{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T23:20:15Z","timestamp":1795130415830,"version":"4.10.3"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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","award":["72071001"],"award-info":[{"award-number":["72071001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61860206004"],"award-info":[{"award-number":["61860206004"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,7]]},"DOI":"10.1016\/j.neunet.2025.107390","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T13:29:41Z","timestamp":1742218181000},"page":"107390","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":13,"special_numbering":"C","title":["Multi-level semantic-aware transformer for image captioning"],"prefix":"10.1016","volume":"187","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9020-2006","authenticated-orcid":false,"given":"Qin","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-5055","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107390_b1","series-title":"Computer vision \u2013 ECCV 2016","first-page":"382","article-title":"SPICE: Semantic propositional image caption evaluation","author":"Anderson","year":"2016"},{"key":"10.1016\/j.neunet.2025.107390_b2","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., & Zhang, L. (2018). Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10.1016\/j.neunet.2025.107390_b3","series-title":"2015 IEEE international conference on computer vision","first-page":"2425","article-title":"VQA: Visual question answering","author":"Antol","year":"2015"},{"key":"10.1016\/j.neunet.2025.107390_b4","series-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"10.1016\/j.neunet.2025.107390_b5","series-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.neunet.2025.107390_b6","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.neunet.2021.11.017","article-title":"Event-centric multi-modal fusion method for dense video captioning","volume":"146","author":"Chang","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107390_b7","series-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","first-page":"1724","article-title":"Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.neunet.2025.107390_b8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., & Cucchiara, R. (2020). Meshed-Memory Transformer for Image Captioning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"10.1016\/j.neunet.2025.107390_b9","series-title":"Proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21","first-page":"657","article-title":"TCIC: Theme concepts learning cross language and vision for image captioning","author":"Fan","year":"2021"},{"key":"10.1016\/j.neunet.2025.107390_b10","first-page":"607","article-title":"Attention-aligned transformer for image captioning","author":"Fei","year":"2022"},{"key":"10.1016\/j.neunet.2025.107390_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127651","article-title":"Show, tell and rectify: Boost image caption generation via an output rectifier","volume":"585","author":"Ge","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107390_b12","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., & Lu, H. (2020). Normalized and Geometry-Aware Self-Attention Network for Image Captioning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"10.1016\/j.neunet.2025.107390_b13","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018). Relation Networks for Object Detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00378"},{"key":"10.1016\/j.neunet.2025.107390_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106384","article-title":"Dual-spatial normalized transformer for image captioning","volume":"123","author":"Hu","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.107390_b15","series-title":"Proceedings of the 29th ACM international conference on information & knowledge management","first-page":"535","article-title":"Image captioning with internal and external knowledge","author":"Huang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107390_b16","series-title":"2019 IEEE\/CVF international conference on computer vision","first-page":"4633","article-title":"Attention on attention for image captioning","author":"Huang","year":"2019"},{"key":"10.1016\/j.neunet.2025.107390_b17","doi-asserted-by":"crossref","first-page":"3962","DOI":"10.1109\/TMM.2022.3169061","article-title":"Multi-branch distance-sensitive self-attention network for image captioning","volume":"25","author":"Ji","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107390_b18","doi-asserted-by":"crossref","unstructured":"Ji, J., Luo, Y., Sun, X., Chen, F., Luo, G., Wu, Y., Gao, Y., & Ji, R. (2021). Improving image captioning by leveraging intra-and inter-layer global representation in transformer network. vol. 35, In Proceedings of the AAAI conference on artificial intelligence (pp. 1655\u20131663). 2.","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"10.1016\/j.neunet.2025.107390_b19","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1016\/j.neucom.2022.06.062","article-title":"Relation constraint self-attention for image captioning","volume":"501","author":"Ji","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107390_b20","doi-asserted-by":"crossref","unstructured":"Jiang, W., Ma, L., Jiang, Y.-G., Liu, W., & Zhang, T. (2018). Recurrent Fusion Network for Image captioning. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"10.1016\/j.neunet.2025.107390_b21","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E., & Chen, X. (2020). In Defense of Grid Features for Visual Question Answering. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.01028"},{"issue":"11","key":"10.1016\/j.neunet.2025.107390_b22","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 Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.107390_b23","series-title":"2015 IEEE conference on computer vision and pattern recognition","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"Karpathy","year":"2015"},{"key":"10.1016\/j.neunet.2025.107390_b24","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.neunet.2025.107390_b25","series-title":"Proceedings of the thirty-first international joint conference on artificial intelligence, IJCAI-22","first-page":"1081","article-title":"ER-SAN: Enhanced-adaptive relation self-attention network for image captioning","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2025.107390_b26","series-title":"2022 IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17969","article-title":"Comprehending and ordering semantics for image captioning","author":"Li","year":"2022"},{"issue":"9","key":"10.1016\/j.neunet.2025.107390_b27","doi-asserted-by":"crossref","first-page":"2070","DOI":"10.1109\/TPAMI.2018.2852750","article-title":"Deep collaborative embedding for social image understanding","volume":"41","author":"Li","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107390_b28","series-title":"2019 IEEE\/CVF international conference on computer vision","first-page":"8927","article-title":"Entangled transformer for image captioning","author":"Li","year":"2019"},{"issue":"5","key":"10.1016\/j.neunet.2025.107390_b29","first-page":"5910","article-title":"Cross modification attention-based deliberation model for image captioning","volume":"53","author":"Lian","year":"2023","journal-title":"Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies"},{"key":"10.1016\/j.neunet.2025.107390_b30","doi-asserted-by":"crossref","first-page":"4389","DOI":"10.1109\/TMM.2023.3322329","article-title":"IcoCap: Improving video captioning by compounding images","volume":"26","author":"Liang","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107390_b31","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.2025.107390_b32","series-title":"2017 IEEE conference on computer vision and pattern recognition","first-page":"3242","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"Lu","year":"2017"},{"key":"10.1016\/j.neunet.2025.107390_b33","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2286","article-title":"Dual-level collaborative transformer for image captioning","volume":"vol. 35","author":"Luo","year":"2021"},{"key":"10.1016\/j.neunet.2025.107390_b34","series-title":"2023 IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23359","article-title":"Semantic-conditional diffusion networks for image captioning*","author":"Luo","year":"2023"},{"key":"10.1016\/j.neunet.2025.107390_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109420","article-title":"Towards local visual modeling for image captioning","volume":"138","author":"Ma","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107390_b36","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":"2023","journal-title":"IEEE Transactions on Multimedia"},{"issue":"5","key":"10.1016\/j.neunet.2025.107390_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3580366","article-title":"Bottom-up and top-down object inference networks for image captioning","volume":"19","author":"Pan","year":"2023","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.neunet.2025.107390_b38","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., & Mei, T. (2020). X-Linear Attention Networks for Image Captioning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"10.1016\/j.neunet.2025.107390_b39","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.2025.107390_b40","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics: student research workshop, ACL 2020, online, July 5-10, 2020","first-page":"95","article-title":"Feature difference makes sense: A medical image captioning model exploiting feature difference and tag information","author":"Park","year":"2020"},{"key":"10.1016\/j.neunet.2025.107390_b41","series-title":"Advances in neural information processing systems","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"vol. 28","author":"Ren","year":"2015"},{"key":"10.1016\/j.neunet.2025.107390_b42","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1016\/j.csbj.2024.04.004","article-title":"Exploring simple triplet representation learning","volume":"23","author":"Ren","year":"2024","journal-title":"Computational and Structural Biotechnology Journal"},{"issue":"3","key":"10.1016\/j.neunet.2025.107390_b43","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1049\/cit2.12216","article-title":"Weakly supervised machine learning","volume":"8","author":"Ren","year":"2023","journal-title":"CAAI Transactions on Intelligence Technology"},{"key":"10.1016\/j.neunet.2025.107390_b44","series-title":"2017 IEEE conference on computer vision and pattern recognition","first-page":"1179","article-title":"Self-critical sequence training for image captioning","author":"Rennie","year":"2017"},{"key":"10.1016\/j.neunet.2025.107390_b45","series-title":"Self-attention with relative position representations","author":"Shaw","year":"2018"},{"key":"10.1016\/j.neunet.2025.107390_b46","series-title":"Advances in neural information processing systems","article-title":"Sequence to sequence learning with neural networks","volume":"vol. 27","author":"Sutskever","year":"2014"},{"issue":"8","key":"10.1016\/j.neunet.2025.107390_b47","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1109\/TPAMI.2016.2608882","article-title":"Tri-clustered tensor completion for social-aware image tag refinement","volume":"39","author":"Tang","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107390_b48","series-title":"Advances in neural information processing systems","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2025.107390_b49","series-title":"2015 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.2025.107390_b50","series-title":"2015 IEEE conference on computer vision and pattern recognition","first-page":"3156","article-title":"Show and tell: A neural image caption generator","author":"Vinyals","year":"2015"},{"key":"10.1016\/j.neunet.2025.107390_b51","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12176","article-title":"Show, recall, and tell: Image captioning with recall mechanism","volume":"vol. 34","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107390_b52","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.neunet.2023.03.010","article-title":"LCM-captioner: A lightweight text-based image captioning method with collaborative mechanism between vision and text","volume":"162","author":"Wang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107390_b53","doi-asserted-by":"crossref","first-page":"2966","DOI":"10.1109\/TMM.2022.3154149","article-title":"A text-guided generation and refinement model for image captioning","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107390_b54","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.1109\/TMM.2020.3011317","article-title":"Fine-grained image captioning with global-local discriminative objective","volume":"23","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107390_b55","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.neunet.2022.01.011","article-title":"Dual global enhanced transformer for image captioning","volume":"148","author":"Xian","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107390_b56","series-title":"2017 IEEE conference on computer vision and pattern recognition","first-page":"5987","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"10.1016\/j.neunet.2025.107390_b57","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., & Cai, J. (2019). Auto-Encoding Scene Graphs for Image Captioning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10685\u201310694).","DOI":"10.1109\/CVPR.2019.01094"},{"key":"10.1016\/j.neunet.2025.107390_b58","series-title":"Computer vision \u2013 ECCV 2018","first-page":"711","article-title":"Exploring visual relationship for image captioning","author":"Yao","year":"2018"},{"issue":"12","key":"10.1016\/j.neunet.2025.107390_b59","doi-asserted-by":"crossref","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","article-title":"Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering","volume":"29","author":"Yu","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107390_b60","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1109\/TMM.2021.3072479","article-title":"Dual attention on pyramid feature maps for image captioning","volume":"24","author":"Yu","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107390_b61","series-title":"Proceedings of the thirty-first international joint conference on artificial intelligence","first-page":"1608","article-title":"S2 transformer for image captioning","author":"Zeng","year":"2022"},{"issue":"2","key":"10.1016\/j.neunet.2025.107390_b62","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":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107390_b63","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sun, X., Luo, Y., Ji, J., Zhou, Y., Wu, Y., Huang, F., & Ji, R. (2021). RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 15465\u201315474).","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"10.1016\/j.neunet.2025.107390_b64","doi-asserted-by":"crossref","first-page":"3101","DOI":"10.1109\/TMM.2021.3093725","article-title":"Exploring pairwise relationships adaptively from linguistic context in image captioning","volume":"24","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"issue":"8","key":"10.1016\/j.neunet.2025.107390_b65","doi-asserted-by":"crossref","first-page":"4257","DOI":"10.1109\/TCSVT.2023.3243725","article-title":"Cross on cross attention: Deep fusion transformer for image captioning","volume":"33","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"1","key":"10.1016\/j.neunet.2025.107390_b66","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/TIP.2018.2855415","article-title":"More is better: Precise and detailed image captioning using online positive recall and missing concepts mining","volume":"28","author":"Zhang","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"10.1016\/j.neunet.2025.107390_b67","doi-asserted-by":"crossref","first-page":"5552","DOI":"10.1109\/TIP.2019.2916757","article-title":"CAM-RNN: Co-attention model based RNN for video captioning","volume":"28","author":"Zhao","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.107390_b68","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1109\/TIP.2020.3042086","article-title":"Cross-domain image captioning via cross-modal retrieval and model adaptation","volume":"30","author":"Zhao","year":"2021","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025002692?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025002692?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:11:41Z","timestamp":1762315901000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025002692"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":68,"alternative-id":["S0893608025002692"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107390","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-level semantic-aware transformer for image captioning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107390","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107390"}}