{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:00:38Z","timestamp":1781006438123,"version":"3.54.1"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116008","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T23:57:07Z","timestamp":1777161427000},"page":"116008","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adaptive dynamic graph interaction network for fine-grained image\u2013text retrieval"],"prefix":"10.1016","volume":"345","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8158-3560","authenticated-orcid":false,"given":"Pengyang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8766-0647","authenticated-orcid":false,"given":"Mayire","family":"Ibrayim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alkut","family":"Mardan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7817-1290","authenticated-orcid":false,"given":"Peichao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.knosys.2026.116008_b1","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.knosys.2026.116008_b2","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.knosys.2026.116008_b3","article-title":"Devise: A deep visual-semantic embedding model","volume":"26","author":"Frome","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116008_b4","series-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017"},{"key":"10.1016\/j.knosys.2026.116008_b5","doi-asserted-by":"crossref","unstructured":"K.-H. Lee, X. Chen, G. Hua, H. Hu, X. He, Stacked cross attention for image-text matching, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 201\u2013216.","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"10.1016\/j.knosys.2026.116008_b6","doi-asserted-by":"crossref","unstructured":"K. Li, Y. Zhang, K. Li, Y. Li, Y. Fu, Visual semantic reasoning for image-text matching, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4654\u20134662.","DOI":"10.1109\/ICCV.2019.00475"},{"key":"10.1016\/j.knosys.2026.116008_b7","doi-asserted-by":"crossref","unstructured":"H. Chen, G. Ding, X. Liu, Z. Lin, J. Liu, J. Han, Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12655\u201312663.","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"10.1016\/j.knosys.2026.116008_b8","first-page":"1218","article-title":"Similarity reasoning and filtration for image-text matching","volume":"vol. 35","author":"Diao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116008_b9","doi-asserted-by":"crossref","unstructured":"Z. Fu, Z. Mao, Y. Song, Y. Zhang, Learning semantic relationship among instances for image-text matching, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15159\u201315168.","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"10.1016\/j.knosys.2026.116008_b10","doi-asserted-by":"crossref","unstructured":"Z. Wang, Z. Gao, K. Guo, Y. Yang, X. Wang, H.T. Shen, Multilateral semantic relations modeling for image text retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2830\u20132839.","DOI":"10.1109\/CVPR52729.2023.00277"},{"issue":"4","key":"10.1016\/j.knosys.2026.116008_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3499027","article-title":"Cross-modal graph matching network for image-text retrieval","volume":"18","author":"Cheng","year":"2022","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.knosys.2026.116008_b12","doi-asserted-by":"crossref","unstructured":"C. Liu, Z. Mao, T. Zhang, H. Xie, B. Wang, Y. Zhang, Graph structured network for image-text matching, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10921\u201310930.","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"10.1016\/j.knosys.2026.116008_b13","doi-asserted-by":"crossref","unstructured":"K. Pham, C. Huynh, S.-N. Lim, A. Shrivastava, Composing object relations and attributes for image-text matching, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14354\u201314363.","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"10.1016\/j.knosys.2026.116008_b14","series-title":"International Conference on Computer Engineering and Networks","first-page":"274","article-title":"Cross attention graph matching network for image-text retrieval","author":"Yang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116008_b15","first-page":"13448","article-title":"Graphadapter: Tuning vision-language models with dual knowledge graph","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116008_b16","doi-asserted-by":"crossref","unstructured":"M. Munir, W. Avery, M.M. Rahman, R. Marculescu, Greedyvig: Dynamic axial graph construction for efficient vision gnns, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 6118\u20136127.","DOI":"10.1109\/CVPR52733.2024.00585"},{"key":"10.1016\/j.knosys.2026.116008_b17","doi-asserted-by":"crossref","unstructured":"M. Munir, M.M. Rahman, R. Marculescu, AdaptViG: Adaptive Vision GNN with Exponential Decay Gating, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2026, pp. 440\u2013450.","DOI":"10.1109\/WACV61042.2026.00051"},{"key":"10.1016\/j.knosys.2026.116008_b18","doi-asserted-by":"crossref","unstructured":"Z. Pan, F. Wu, B. Zhang, Fine-grained image-text matching by cross-modal hard aligning network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19275\u201319284.","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"10.1016\/j.knosys.2026.116008_b19","series-title":"A new fine-grained alignment method for image-text matching","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116008_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105923","article-title":"Cross-modal information balance-aware reasoning network for image-text retrieval","volume":"120","author":"Qin","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116008_b21","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.knosys.2026.116008_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111096","article-title":"Cross-modal independent matching network for image-text retrieval","volume":"159","author":"Ke","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116008_b23","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.2026.116008_b24","series-title":"International Conference on Knowledge Science, Engineering and Management","first-page":"433","article-title":"PolyBERT: Fine-tuned poly encoder BERT-based model for word sense disambiguation","author":"Xia","year":"2025"},{"key":"10.1016\/j.knosys.2026.116008_b25","unstructured":"D.K. Sumanathilaka, N. Micallef, J. Hough, Can llms assist with ambiguity? a quantitative evaluation of various large language models on word sense disambiguation, in: Proceedings of the First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security, 2024, pp. 97\u2013108."},{"key":"10.1016\/j.knosys.2026.116008_b26","series-title":"Exploring the word sense disambiguation capabilities of large language models","author":"Basile","year":"2025"},{"key":"10.1016\/j.knosys.2026.116008_b27","unstructured":"D. Vollmers, H. Zahera, D. Moussallem, A.-C.N. Ngomo, Contextual augmentation for entity linking using large language models, in: Proceedings of the 31st International Conference on Computational Linguistics, 2025, pp. 8535\u20138545."},{"key":"10.1016\/j.knosys.2026.116008_b28","doi-asserted-by":"crossref","unstructured":"R. Kibria, S.I.U. Dipta, M.A. Adnan, On functional competence of llms for linguistic disambiguation, in: Proceedings of the 28th Conference on Computational Natural Language Learning, 2024, pp. 143\u2013160.","DOI":"10.18653\/v1\/2024.conll-1.12"},{"issue":"04","key":"10.1016\/j.knosys.2026.116008_b29","doi-asserted-by":"crossref","DOI":"10.1142\/S1464333225500139","article-title":"Bayesian gaussian process predictions of chongqing carbon market prices","volume":"27","author":"Jin","year":"2025","journal-title":"J. Environ. Assess. Policy Manag."},{"issue":"01","key":"10.1016\/j.knosys.2026.116008_b30","article-title":"Predicting the trading volume of the thermal coal futures through Gaussian process regressions","volume":"19","author":"Jin","year":"2026","journal-title":"J. Uncertain Syst."},{"issue":"03","key":"10.1016\/j.knosys.2026.116008_b31","doi-asserted-by":"crossref","DOI":"10.1142\/S2424786325500033","article-title":"China commodity price index (CCPI) forecasting via the neural network","volume":"12","author":"Jin","year":"2025","journal-title":"Int. J. Financ. Eng."},{"key":"10.1016\/j.knosys.2026.116008_b32","first-page":"1","article-title":"Employing gaussian process regression with bayesian inference to predict the living-materials producer price index in China","author":"Jin","year":"2025","journal-title":"Qual. Quant."},{"issue":"04","key":"10.1016\/j.knosys.2026.116008_b33","article-title":"High-frequency CSI300 spot and futures price predictions via the neural network","volume":"18","author":"Jin","year":"2025","journal-title":"J. Uncertain Syst."},{"key":"10.1016\/j.knosys.2026.116008_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2021.106120","article-title":"Corn cash price forecasting with neural networks","volume":"184","author":"Xu","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.knosys.2026.116008_b35","article-title":"Thermal coal price forecasting via the neural network","volume":"14","author":"Xu","year":"2022","journal-title":"Intell. Syst. Appl."},{"issue":"4","key":"10.1016\/j.knosys.2026.116008_b36","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1093\/erae\/jby036","article-title":"Contemporaneous and granger causality among us corn cash and futures prices","volume":"46","author":"Xu","year":"2019","journal-title":"Eur. Rev. Agric. Econ."},{"key":"10.1016\/j.knosys.2026.116008_b37","article-title":"An integrated vector error correction and directed acyclic graph method for investigating contemporaneous causalities","volume":"7","author":"Xu","year":"2023","journal-title":"Decis. Anal. J."},{"key":"10.1016\/j.knosys.2026.116008_b38","doi-asserted-by":"crossref","DOI":"10.1142\/S308284142550008X","article-title":"A study of contemporaneous residential real estate price causation across major jiangsu province cities: Methodology using vector error-correction models and directed acyclic graphs","author":"Jin","year":"2025","journal-title":"Econ. Open"},{"key":"10.1016\/j.knosys.2026.116008_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106870","article-title":"Price forecasts of ten steel products using Gaussian process regressions","volume":"126","author":"Xu","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"Suppl 2","key":"10.1016\/j.knosys.2026.116008_b40","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1007\/s11135-025-02080-3","article-title":"Predictions of residential property price indices for China via machine learning models: B. Jin, X. Xu","volume":"59","author":"Jin","year":"2025","journal-title":"Qual. Quant."},{"issue":"1","key":"10.1016\/j.knosys.2026.116008_b41","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1007\/s13563-024-00472-9","article-title":"Forecasts of coking coal futures price indices through Gaussian process regressions: B. Jin and X. Xu","volume":"38","author":"Jin","year":"2025","journal-title":"Miner. Econ."},{"issue":"4","key":"10.1016\/j.knosys.2026.116008_b42","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1002\/ajae.12041","article-title":"Corn cash price forecasting","volume":"102","author":"Xu","year":"2020","journal-title":"Am. J. Agric. Econ."},{"key":"10.1016\/j.knosys.2026.116008_b43","article-title":"Individual time series and composite forecasting of the Chinese stock index","volume":"5","author":"Xu","year":"2021","journal-title":"Mach. Learn. Appl."},{"issue":"14","key":"10.1016\/j.knosys.2026.116008_b44","doi-asserted-by":"crossref","first-page":"2593","DOI":"10.1080\/02664763.2016.1259399","article-title":"Short-run price forecast performance of individual and composite models for 496 corn cash markets","volume":"44","author":"Xu","year":"2017","journal-title":"J. Appl. Stat."},{"key":"10.1016\/j.knosys.2026.116008_b45","doi-asserted-by":"crossref","unstructured":"P. Anderson, X. He, C. Buehler, D. Teney, M. Johnson, S. Gould, L. Zhang, 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, 2018, pp. 6077\u20136086.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10.1016\/j.knosys.2026.116008_b46","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: 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), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.knosys.2026.116008_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123842","article-title":"Heterogeneous graph fusion network for cross-modal image-text retrieval","volume":"249","author":"Qin","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116008_b48","doi-asserted-by":"crossref","unstructured":"S. Long, S.C. Han, X. Wan, J. Poon, Gradual: Graph-based dual-modal representation for image-text matching, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 3459\u20133468.","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"10.1016\/j.knosys.2026.116008_b49","doi-asserted-by":"crossref","unstructured":"J. Chen, H. Hu, H. Wu, Y. Jiang, C. Wang, Learning the best pooling strategy for visual semantic embedding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15789\u201315798.","DOI":"10.1109\/CVPR46437.2021.01553"},{"issue":"4","key":"10.1016\/j.knosys.2026.116008_b50","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1109\/TIP.2018.2882225","article-title":"Bi-directional spatial-semantic attention networks for image-text matching","volume":"28","author":"Huang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116008_b51","series-title":"Representation learning with contrastive predictive coding","first-page":"arXiv","author":"den Oord","year":"2018"},{"key":"10.1016\/j.knosys.2026.116008_b52","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume":"vol 1","author":"Chopra","year":"2005"},{"key":"10.1016\/j.knosys.2026.116008_b53","doi-asserted-by":"crossref","unstructured":"A. Karpathy, L. Fei-Fei, Deep visual-semantic alignments for generating image descriptions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3128\u20133137.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"10.1016\/j.knosys.2026.116008_b54","doi-asserted-by":"crossref","unstructured":"F. Schroff, D. Kalenichenko, J. Philbin, Facenet: A unified embedding for face recognition and clustering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10.1016\/j.knosys.2026.116008_b55","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"8245","article-title":"Enhancing image-text matching with adaptive feature aggregation","author":"Wang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116008_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109272","article-title":"Improving visual-semantic embeddings by learning semantically-enhanced hard negatives for cross-modal information retrieval","volume":"137","author":"Gong","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116008_b57","first-page":"52326","article-title":"Geodesic multi-modal mixup for robust fine-tuning","volume":"36","author":"Oh","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116008_b58","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.knosys.2026.116008_b59","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."},{"key":"10.1016\/j.knosys.2026.116008_b60","doi-asserted-by":"crossref","unstructured":"B.A. Plummer, L. Wang, C.M. Cervantes, J.C. Caicedo, J. Hockenmaier, S. Lazebnik, Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 2641\u20132649.","DOI":"10.1109\/ICCV.2015.303"},{"key":"10.1016\/j.knosys.2026.116008_b61","doi-asserted-by":"crossref","unstructured":"A. Karpathy, L. Fei-Fei, Deep visual-semantic alignments for generating image descriptions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3128\u20133137.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"10.1016\/j.knosys.2026.116008_b62","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116008_b63","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.2026.116008_b64","series-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116008_b65","series-title":"Step-wise hierarchical alignment network for image-text matching","author":"Ji","year":"2021"},{"key":"10.1016\/j.knosys.2026.116008_b66","doi-asserted-by":"crossref","unstructured":"Z. Fan, Z. Wei, Z. Li, S. Wang, H. Shan, X. Huang, J. Fan, Constructing phrase-level semantic labels to form multi-grained supervision for image-text retrieval, in: Proceedings of the 2022 International Conference on Multimedia Retrieval, 2022, pp. 137\u2013145.","DOI":"10.1145\/3512527.3531368"},{"key":"10.1016\/j.knosys.2026.116008_b67","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110900","article-title":"GADNet: Improving image\u2013text matching via graph-based aggregation and disentanglement","volume":"157","author":"Pu","year":"2025","journal-title":"Pattern Recognit."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007343?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007343?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:24:00Z","timestamp":1781004240000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126007343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":67,"alternative-id":["S0950705126007343"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116008","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive dynamic graph interaction network for fine-grained image\u2013text retrieval","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116008","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116008"}}