-title":"Learning to explain with complemental examples","author":"kanehira","year":"2018","journal-title":"arXiv 1812 01280"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3063289"},{"key":"ref189","article-title":"A study on multimodal and interactive explanations for visual question answering","author":"alipour","year":"2020","journal-title":"arXiv 2003 00431"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-020-00637-y"},{"key":"ref187","article-title":"Contrastive visual-linguistic pretraining","author":"shi","year":"2020","journal-title":"arXiv 2007 13135"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00654"},{"key":"ref28","first-page":"93","article-title":"A survey of methods for explaining black box models","volume":"51","author":"guidotti","year":"2018","journal-title":"ACM Comput Surv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2018.00018"},{"key":"ref179","article-title":"Beyond VQA: Generating multi-word answer and rationale to visual questions","author":"dua","year":"2020","journal-title":"arXiv 2010 12852"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref23","article-title":"Explainable deep learning: A field guide for the uninitiated","author":"xie","year":"2020","journal-title":"arXiv 2004 14545"},{"key":"ref26","article-title":"A survey on explainable artificial intelligence (XAI): Towards medical XAI","author":"tjoa","year":"2019","journal-title":"arXiv 1907 07374"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8080832"},{"key":"ref50","article-title":"Explainable artificial intelligence: A systematic review","author":"vilone","year":"2020","journal-title":"arXiv 2006 00093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0911-8"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-0557-2_87"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070500"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref152","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"2017","journal-title":"arXiv 1703 01365"},{"key":"ref151","article-title":"Learning important features through propagating activation differences","author":"shrikumar","year":"2017","journal-title":"arXiv 1704 02685"},{"key":"ref146","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"lundberg","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref147","first-page":"2288","article-title":"Examples are not enough, learn to criticize! Criticism for interpretability","author":"kim","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref148","article-title":"Understanding black-box predictions via influence functions","author":"wei koh","year":"2017","journal-title":"arXiv 1703 04730"},{"key":"ref149","article-title":"Rise: Randomized input sampling for explanation of black-box models","author":"petsiuk","year":"2018","journal-title":"arXiv 1806 07421"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/I2C2SW45816.2018.8997125"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79860-6_12"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2892755"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5772\/65683"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref166","article-title":"Can you explain that? Lucid explanations help human-AI collaborative image retrieval","author":"ray","year":"2019","journal-title":"arXiv 1904 03285"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00546"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287574"},{"key":"ref162","article-title":"Explaining deep neural networks","author":"camburu","year":"2020","journal-title":"arXiv 2010 01496"},{"key":"ref161","first-page":"4157","article-title":"Make up your mind! adversarial generation of inconsistent natural language explanations","author":"camburu","year":"2019","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00879"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref6","author":"molnar","year":"2020","journal-title":"Interpretable Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"ref159","article-title":"A multidisciplinary survey and framework for design and evaluation of explainable AI systems","author":"mohseni","year":"2018","journal-title":"arXiv 1811 11839"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99740-7_21"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.538"},{"key":"ref157","first-page":"5999","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314273"},{"key":"ref46","first-page":"2949","article-title":"Multimodal learning with deep Boltzmann machines","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-0997-7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.013"},{"key":"ref47","first-page":"4351","article-title":"Leakage-adjusted simulatability: Can models generate non-trivial explanations of their behavior in natural language?","author":"hase","year":"2020","journal-title":"Proc Findings Assoc Comput Linguistics (EMNLP)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.10.006"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1515\/icom-2020-0024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461053"},{"key":"ref76","first-page":"1","article-title":"What clinicians want: Contextualizing explainable machine learning for clinical end use","author":"tonekaboni","year":"2019","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref77","article-title":"Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond","author":"yang","year":"2021","journal-title":"arXiv 2102 01998"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3390\/e23010018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.01346"},{"key":"ref78","first-page":"1","article-title":"Achievements and challenges in explaining deep learning based computer-aided diagnosis systems","author":"lucieri","year":"2020","journal-title":"arXiv 2011 13169"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2016.06.003"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123046"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.06.001"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.06.002"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98131-4_10"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94544-6_10"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00178"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref69","article-title":"Explainability of vision-based autonomous driving systems: Review and challenges","author":"zablocki","year":"2021","journal-title":"arXiv 2101 05307"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390672"},{"key":"ref198","article-title":"TAB-VCR: Tags and attributes based VCR baselines","author":"lin","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012539"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00518"},{"key":"ref194","article-title":"Visual relationship detection using language priors","author":"lu","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref195","article-title":"Semantics of the black-box: Can knowledge graphs help make deep learning systems more interpretable and explainable?","author":"gaur","year":"2020","journal-title":"arXiv 2010 08660"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.3390\/info11020122"},{"key":"ref95","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for Vision-and-Language tasks","author":"lu","year":"2019","journal-title":"arXiv 1908 02265"},{"key":"ref94","article-title":"Uniter: Learning universal image-text representations","author":"chen","year":"2019","journal-title":"arXiv 1909 11740"},{"key":"ref190","article-title":"XAlgo: Explaining the internal states of algorithms via question answering","author":"rebanal","year":"2020","journal-title":"arXiv 2007 07407"},{"key":"ref93","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2019","journal-title":"arXiv 1908 08530"},{"key":"ref191","first-page":"1","article-title":"Multimodal explanations for ai-based multisensor fusion","author":"braines","year":"2018","journal-title":"Proc RSM Artif Intell Military Multisensor Fusion Engines"},{"key":"ref92","first-page":"11336","article-title":"Unicoder-VL: A universal encoder for vision and language by cross-modal pre-training","author":"li","year":"2019","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref98","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1201\/9781420053098"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref82","article-title":"Generating user-friendly explanations for loan denials using GANs","author":"srinivasan","year":"2018","journal-title":"Proc NeurIPS Workshop"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2018.00091"},{"key":"ref84","first-page":"101","article-title":"Challenges in multimodal data fusion","author":"lahat","year":"2014","journal-title":"Proc 22nd Eur Signal Process Conf (EUSIPCO)"},{"key":"ref83","article-title":"Multimodal deep learning for finance: Integrating and forecasting international stock markets","author":"li","year":"2019","journal-title":"arXiv 1903 06478"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03553-2_8"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-020-00332-0"},{"key":"ref85","article-title":"Multimodal research in vision and language: A review of current and emerging trends","author":"uppal","year":"2020","journal-title":"arXiv 2010 09522"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref87","first-page":"1","article-title":"Challenges and prospects in vision and language research","volume":"2","author":"challenges","year":"2019","journal-title":"Frontiers in Artificial Intellingence"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref200","article-title":"Class activation map generation by representative class selection and multi-layer feature fusion","author":"meng","year":"2019","journal-title":"arXiv 1901 07683"},{"key":"ref101","author":"tharwat","year":"2020","journal-title":"Appl Comput Inform"},{"key":"ref100","first-page":"333","article-title":"Principal components analysis","volume":"12","author":"l\u00f3pez del val","year":"1993","journal-title":"Aten Primaria"},{"key":"ref209","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TPAMI.2013.128","article-title":"Learning multimodal latent attributes","volume":"36","author":"fu","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1283"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975980"},{"key":"ref202","first-page":"1577","article-title":"Robust explanations for visual question answering","author":"patro","year":"2020","journal-title":"Proc IEEE Winter Conf Appl Comput Vis (WACV)"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"ref208","article-title":"Generating natural language explanations for visual question answering using scene graphs and visual attention","author":"ghosh","year":"2019","journal-title":"arXiv 1902 05715"},{"key":"ref205","first-page":"41","article-title":"Attention-based information fusion using multi-encoder-decoder recurrent neural networks","author":"baier","year":"2017","journal-title":"Proc 25th Eur Symp Artif Neural Netw Comput Intell Mach Learn (ESANN)"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1021\/acs.molpharmaceut.9b00520"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2019.8877393"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987729"},{"key":"ref212","article-title":"Evaluating explanation without ground truth in interpretable machine learning","author":"yang","year":"2019","journal-title":"arXiv 1907 06831"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98131-4_2"},{"key":"ref214","first-page":"1","article-title":"An evaluation of the human-interpretability of explanation","author":"lage","year":"2019","journal-title":"arXiv 1902 00006"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref217","first-page":"4566","article-title":"METEOR: An automatic metric for MT evaluation with high levels of correlation with human judgments","author":"vedantam","year":"2015","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref218","article-title":"SPICE: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proc ECCV"},{"key":"ref219","article-title":"Evaluating Explanations: How much do explanations from the teacher aid students?","author":"pruthi","year":"2020","journal-title":"arXiv 2012 00893"},{"key":"ref220","article-title":"Can we do better explanations? A proposal of usercentered explainable AI","author":"ribera","year":"2019","journal-title":"Proc IUI Workshops"},{"key":"ref222","first-page":"1","article-title":"Caltech-UCSD birds 200","author":"welinder","year":"2010"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref229","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2020","journal-title":"arXiv 2102 12092"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00520"},{"key":"ref226","first-page":"1","article-title":"Attend and attack?: Attention guided adversarial attacks on visual question answering models","author":"sharma","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref225","first-page":"1","article-title":"RUBi: Reducing unimodal biases in visual question answering","author":"cadene","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00022"},{"key":"ref223","article-title":"Removing bias in multi-modal classifiers: Regularization by maximizing functional entropies","author":"gat","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref127","article-title":"Deep-HOSeq: Deep higher order sequence fusion for multimodal sentiment analysis","author":"verma","year":"2020","journal-title":"arXiv 2010 08218"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418849"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"ref124","first-page":"1","article-title":"Deep multimodal fusion by channel exchanging","volume":"33","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref129","first-page":"1","article-title":"A survey of deep learning for scientific discovery","author":"raghu","year":"2020","journal-title":"arXiv 2003 11755"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2989782"},{"key":"ref130","article-title":"Explainable artificial intelligence (XAI)","volume":"2","author":"gunning","year":"2017","journal-title":"Defense Advanced Research Projects Agency"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"ref134","first-page":"8","article-title":"Explanation and justification in machine learning: A survey","volume":"8","author":"biran","year":"2017","journal-title":"Proc Workshop Explainable AI (XAI)"},{"key":"ref131","article-title":"Explaining explanations to society","author":"gilpin","year":"2019","journal-title":"arXiv 1901 06560"},{"key":"ref132","first-page":"4812","article-title":"Explanation perspectives from the cognitive sciences—A survey","author":"srinivasan","year":"2018","journal-title":"Proc 29th Int Joint Conf Artif Intell"},{"key":"ref230","author":"radford","year":"2021","journal-title":"Learning Transferable Visual Models From Natural Language Supervision"},{"key":"ref136","author":"alvarez-melis","year":"2018","journal-title":"Self-Explaining Neural Networks"},{"key":"ref135","first-page":"1","article-title":"Contextual explanation networks","volume":"21","author":"al-shedivat","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/371"},{"key":"ref137","first-page":"1670","article-title":"Beyond sparsity: Tree regularization of deep models for interpretability","author":"wu","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.210"},{"key":"ref140","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"arXiv 1312 6034"},{"key":"ref141","article-title":"Striving for simplicity: The all convolutional net","author":"tobias springenberg","year":"2014","journal-title":"arXiv 1412 6806"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref1","article-title":"Trends in integration of vision and language research: A survey of tasks, datasets, and methods","author":"mogadala","year":"2019","journal-title":"arXiv 1907 09358"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2014.907095"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.11.007"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2005.01.012"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_26"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663236"},{"key":"ref105","first-page":"5198","article-title":"Efficient large-scale multi-modal classification","author":"kiela","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2006.05.002"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1303"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.936725"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00341-z"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2875385"},{"key":"ref10","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref11","article-title":"Learn to combine modalities in multimodal deep learning","author":"liu","year":"2018","journal-title":"arXiv 1805 11730"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref14","article-title":"Grad-CAM: Why did you say that?","author":"selvaraju","year":"2016","journal-title":"arXiv 1611 07450"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0212-3"},{"key":"ref118","first-page":"12136","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","author":"hou","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"ref117","article-title":"Towards good practices for multi-modal fusion in large-scale video classification","author":"liu","year":"2018","journal-title":"arXiv 1809 05848"},{"key":"ref18","article-title":"Generating counterfactual explanations with natural language","author":"anne hendricks","year":"2018","journal-title":"arXiv 1806 09809"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.280"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2462751"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref121","article-title":"Memory fusion network for multi-view sequential learning","author":"zadeh","year":"2018","journal-title":"arXiv 1802 00927"},{"key":"ref122","article-title":"Dynamic fusion for multimodal data","author":"sahu","year":"2019","journal-title":"arXiv 1911 03821"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945992"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09391727.pdf?arnumber=9391727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:23Z","timestamp":1639770923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9391727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":230,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3070212","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}