{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:39:33Z","timestamp":1792726773617,"version":"4.5.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"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":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133711","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:28:49Z","timestamp":1784820529000},"page":"133711","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Cross-modal attention fusion guided semantic unification for image-text matching"],"prefix":"10.1016","volume":"332","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4256-4771","authenticated-orcid":false,"given":"Xiaoqing","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5105-9221","authenticated-orcid":false,"given":"Jinhui","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-5890","authenticated-orcid":false,"given":"Zhiwen","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanqiang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8406-994X","authenticated-orcid":false,"given":"Jun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.eswa.2026.133711_bib0001","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TBDATA.2023.3338951","article-title":"Proxy-based graph convolutional hashing for cross-modal retrieval","volume":"10","author":"Bai","year":"2023","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.eswa.2026.133711_bib0002","series-title":"Proceedings of the ACM international conference on image and video retrieval","first-page":"1","article-title":"Nus-wide: A real-world web image database from national university of singapore","author":"Chua","year":"2009"},{"key":"10.1016\/j.eswa.2026.133711_bib0003","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2075","article-title":"Collective matrix factorization hashing for multimodal data","author":"Ding","year":"2014"},{"key":"10.1016\/j.eswa.2026.133711_bib0004","series-title":"Proceedings of the 2023\u202fACM international conference on multimedia retrieval","first-page":"612","article-title":"Deep enhanced-similarity attention cross-modal hashing learning","author":"Ge","year":"2023"},{"issue":"4","key":"10.1016\/j.eswa.2026.133711_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3632527","article-title":"Supervised hierarchical online hashing for cross-modal retrieval","volume":"20","author":"Han","year":"2024","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.eswa.2026.133711_bib0006","series-title":"Proceedings of the 1st ACM international conference on multimedia information retrieval","first-page":"39","article-title":"The MIR flickr retrieval evaluation","author":"Huiskes","year":"2008"},{"key":"10.1016\/j.eswa.2026.133711_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110688","article-title":"Discrete online cross-modal hashing with consistency preservation","volume":"155","author":"Kang","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133711_bib0008","series-title":"Twenty-second international joint conference on artificial intelligence","article-title":"Learning hash functions for cross-view similarity search","author":"Kumar","year":"2011"},{"key":"10.1016\/j.eswa.2026.133711_bib0009","doi-asserted-by":"crossref","first-page":"4440","DOI":"10.1109\/TIP.2025.3586504","article-title":"Fast partial-modal online cross-modal hashing","volume":"34","author":"Li","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133711_bib0010","doi-asserted-by":"crossref","first-page":"9664","DOI":"10.1109\/TCSVT.2024.3374791","article-title":"Cross-domain transfer hashing for efficient cross-modal retrieval","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133711_bib0011","doi-asserted-by":"crossref","first-page":"2311","DOI":"10.1109\/TKDE.2025.3537704","article-title":"Collaboratively semantic alignment and metric learning for cross-modal hashing","volume":"37","author":"Li","year":"2025","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.133711_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110922","article-title":"MAFH: Multilabel aware framework for bit-scalable cross-modal hashing","volume":"279","author":"Li","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133711_bib0013","doi-asserted-by":"crossref","first-page":"3009","DOI":"10.1109\/TIP.2024.3385656","article-title":"Multi-relational deep hashing for cross-modal search","volume":"33","author":"Liang","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133711_bib0014","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, Part v 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.133711_bib0015","series-title":"Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval","first-page":"1379","article-title":"Joint-modal distribution-based similarity hashing for large-scale unsupervised deep cross-modal retrieval","author":"Liu","year":"2020"},{"issue":"4","key":"10.1016\/j.eswa.2026.133711_bib0016","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1109\/TETCI.2020.3007143","article-title":"Adversarial tri-fusion hashing network for imbalanced cross-modal retrieval","volume":"5","author":"Liu","year":"2020","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"issue":"2","key":"10.1016\/j.eswa.2026.133711_bib0017","first-page":"552","article-title":"Weakly supervised cross-modal hashing","volume":"8","author":"Liu","year":"2019","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.eswa.2026.133711_bib0018","doi-asserted-by":"crossref","first-page":"10880","DOI":"10.1109\/TCE.2025.3603210","article-title":"Improved cross-modal retrieval systems using self-reinforcement and quadruplet alignment hashing","volume":"71","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.eswa.2026.133711_bib0019","doi-asserted-by":"crossref","DOI":"10.1145\/3829354","article-title":"A comprehensive survey of cross-modal retrieval: Breaking through modal barriers","author":"Liu","year":"2026","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.133711_bib0020","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.1109\/TIP.2026.3666793","article-title":"Exploring hierarchical cross-modal correlation consistency for partial mismatching","volume":"35","author":"Liu","year":"2026","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133711_bib0021","doi-asserted-by":"crossref","first-page":"9530","DOI":"10.1109\/TMM.2023.3254199","article-title":"Deep cross-modal hashing based on semantic consistent ranking","volume":"25","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.133711_bib0022","doi-asserted-by":"crossref","first-page":"3476","DOI":"10.1109\/TMM.2025.3535378","article-title":"Ensemble prototype networks for unsupervised cross-modal hashing with cross-task consistency","volume":"27","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"issue":"1","key":"10.1016\/j.eswa.2026.133711_bib0023","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/TCSVT.2020.2974877","article-title":"Deep multiscale fusion hashing for cross-modal retrieval","volume":"31","author":"Nie","year":"2020","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"10","key":"10.1016\/j.eswa.2026.133711_bib0024","doi-asserted-by":"crossref","first-page":"7255","DOI":"10.1109\/TCSVT.2022.3172716","article-title":"Deep adaptively-enhanced hashing with discriminative similarity guidance for unsupervised cross-modal retrieval","volume":"32","author":"Shi","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133711_bib0025","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1109\/TBDATA.2024.3423704","article-title":"Deep cross-modal hashing with ranking learning for noisy labels","volume":"11","author":"Shu","year":"2024","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.eswa.2026.133711_bib0026","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1109\/TBDATA.2026.3689012","article-title":"Predictive completion enhanced deep hashing with auxiliary code guidance for incomplete cross-modal retrieval","volume":"12","author":"Shu","year":"2026","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.eswa.2026.133711_bib0027","series-title":"Proceedings of the 2013\u202fACM SIGMOD international conference on management of data","first-page":"785","article-title":"Inter-media hashing for large-scale retrieval from heterogeneous data sources","author":"Song","year":"2013"},{"key":"10.1016\/j.eswa.2026.133711_bib0028","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3027","article-title":"Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval","author":"Su","year":"2019"},{"key":"10.1016\/j.eswa.2026.133711_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128747","article-title":"Deep semantic center-guided hashing for multi-label cross-modal retrieval","volume":"295","author":"Sui","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133711_bib0030","doi-asserted-by":"crossref","first-page":"2737","DOI":"10.1109\/TIP.2025.3561659","article-title":"Cross-modal hashing via diverse instances matching","volume":"34","author":"Tu","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133711_bib0031","doi-asserted-by":"crossref","first-page":"4366","DOI":"10.1109\/TPAMI.2024.3355461","article-title":"Content-aware rectified activation for zero-shot fine-grained image retrieval","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"10","key":"10.1016\/j.eswa.2026.133711_bib0032","doi-asserted-by":"crossref","first-page":"10064","DOI":"10.1109\/TCYB.2021.3059886","article-title":"Fast cross-modal hashing with global and local similarity embedding","volume":"52","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.eswa.2026.133711_bib0033","doi-asserted-by":"crossref","first-page":"5835","DOI":"10.1109\/TKDE.2024.3419577","article-title":"Contrastive multi-bit collaborative learning for deep cross-modal hashing","volume":"36","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.133711_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108969","article-title":"Unsupervised cross-modal hashing retrieval via dynamic contrast and optimization","volume":"136","author":"Xie","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133711_bib0035","first-page":"1","article-title":"Multi-scale consistency deep lifelong cross-modal hashing","volume":"21","author":"Xu","year":"2024","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.eswa.2026.133711_bib0036","series-title":"2015\u202fIEEE International conference on multimedia and expo (ICME)","first-page":"1","article-title":"Coupled dictionary learning and feature mapping for cross-modal retrieval","author":"Xu","year":"2015"},{"key":"10.1016\/j.eswa.2026.133711_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131939","article-title":"Adaptive pseudo-labeling for causal-driven cross-modal hashing","volume":"318","author":"Yang","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133711_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121516","article-title":"Similarity graph-correlation reconstruction network for unsupervised cross-modal hashing","volume":"237","author":"Yao","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133711_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4626","article-title":"Deep graph-neighbor coherence preserving network for unsupervised cross-modal hashing","volume":"vol. 35","author":"Yu","year":"2021"},{"key":"10.1016\/j.eswa.2026.133711_bib0040","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1109\/TPAMI.2024.3467130","article-title":"Unsupervised dual deep hashing with semantic-index and content-code for cross-modal retrieval","volume":"47","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133711_bib0041","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Unsupervised generative adversarial cross-modal hashing","volume":"vol. 32","author":"Zhang","year":"2018"},{"key":"10.1016\/j.eswa.2026.133711_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128723","article-title":"GPO++: A dynamic pooling routing network based on pooling operator for cross-modal retrieval","volume":"293","author":"Zhong","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133711_bib0043","series-title":"Proceedings of the 37th international ACM SIGIR conference on research & development in information retrieval","first-page":"415","article-title":"Latent semantic sparse hashing for cross-modal similarity search","author":"Zhou","year":"2014"},{"issue":"3","key":"10.1016\/j.eswa.2026.133711_bib0044","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1109\/TBDATA.2024.3481898","article-title":"Deep residual coupled prompt learning for zero-shot sketch-based image retrieval","volume":"11","author":"Zhuo","year":"2024","journal-title":"IEEE Transactions on Big Data"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426026199?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426026199?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:13:28Z","timestamp":1792725208000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426026199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":44,"alternative-id":["S0957417426026199"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133711","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cross-modal attention fusion guided semantic unification for image-text matching","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133711","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":"133711"}}