{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:57:07Z","timestamp":1781301427748,"version":"3.54.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["62406082"],"award-info":[{"award-number":["62406082"]}],"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":["62506085"],"award-info":[{"award-number":["62506085"]}],"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":["62394334"],"award-info":[{"award-number":["62394334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014881","name":"Guangzhou University","doi-asserted-by":"publisher","award":["JCCX2025-022"],"award-info":[{"award-number":["JCCX2025-022"]}],"id":[{"id":"10.13039\/501100014881","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515110659"],"award-info":[{"award-number":["2023A1515110659"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515110650"],"award-info":[{"award-number":["2023A1515110650"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2025A04J4590"],"award-info":[{"award-number":["2025A04J4590"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2024A03J0013"],"award-info":[{"award-number":["2024A03J0013"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113664","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:57:18Z","timestamp":1775098638000},"page":"113664","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["F3-SD: Focal feature fusion with self-distillation on large vision-language models for cross-modal retrieval"],"prefix":"10.1016","volume":"179","author":[{"given":"Da","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4605-9270","authenticated-orcid":false,"given":"Yangtao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaocui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maobin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meie","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wensheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113664_bib0001","series-title":"Proceedings of ACM International Conference on Information and Knowledge Management","first-page":"2629","article-title":"Image-text retrieval with main semantics consistency","author":"Xie","year":"2024"},{"issue":"11","key":"10.1016\/j.patcog.2026.113664_bib0002","doi-asserted-by":"crossref","first-page":"5926","DOI":"10.1109\/TKDE.2024.3401050","article-title":"Deep hierarchy-aware proxy hashing with self-paced learning for cross-modal retrieval","volume":"36","author":"Huo","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"10.1016\/j.patcog.2026.113664_bib0003","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":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113664_bib0004","doi-asserted-by":"crossref","first-page":"4613","DOI":"10.1109\/TMM.2025.3535306","article-title":"Deep semantic-consistent penalizing hashing for cross-modal retrieval","volume":"27","author":"Qin","year":"2025","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.patcog.2026.113664_bib0005","doi-asserted-by":"crossref","first-page":"3622","DOI":"10.1109\/TIP.2025.3574918","article-title":"UCPM: uncertainty-guided cross-Modal retrieval with partially mismatched pairs","volume":"34","author":"Zha","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"10.1016\/j.patcog.2026.113664_bib0006","first-page":"5612","article-title":"An NVM SSD-based high performance query processing framework for search engines","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.113664_bib0007","series-title":"Proceedings of Annual Meeting of the Association for Computational Linguistics and International Joint Conference on Natural Language Processing","first-page":"2666","article-title":"Large language models are built-in autoregressive search engines","author":"Ziems","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0008","series-title":"Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"1713","article-title":"Predicting session length for product search on E-commerce platform","author":"Gupta","year":"2020"},{"issue":"3","key":"10.1016\/j.patcog.2026.113664_bib0009","doi-asserted-by":"crossref","first-page":"1260","DOI":"10.1109\/TKDE.2023.3297331","article-title":"Query-aware explainable product search with reinforcement knowledge graph reasoning","volume":"36","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.113664_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111609","article-title":"Cycle-VQA: a cycle-consistent framework for robust medical visual question answering","volume":"165","author":"Fan","year":"2025","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.patcog.2026.113664_bib0011","doi-asserted-by":"crossref","first-page":"4160","DOI":"10.1109\/TNNLS.2021.3135655","article-title":"Bilateral cross-modality graph matching attention for feature fusion in visual question answering","volume":"36","author":"Cao","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113664_bib0012","series-title":"Proceedings of AAAI Conference on Artificial Intelligence","first-page":"1218","article-title":"Similarity reasoning and filtration for image-text matching","author":"Diao","year":"2021"},{"key":"10.1016\/j.patcog.2026.113664_bib0013","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"19275","article-title":"Fine-grained image-text matching by cross-modal hard aligning network","author":"Pan","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0014","doi-asserted-by":"crossref","first-page":"7555","DOI":"10.1109\/TMM.2024.3369968","article-title":"A mutually textual and visual refinement network for image-text matching","volume":"26","author":"Pang","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"10.1016\/j.patcog.2026.113664_bib0015","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."},{"key":"10.1016\/j.patcog.2026.113664_bib0016","first-page":"1","article-title":"Parameters inversion of sedimentary layers in martian north polar region based on a CNN-BiGRU network","volume":"63","author":"Xin","year":"2025","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"10.1016\/j.patcog.2026.113664_bib0017","series-title":"Proceedings of Annual Conference on Neural Information Processing Systems","first-page":"9694","article-title":"Align before fuse: vision and language representation learning with momentum distillation","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113664_bib0018","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4943","article-title":"Align and prompt: video-and-language pre-training with entity prompts","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113664_bib0019","series-title":"Proceedings of 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.patcog.2026.113664_bib0020","series-title":"Proceedings of AAAI Conference on Artificial Intelligence","first-page":"18298","article-title":"Cross-modal and uni-modal soft-label alignment for image-text retrieval","author":"Huang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113664_bib0021","series-title":"Proceedings of AAAI Conference on Artificial Intelligence","first-page":"1860","article-title":"SoftCLIP: softer cross-modal alignment makes CLIP stronger","author":"Gao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113664_bib0022","series-title":"Proceedings of European Conference on Computer Vision","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.113664_bib0023","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"19113","article-title":"MaPLe: multi-modal prompt learning","author":"Khattak","year":"2023"},{"issue":"1","key":"10.1016\/j.patcog.2026.113664_bib0024","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1109\/TNNLS.2023.3333846","article-title":"Enhanced scalable graph neural network via knowledge distillation","volume":"36","author":"Mai","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113664_bib0025","doi-asserted-by":"crossref","first-page":"6361","DOI":"10.1109\/TMM.2023.3349075","article-title":"Deep neighborhood-preserving hashing with quadratic spherical mutual information for cross-modal retrieval","volume":"26","author":"Qin","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.patcog.2026.113664_bib0026","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1109\/TIP.2023.3348297","article-title":"USER: unified semantic enhancement with momentum contrast for image-text retrieval","volume":"33","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113664_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112817","article-title":"Intra-modal consistency for image-text retrieval through soft-label distillation","volume":"173","author":"Chen","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113664_bib0028","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"15640","article-title":"Negative-aware attention framework for image-text matching","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113664_bib0029","series-title":"Proceedings of International Conference on Learning Representations","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113664_bib0030","doi-asserted-by":"crossref","first-page":"1921","DOI":"10.1109\/TIP.2025.3551647","article-title":"Hyperbolic insights with knowledge distillation for cross-domain few-shot learning","volume":"34","author":"Yang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113664_bib0031","doi-asserted-by":"crossref","first-page":"3578","DOI":"10.1109\/TIP.2025.3573474","article-title":"CKD: contrastive knowledge distillation from a sample-wise perspective","volume":"34","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113664_bib0032","series-title":"Proceedings of IEEE International Conference on Computer Vision","first-page":"6123","article-title":"Cumulative spatial knowledge distillation for vision transformers","author":"Zhao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0033","series-title":"Proceedings of IEEE International Conference on Computer Vision","first-page":"1515","article-title":"Data-free knowledge distillation for fine-grained visual categorization","author":"Shao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0034","series-title":"Proceedings of Annual Meeting of the Association for Computational Linguistics and International Joint Conference on Natural Language Processing","first-page":"71","article-title":"CocaCLIP: exploring distillation of fully-connected knowledge interaction graph for lightweight text-image retrieval","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0035","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"14974","article-title":"Prompting large language models with answer heuristics for knowledge-based visual question answering","author":"Shao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0036","doi-asserted-by":"crossref","first-page":"2652","DOI":"10.1109\/TIP.2024.3379900","article-title":"Knowledge-augmented visual question answering with natural language explanation","volume":"33","author":"Xie","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113664_bib0037","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6935","article-title":"Cross-domain image captioning with discriminative finetuning","author":"Dess\u00ec","year":"2023"},{"key":"10.1016\/j.patcog.2026.113664_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110941","article-title":"M3ixup: a multi-modal data augmentation approach for image captioning","volume":"158","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113664_bib0039","series-title":"Proceedings of ACM International Conference on Multimedia","first-page":"2350","article-title":"Overcoming the pitfalls of vision-language model for image-text retrieval","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113664_bib0040","first-page":"67","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. Ling."},{"key":"10.1016\/j.patcog.2026.113664_bib0041","series-title":"Proceedings of European Conference on Computer Vision","first-page":"212","article-title":"Stacked cross attention for image-text matching","author":"Lee","year":"2018"},{"key":"10.1016\/j.patcog.2026.113664_bib0042","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"15789","article-title":"Learning the best pooling strategy for visual semantic embedding","author":"Chen","year":"2021"},{"issue":"1","key":"10.1016\/j.patcog.2026.113664_bib0043","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1109\/TPAMI.2022.3148470","article-title":"Image-text embedding learning via visual and textual semantic reasoning","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113664_bib0044","series-title":"Proceedings of IEEE International Conference on Data Engineering","first-page":"70","article-title":"Knowledge graph enhanced multimodal transformer for image-text retrieval","author":"Zheng","year":"2024"},{"key":"10.1016\/j.patcog.2026.113664_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111088","article-title":"Multi-view visual semantic embedding for cross-modal image-text retrieval","volume":"159","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113664_bib0046","series-title":"Proceedings of International Conference on Learning Representations","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"issue":"9","key":"10.1016\/j.patcog.2026.113664_bib0047","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113664_bib0048","series-title":"Proceedings of European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","volume":"13693","author":"Jia","year":"2022"},{"issue":"2","key":"10.1016\/j.patcog.2026.113664_bib0049","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"CLIP-adapter: better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"Int. J. Comput. Vis."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006291?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006291?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:19:34Z","timestamp":1781299174000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006291"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":49,"alternative-id":["S0031320326006291"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113664","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"F3-SD: Focal feature fusion with self-distillation on large vision-language models for cross-modal retrieval","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113664","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":"113664"}}