{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:28:00Z","timestamp":1793608080641,"version":"4.5.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111801"],"award-info":[{"award-number":["2021ZD0111801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013773","name":"Hefei University of Technology","doi-asserted-by":"publisher","award":["62376087"],"award-info":[{"award-number":["62376087"]}],"id":[{"id":"10.13039\/501100013773","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109673","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T15:39:51Z","timestamp":1790177991000},"page":"109673","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Context-aware causal reasoning for explanatory visual question answering"],"prefix":"10.1016","volume":"206","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2718-4214","authenticated-orcid":false,"given":"Jiali","family":"Miao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-8055","authenticated-orcid":false,"given":"Xiaoling","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yecheng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuyuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109673_bib0001","series-title":"Computer vision\u2013ECCV 2016: 14th european conference, amsterdam, the netherlands, october 11-14, 2016, proceedings, part v 14","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"Anderson","year":"2016"},{"key":"10.1016\/j.neunet.2026.109673_bib0002","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018"},{"key":"10.1016\/j.neunet.2026.109673_bib0003","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2425","article-title":"VQA: Visual question answering","author":"Antol","year":"2015"},{"key":"10.1016\/j.neunet.2026.109673_bib0004","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"10800","article-title":"Counterfactual samples synthesizing for robust visual question answering","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109673_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"15586","article-title":"REX: Reasoning-aware and grounded explanation","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.109673_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112827","article-title":"R-VQA: A robust visual question answering model","volume":"309","author":"Chowdhury","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0007","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805."},{"key":"10.1016\/j.neunet.2026.109673_bib0008","series-title":"Proceedings of the 2019 Conference of the north american chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neunet.2026.109673_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"6700","article-title":"GQA: A new dataset for real-world visual reasoning and compositional question answering","author":"Hudson","year":"2019"},{"key":"10.1016\/j.neunet.2026.109673_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"2776","article-title":"Roses are red, violets are blue...but should vqa expect them to?","author":"Kervadec","year":"2021"},{"key":"10.1016\/j.neunet.2026.109673_bib0011","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.neunet.2021.02.001","article-title":"Visual question answering based on local-scene-aware referring expression generation","volume":"139","author":"Kim","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109673_bib0012","unstructured":"Kingma, D. P., Welling, M. (2013). Auto-encoding variational Bayes. arXiv: 1312.6114."},{"key":"10.1016\/j.neunet.2026.109673_bib0013","series-title":"Proceedings of the second workshop on statistical machine translation","first-page":"228","article-title":"Meteor: An automatic metric for MT evaluation with high levels of correlation with human judgments","author":"Lavie","year":"2007"},{"key":"10.1016\/j.neunet.2026.109673_bib0014","series-title":"Proceedings of the 2022 Conference on empirical methods in natural language processing","first-page":"7241","article-title":"MPLUG: Effective and efficient vision-language learning by cross-modal skip-connections","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109673_bib0015","series-title":"International conference on machine learning","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109673_bib0016","unstructured":"Li, K., Vosselman, G., & Yang, M. Y. (2024). Convincing rationales for visual question answering reasoning. arXiv: 2402.03896."},{"key":"10.1016\/j.neunet.2026.109673_bib0017","unstructured":"Li, L. H., Yatskar, M., Yin, D., Hsieh, C. J., & Chang, K. W. (2019). VisualBERT: A simple and performant baseline for vision and language. arXiv: 1908.03557."},{"key":"10.1016\/j.neunet.2026.109673_bib0018","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"552","article-title":"VQA-E: Explaining, elaborating, and enhancing your answers for visual questions","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.109673_bib0019","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.neunet.2026.109673_bib0020","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0021","series-title":"Proceedings of the 40th Annual meeting of the association for computational linguistics","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.neunet.2026.109673_bib0022","first-page":"857","article-title":"deep structural causal models for tractable counterfactual inference","volume":"33","author":"Pawlowski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0023","series-title":"Proceedings of the 38th international conference on neural information processing systems","first-page":"108116","article-title":"Image textualization: An automatic framework for creating accurate and detailed image descriptions","author":"Pi","year":"2024"},{"key":"10.1016\/j.neunet.2026.109673_bib0024","first-page":"118807","article-title":"Spiqa: A dataset for multimodal question answering on scientific papers","volume":"37","author":"Pramanick","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113672","article-title":"Explainable medical visual question answering via chain of evidence","author":"Qiu","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0026","first-page":"91","article-title":"Faster r-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0027","unstructured":"Tan, H., & Bansal, M. (2019). LXMERT: Learning cross-modality encoder representations from transformers. arXiv: 1908.07490."},{"key":"10.1016\/j.neunet.2026.109673_bib0028","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0029","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4566","article-title":"CIDER: Consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.neunet.2026.109673_bib0030","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W. et al. (2024). QWEN2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv: 2409.12191."},{"key":"10.1016\/j.neunet.2026.109673_bib0031","unstructured":"Wu, J., & Mooney, R. J. (2018). Faithful multimodal explanation for visual question answering. arXiv: 1809.02805."},{"key":"10.1016\/j.neunet.2026.109673_bib0032","article-title":"Explicitly diverse visual question generation","author":"Xie","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109673_bib0033","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TMM.2024.3521709","article-title":"LININ: Logic integrated neural inference network for explanatory visual question answering","volume":"27","author":"Xue","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109673_bib0034","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"2515","article-title":"Variational causal inference network for explanatory visual question answering","author":"Xue","year":"2023"},{"key":"10.1016\/j.neunet.2026.109673_bib0035","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"1875","article-title":"Few-shot multimodal explanation for visual question answering","author":"Xue","year":"2024"},{"issue":"12","key":"10.1016\/j.neunet.2026.109673_bib0036","doi-asserted-by":"crossref","first-page":"7893","DOI":"10.1109\/TPAMI.2024.3398012","article-title":"Integrating neural-symbolic reasoning with variational causal inference network for explanatory visual question answering","volume":"46","author":"Xue","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2026.109673_bib0037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3572833","article-title":"Achieving human parity on visual question answering","volume":"41","author":"Yan","year":"2023","journal-title":"ACM Transactions on Information Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0038","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C. et al. (2025). Qwen3 technical report. arXiv: 2505.09388."},{"key":"10.1016\/j.neunet.2026.109673_bib0039","first-page":"1","article-title":"Understanding the variational lower bound","volume":"22","author":"Yang","year":"2017","journal-title":"Variational Lower Bound, ELBO, Hard Attention"},{"key":"10.1016\/j.neunet.2026.109673_bib0040","doi-asserted-by":"crossref","unstructured":"Ye, Q., Xu, H., Ye, J., Yan, M., Hu, A., Liu, H., Qian, Q., Zhang, J., Huang, F., & Zhou, J. (2023). MPLUG-owl2: Revolutionizing multi-modal large language model with modality collaboration, arXiv: 2311.04257.","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"10.1016\/j.neunet.2026.109673_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"6281","article-title":"Deep modular co-attention networks for visual question answering","author":"Yu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109673_bib0042","article-title":"Acra: An adaptive chain retrieval architecture for multi-modal knowledge-augmented visual question answering","author":"Zhang","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109673_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112629","article-title":"Robust visual question answering utilizing bias instances and label imbalance","volume":"305","author":"Zhao","year":"2024","journal-title":"Knowledge-Based Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011287?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011287?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:48:10Z","timestamp":1793605690000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":43,"alternative-id":["S0893608026011287"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109673","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Context-aware causal reasoning for explanatory visual question answering","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109673","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109673"}}