{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T04:52:27Z","timestamp":1783831947088,"version":"3.55.0"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"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"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113421","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T17:04:48Z","timestamp":1772730288000},"page":"113421","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Refined generation-based framework for consistent and reliable visual question answering"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4354-8371","authenticated-orcid":false,"given":"Quanxing","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8313-5749","authenticated-orcid":false,"given":"Ling","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5242-0467","authenticated-orcid":false,"given":"Xian","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8153-9977","authenticated-orcid":false,"given":"Feifei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-5277","authenticated-orcid":false,"given":"Jinyu","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6186-0520","authenticated-orcid":false,"given":"Xiaohan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1769-6126","authenticated-orcid":false,"given":"Rubing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113421_bib0001","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"2425","article-title":"VQA: visual question answering","author":"Agrawal","year":"2015"},{"key":"10.1016\/j.patcog.2026.113421_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112163","article-title":"OpenCIL: benchmarking out-of-distribution detection in class incremental learning","volume":"171","author":"Miao","year":"2026","journal-title":"Pattern Recognit."},{"issue":"7","key":"10.1016\/j.patcog.2026.113421_bib0003","doi-asserted-by":"crossref","first-page":"4795","DOI":"10.1007\/s11263-025-02407-5","article-title":"Fully decoupled end-to-end person search: an approach without conflicting objectives","volume":"133","author":"Zhang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"issue":"12","key":"10.1016\/j.patcog.2026.113421_bib0004","doi-asserted-by":"crossref","first-page":"11152","DOI":"10.1109\/TPAMI.2024.3458921","article-title":"Learning from human attention for attribute-assisted visual recognition","volume":"46","author":"Bai","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113421_bib0005","series-title":"Proc. Int. Conf. Comput. Linguist.","first-page":"3936","article-title":"StoryLLaVA: enhancing visual storytelling with multi-modal large language models","author":"Yang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113421_bib0006","series-title":"Proc. AAAI Conf. Artif. Intell.","first-page":"3724","article-title":"Refined semantic enhancement towards frequency diffusion for video captioning","author":"Zhong","year":"2023"},{"issue":"10","key":"10.1016\/j.patcog.2026.113421_bib0007","doi-asserted-by":"crossref","first-page":"326:1","DOI":"10.1145\/3679203","article-title":"Action-aware linguistic skeleton optimization network for non-autoregressive video captioning","volume":"20","author":"Chen","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.patcog.2026.113421_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113105","article-title":"Ask and focus more: question-prompt uncertainty allocation for dual-controllable video captioning","volume":"175","author":"Chen","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113421_bib0009","series-title":"Proc. ACM Int. Conf. Multimedia","first-page":"1206","article-title":"MPT: multi-grained prompt tuning for text-video retrieval","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113421_bib0010","doi-asserted-by":"crossref","first-page":"9597","DOI":"10.1109\/TMM.2023.3256092","article-title":"Progressive local filter pruning for image retrieval acceleration","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113421_bib0011","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"6325","article-title":"Making the V in VQA matter: elevating the role of image understanding in visual question answering","author":"Goyal","year":"2017"},{"issue":"10","key":"10.1016\/j.patcog.2026.113421_bib0012","doi-asserted-by":"crossref","first-page":"4362","DOI":"10.1109\/TNNLS.2020.3017530","article-title":"Rich visual knowledge-based augmentation network for visual question answering","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113421_bib0013","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"14337","article-title":"DiN: diffusion model for robust medical VQA with semantic noisy labels","author":"Guo","year":"2025"},{"key":"10.1016\/j.patcog.2026.113421_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111394","article-title":"Unbiased VQA via modal information interaction and question transformation","volume":"162","author":"Peng","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113421_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111129","article-title":"Enhancing robust VQA via contrastive and self-supervised learning","volume":"159","author":"Cao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113421_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109339","article-title":"Learning visual question answering on controlled semantic noisy labels","volume":"138","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113421_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108455","article-title":"Text-instance graph: exploring the relational semantics for text-based visual question answering","volume":"124","author":"Li","year":"2022","journal-title":"Pattern Recognit."},{"issue":"11","key":"10.1016\/j.patcog.2026.113421_bib0018","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut learning in deep neural networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113421_bib0019","series-title":"Proc. Eur. Conf. Comput. Vis.","first-page":"148","article-title":"Reliable visual question answering: abstain rather than answer incorrectly","author":"Whitehead","year":"2022"},{"key":"10.1016\/j.patcog.2026.113421_bib0020","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"24049","article-title":"Improving selective visual question answering by learning from your peers","author":"Dancette","year":"2023"},{"key":"10.1016\/j.patcog.2026.113421_bib0021","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"6649","article-title":"Cycle-consistency for robust visual question answering","author":"Shah","year":"2019"},{"key":"10.1016\/j.patcog.2026.113421_bib0022","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"5089","article-title":"Maintaining reasoning consistency in compositional visual question answering","author":"Jing","year":"2022"},{"key":"10.1016\/j.patcog.2026.113421_bib0023","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"10854","article-title":"Consistency and uncertainty: identifying unreliable responses from black-box vision-language models for selective visual question answering","author":"Khan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113421_bib0024","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","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.patcog.2026.113421_bib0025","series-title":"Proc. Int. Joint Conf. Artif. Intell.","first-page":"906","article-title":"From pixels to objects: cubic visual attention for visual question answering","author":"Song","year":"2018"},{"key":"10.1016\/j.patcog.2026.113421_bib0026","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"6281","article-title":"Deep modular Co-attention networks for visual question answering","author":"Yu","year":"2019"},{"key":"10.1016\/j.patcog.2026.113421_bib0027","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"4971","article-title":"Don\u2019t just assume; look and answer: overcoming priors for visual question answering","author":"Agrawal","year":"2018"},{"key":"10.1016\/j.patcog.2026.113421_bib0028","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","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.patcog.2026.113421_bib0029","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"1554","article-title":"Beyond question-based biases: assessing multimodal shortcut learning in visual question answering","author":"Dancette","year":"2021"},{"key":"10.1016\/j.patcog.2026.113421_bib0030","series-title":"Adv. Neural Inf. Process. Syst.","first-page":"20346","article-title":"Human-adversarial visual question answering","author":"Sheng","year":"2021"},{"key":"10.1016\/j.patcog.2026.113421_bib0031","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"2022","article-title":"Adversarial VQA: a new benchmark for evaluating the robustness of VQA models","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113421_bib0032","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"3195","article-title":"OK-VQA: a visual question answering benchmark requiring external knowledge","author":"Marino","year":"2019"},{"key":"10.1016\/j.patcog.2026.113421_bib0033","series-title":"Findings Conf. Eur. Chapter Assoc. Comput. Linguist.","first-page":"1171","article-title":"Reassessing evaluation practices in visual question answering: a case study on out-of-distribution generalization","author":"Agrawal","year":"2023"},{"key":"10.1016\/j.patcog.2026.113421_bib0034","series-title":"Proc. Annu. Meet. Assoc. Comput. Linguist.","first-page":"5684","article-title":"Selective question answering under domain shift","author":"Kamath","year":"2020"},{"key":"10.1016\/j.patcog.2026.113421_bib0035","series-title":"Proc. Annu. Meet. Assoc. Comput. Linguist.","first-page":"7918","article-title":"Iterative edit-based unsupervised sentence simplification","author":"Kumar","year":"2020"},{"key":"10.1016\/j.patcog.2026.113421_bib0036","series-title":"Proc. Int. Conf. Mach. Learn.","first-page":"2151","article-title":"SelectiveNet: a deep neural network with an integrated reject option","author":"Geifman","year":"2019"},{"key":"10.1016\/j.patcog.2026.113421_bib0037","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"7720","article-title":"Versatile diffusion: text, images and variations all in one diffusion model","author":"Xu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113421_bib0038","series-title":"Proc. Int. Conf. Learn. Represent.","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2022"},{"key":"10.1016\/j.patcog.2026.113421_bib0039","series-title":"Proc. Int. Conf. Learn. Represent.","article-title":"MoVie: revisiting modulated convolutions for visual counting and beyond","author":"Nguyen","year":"2021"},{"key":"10.1016\/j.patcog.2026.113421_bib0040","series-title":"Proc. Int. Conf. Mach. Learn.","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113421_bib0041","series-title":"Proc. Int. Conf. Mach. Learn.","first-page":"23318","article-title":"OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113421_bib0042","series-title":"Adv. Neural Inf. Process. Syst.","first-page":"4878","article-title":"Selective classification for deep neural networks","author":"Geifman","year":"2017"},{"key":"10.1016\/j.patcog.2026.113421_bib0043","series-title":"Proc. Int. Conf. Learn. Represent.","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2017"},{"key":"10.1016\/j.patcog.2026.113421_bib0044","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"21","article-title":"Stacked attention networks for image question answering","author":"Yang","year":"2016"},{"key":"10.1016\/j.patcog.2026.113421_bib0045","series-title":"Proc. Conf. Empir. Methods Nat. Lang. Process.","first-page":"5099","article-title":"LXMERT: learning cross-modality encoder representations from transformers","author":"Tan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113421_bib0046","series-title":"Adv. Neural Inf. Process. Syst.","first-page":"8024","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.1016\/j.patcog.2026.113421_bib0047","series-title":"Proc. Int. Conf. Mach. Learn.","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.patcog.2026.113421_bib0048","series-title":"Proc. Int. Conf. Learn. Represent.","article-title":"The curious case of neural text degeneration","author":"Holtzman","year":"2020"},{"key":"10.1016\/j.patcog.2026.113421_bib0049","series-title":"Proc. Int. Conf. Mach. Learn.","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113421_bib0050","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"26296","article-title":"Improved visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113421_bib0051","unstructured":"P. Wang, S. Bai, S. Tan, S. Wang, Z. Fan, J. Bai, K. Chen, X. Liu, J. Wang, W. Ge, Y. Fan, K. Dang, M. Du, X. Ren, R. Men, D. Liu, C. Zhou, J. Zhou, J. Lin, Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution, (2024). arXiv: 2409.12191."},{"key":"10.1016\/j.patcog.2026.113421_bib0052","unstructured":"F. Li, R. Zhang, H. Zhang, Y. Zhang, B. Li, W. Li, Z. Ma, C. Li, LLaVA-NeXT-interleave: tackling multi-image, video, and 3D in large multimodal models, (2024). arXiv: 2407.07895."},{"key":"10.1016\/j.patcog.2026.113421_bib0053","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"10000","article-title":"SQuINTing at VQA models: introspecting VQA models with sub-questions","author":"Selvaraju","year":"2020"},{"key":"10.1016\/j.patcog.2026.113421_bib0054","series-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Interv.","first-page":"386","article-title":"Consistency-preserving visual question answering in medical imaging","author":"Tascon-Morales","year":"2022"},{"key":"10.1016\/j.patcog.2026.113421_bib0055","series-title":"Proc. AAAI Conf. Artif. Intell.","first-page":"26290","article-title":"Evaluating image hallucination in text-to-image generation with question-answering","author":"Lim","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003869?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003869?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:04:24Z","timestamp":1779383064000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326003869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":55,"alternative-id":["S0031320326003869"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113421","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Refined generation-based framework for consistent and reliable visual question answering","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113421","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":"113421"}}