{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:31:51Z","timestamp":1772094711683,"version":"3.50.1"},"reference-count":76,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.knosys.2026.115366","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:47:39Z","timestamp":1768981659000},"page":"115366","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Omniscient bottom-up double-stream symmetric network for image captioning"],"prefix":"10.1016","volume":"337","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0883-1316","authenticated-orcid":false,"given":"Jianchao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9237-7205","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2006-5760","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115366_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107313","article-title":"Reasoning like humans: on dynamic attention prior in image captioning","volume":"228","author":"Wang","year":"2021","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110515","article-title":"VABDC-Net: a framework for visual-caption sentiment recognition via spatio-depth visual attention and bi-directional caption processing","volume":"269","author":"Pandey","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0003","doi-asserted-by":"crossref","unstructured":"H. Zhang, S. Sugawara, A. Aizawa, L. Zhou, R. Sasano, K. Takeda, Cross-modal similarity-based curriculum learning for image captioning, arXiv preprint arXiv: 2212.07075(2022).","DOI":"10.18653\/v1\/2022.emnlp-main.516"},{"key":"10.1016\/j.knosys.2026.115366_bib0004","series-title":"14th Asian Conference on Computer Vision, Revised Selected Papers, Part VI 14 (ACCV)","first-page":"587","article-title":"Multivariate attention network for image captioning","author":"Wang","year":"2019"},{"key":"10.1016\/j.knosys.2026.115366_bib0005","first-page":"11135","article-title":"Image captioning: transforming objects into words","volume":"32","author":"Herdade","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0006","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4634","article-title":"Attention on attention for image captioning","author":"Huang","year":"2019"},{"key":"10.1016\/j.knosys.2026.115366_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117174","article-title":"Geometry attention transformer with position-aware LSTMs for image captioning","volume":"201","author":"Wang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115366_bib0008","doi-asserted-by":"crossref","first-page":"1785","DOI":"10.1109\/TNNLS.2022.3185320","article-title":"Adaptive semantic-enhanced transformer for image captioning","volume":"35","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10578","article-title":"Meshed-memory transformer for image captioning","author":"Cornia","year":"2020"},{"key":"10.1016\/j.knosys.2026.115366_bib0010","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"684","article-title":"Exploring visual relationship for image captioning","author":"Yao","year":"2018"},{"key":"10.1016\/j.knosys.2026.115366_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10685","article-title":"Auto-encoding scene graphs for image captioning","author":"Yang","year":"2019"},{"issue":"6","key":"10.1016\/j.knosys.2026.115366_bib0012","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1109\/TCSVT.2021.3107035","article-title":"Region-aware image captioning via interaction learning","volume":"32","author":"Liu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.115366_bib0013","series-title":"Proceedings of the International Joint Conferences on Artificial Intelligence","article-title":"S2 Transformer for image captioning","volume":"5","author":"Zeng","year":"2022"},{"key":"10.1016\/j.knosys.2026.115366_bib0014","doi-asserted-by":"crossref","first-page":"3723","DOI":"10.1109\/TMM.2022.3164787","article-title":"Knowing what it is: semantic-enhanced dual attention transformer","volume":"25","author":"Ma","year":"2022","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.knosys.2026.115366_bib0015","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","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.knosys.2026.115366_bib0016","series-title":"European Conference on Computer Vision (ECCV)","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.knosys.2026.115366_bib0017","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions","volume":"2","author":"Young","year":"2014","journal-title":"Trans. Assoc. Comput. Linguist."},{"issue":"1","key":"10.1016\/j.knosys.2026.115366_bib0018","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1007\/s11263-016-0965-7","article-title":"Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models","volume":"123","author":"Plummer","year":"2017","journal-title":"IJCV"},{"key":"10.1016\/j.knosys.2026.115366_bib0019","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.knosys.2026.115366_bib0020","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0021","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3588","article-title":"Relation networks for object detection","author":"Hu","year":"2018"},{"key":"10.1016\/j.knosys.2026.115366_bib0022","series-title":"Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (ACL)","first-page":"747","article-title":"Midge: generating image descriptions from computer vision detections","author":"Mitchell","year":"2012"},{"issue":"12","key":"10.1016\/j.knosys.2026.115366_bib0023","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","article-title":"Babytalk: understanding and generating simple image descriptions","volume":"35","author":"Kulkarni","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"10.1016\/j.knosys.2026.115366_bib0024","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.1109\/JPROC.2010.2050411","article-title":"I2t: Image parsing to text description","volume":"98","author":"Yao","year":"2010","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.knosys.2026.115366_bib0025","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3156","article-title":"Show and tell: a neural image caption generator","author":"Vinyals","year":"2015"},{"key":"10.1016\/j.knosys.2026.115366_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":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0027","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8888","article-title":"Reflective decoding network for image captioning","author":"Ke","year":"2019"},{"key":"10.1016\/j.knosys.2026.115366_bib0028","first-page":"11230","article-title":"Adaptively aligned image captioning via adaptive attention time","volume":"32","author":"Huang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4808","article-title":"Show, edit and tell: a framework for editing image captions","author":"Sammani","year":"2020"},{"key":"10.1016\/j.knosys.2026.115366_bib0030","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2621","article-title":"Hierarchy parsing for image captioning","author":"Yao","year":"2019"},{"issue":"8","key":"10.1016\/j.knosys.2026.115366_bib0031","doi-asserted-by":"crossref","first-page":"3118","DOI":"10.1109\/TCSVT.2020.3036860","article-title":"Noise augmented double-stream graph convolutional networks for image captioning","volume":"31","author":"Wu","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.115366_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15565","article-title":"Visual abductive reasoning","author":"Liang","year":"2022"},{"key":"10.1016\/j.knosys.2026.115366_bib0033","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"8498","article-title":"MoS2: mixture of scale and shift experts for text-only video captioning","author":"Jia","year":"2024"},{"key":"10.1016\/j.knosys.2026.115366_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3195","article-title":"Ok-vqa: a visual question answering benchmark requiring external knowledge","author":"Marino","year":"2019"},{"issue":"10","key":"10.1016\/j.knosys.2026.115366_bib0035","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":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"10.1016\/j.knosys.2026.115366_bib0036","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.1109\/TCSVT.2020.2991866","article-title":"Multi-level knowledge injecting for visual commonsense reasoning","volume":"31","author":"Wen","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.115366_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118669","article-title":"Image captioning for effective use of language models in knowledge-based visual question answering","volume":"212","author":"Salaberria","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115366_bib0038","unstructured":"P. Zeng, H. Zhang, L. Gao, X. Li, J. Qian, H.T. Shen, Visual commonsense-aware representation network for video captioning, arXiv preprint arXiv: 2211.09469(2022)."},{"key":"10.1016\/j.knosys.2026.115366_bib0039","series-title":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"283","article-title":"Improving image captioning by leveraging knowledge graphs","author":"Zhou","year":"2019"},{"key":"10.1016\/j.knosys.2026.115366_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9837","article-title":"Open-book video captioning with retrieve-copy-generate network","author":"Zhang","year":"2021"},{"key":"10.1016\/j.knosys.2026.115366_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111433","article-title":"Top-down framework for weakly-supervised grounded image captioning","volume":"287","author":"Cai","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111503","article-title":"MiC: Image-text matching in circles with cross-modal generative knowledge enhancement","volume":"289","author":"Pu","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111056","article-title":"Parallel encoder\u2013decoder framework for image captioning","volume":"282","author":"Saeidimesineh","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0044","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.knosys.2026.115366_bib0045","series-title":"International Conference on Machine Learning","first-page":"4651","article-title":"Perceiver: general perception with iterative attention","author":"Jaegle","year":"2021"},{"issue":"11","key":"10.1016\/j.knosys.2026.115366_bib0046","doi-asserted-by":"crossref","first-page":"7706","DOI":"10.1109\/TCSVT.2022.3181490","article-title":"Double-stream position learning transformer network for image captioning","volume":"32","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.115366_bib0047","unstructured":"A.K. Boyat, B.K. Joshi, A review paper: noise models in digital image processing, arXiv preprint arXiv: 1505.03489(2015)."},{"issue":"6","key":"10.1016\/j.knosys.2026.115366_bib0048","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1089\/big.2021.0262","article-title":"Dual position relationship transformer for image captioning","volume":"10","author":"Wang","year":"2022","journal-title":"Big Data"},{"issue":"3","key":"10.1016\/j.knosys.2026.115366_bib0049","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"10.1016\/j.knosys.2026.115366_bib0050","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7008","article-title":"Self-critical sequence training for image captioning","author":"Rennie","year":"2017"},{"key":"10.1016\/j.knosys.2026.115366_bib0051","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"4894","article-title":"Boosting image captioning with attributes","author":"Yao","year":"2017"},{"issue":"1","key":"10.1016\/j.knosys.2026.115366_bib0052","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TCSVT.2021.3067449","article-title":"Task-adaptive attention for image captioning","volume":"32","author":"Yan","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.knosys.2026.115366_bib0053","doi-asserted-by":"crossref","first-page":"2429","DOI":"10.1007\/s00521-022-07726-z","article-title":"Hierarchical decoding with latent context for image captioning","volume":"35","author":"Zhang","year":"2023","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"10.1016\/j.knosys.2026.115366_bib0054","doi-asserted-by":"crossref","first-page":"190","DOI":"10.3390\/sym15010190","article-title":"Full-memory transformer for image captioning","volume":"15","author":"Lu","year":"2023","journal-title":"Symmetry"},{"key":"10.1016\/j.knosys.2026.115366_bib0055","doi-asserted-by":"crossref","first-page":"3920","DOI":"10.1109\/TIP.2022.3177318","article-title":"Visual cluster grounding for image captioning","volume":"31","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.115366_bib0056","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11039","article-title":"Haav: hierarchical aggregation of augmented views for image captioning","author":"Kuo","year":"2023"},{"issue":"8","key":"10.1016\/j.knosys.2026.115366_bib0057","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1109\/TMM.2019.2951226","article-title":"Show, tell, and polish: ruminant decoding for image captioning","volume":"22","author":"Guo","year":"2019","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.knosys.2026.115366_bib0058","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16","first-page":"353","article-title":"Learning to generate grounded visual captions without localization supervision","author":"Ma","year":"2020"},{"key":"10.1016\/j.knosys.2026.115366_bib0059","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"1966","article-title":"Distributed attention for grounded image captioning","author":"Chen","year":"2021"},{"key":"10.1016\/j.knosys.2026.115366_bib0060","first-page":"1865","article-title":"Prophet attention: predicting attention with future attention","volume":"33","author":"Liu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0061","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4777","article-title":"More grounded image captioning by distilling image-text matching model","author":"Zhou","year":"2020"},{"key":"10.1016\/j.knosys.2026.115366_bib0062","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"Karpathy","year":"2015"},{"key":"10.1016\/j.knosys.2026.115366_bib0063","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10267","article-title":"In defense of grid features for visual question answering","author":"Jiang","year":"2020"},{"key":"10.1016\/j.knosys.2026.115366_bib0064","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.115366_bib0065","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"2","key":"10.1016\/j.knosys.2026.115366_bib0066","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10.1016\/j.knosys.2026.115366_bib0067","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.knosys.2016.02.001","article-title":"Study on density peaks clustering based on k-nearest neighbors and principal component analysis","volume":"99","author":"Du","year":"2016","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115366_bib0068","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL)","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.knosys.2026.115366_bib0069","series-title":"Proceedings of the Ninth Workshop on Statistical Machine Translation","first-page":"376","article-title":"Meteor universal: language specific translation evaluation for any target language","author":"Denkowski","year":"2014"},{"key":"10.1016\/j.knosys.2026.115366_bib0070","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.knosys.2026.115366_bib0071","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4566","article-title":"Cider: consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.knosys.2026.115366_bib0072","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.115366_bib0073","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17969","article-title":"Beyond a pre-trained object detector: cross-modal textual and visual context for image captioning","author":"Kuo","year":"2022"},{"key":"10.1016\/j.knosys.2026.115366_bib0074","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.knosys.2026.115366_bib0075","unstructured":"J. Devlin, Bert: pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv: 1810.04805(2018)."},{"key":"10.1016\/j.knosys.2026.115366_bib0076","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5579","article-title":"Vinvl: revisiting visual representations in vision-language models","author":"Zhang","year":"2021"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126001097?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126001097?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T07:44:02Z","timestamp":1772091842000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126001097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":76,"alternative-id":["S0950705126001097"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115366","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Omniscient bottom-up double-stream symmetric network for image captioning","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115366","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115366"}}