{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:21:05Z","timestamp":1783171265968,"version":"3.54.6"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["62202204"],"award-info":[{"award-number":["62202204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JUSRP123032"],"award-info":[{"award-number":["JUSRP123032"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.patrec.2026.05.006","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T23:55:00Z","timestamp":1778543700000},"page":"56-62","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["VIP-CAN: Vision prompt-based cross-attention network for zero-shot sketch-based image retrieval"],"prefix":"10.1016","volume":"206","author":[{"given":"Guoliang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-0918","authenticated-orcid":false,"given":"Donglin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.patrec.2026.05.006_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925954","article-title":"The sketchy database: learning to retrieve badly drawn bunnies","volume":"35","author":"Sangkloy","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.patrec.2026.05.006_bib0002","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.patrec.2025.04.018","article-title":"Achieving high performance on sketch-based image retrieval without real sketches for training","volume":"193","author":"Saavedra","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.05.006_bib0003","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.patrec.2024.04.022","article-title":"Manifold information through neighbor embedding projection for image retrieval","volume":"183","author":"Leticio","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.05.006_bib0004","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3598","article-title":"Zero-shot sketch-image hashing","author":"Shen","year":"2018"},{"key":"10.1016\/j.patrec.2026.05.006_bib0005","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"300","article-title":"A zero-shot framework for sketch based image retrieval","author":"Yelamarthi","year":"2018"},{"key":"10.1016\/j.patrec.2026.05.006_bib0006","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7678","article-title":"Semi-transductive learning for generalized zero-shot sketch-based image retrieval","volume":"37","author":"Ge","year":"2023"},{"key":"10.1016\/j.patrec.2026.05.006_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108528","article-title":"An efficient framework for zero-shot sketch-based image retrieval","volume":"126","author":"Tursun","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patrec.2026.05.006_bib0008","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Elevating all zero-shot sketch-based image retrieval through multimodal prompt learning","author":"Singha","year":"2025"},{"key":"10.1016\/j.patrec.2026.05.006_bib0009","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.patrec.2021.07.018","article-title":"MOON: multi-hash codes joint learning for cross-media retrieval","volume":"151","author":"Zhang","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.05.006_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23349","article-title":"Zero-shot everything sketch-based image retrieval, and in explainable style","author":"Lin","year":"2023"},{"key":"10.1016\/j.patrec.2026.05.006_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2765","article-title":"Clip for all things zero-shot sketch-based image retrieval, fine-grained or not","author":"Sain","year":"2023"},{"key":"10.1016\/j.patrec.2026.05.006_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5089","article-title":"Semantically tied paired cycle consistency for zero-shot sketch-based image retrieval","author":"Dutta","year":"2019"},{"key":"10.1016\/j.patrec.2026.05.006_bib0013","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2370","article-title":"TVT: three-way vision transformer through multi-modal hypersphere learning for zero-shot sketch-based image retrieval","volume":"36","author":"Tian","year":"2022"},{"key":"10.1016\/j.patrec.2026.05.006_bib0014","series-title":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"1033","article-title":"Multi-level encoding with hierarchical alignment for sketch-based 3D shape retrieval","author":"Zhang","year":"2025"},{"key":"10.1016\/j.patrec.2026.05.006_bib0015","series-title":"European Conference on Computer Vision","first-page":"163","article-title":"Adaptive fine-grained sketch-based image retrieval","author":"Bhunia","year":"2022"},{"key":"10.1016\/j.patrec.2026.05.006_bib0016","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"601","article-title":"Prototype-based selective knowledge distillation for zero-shot sketch based image retrieval","author":"Wang","year":"2022"},{"key":"10.1016\/j.patrec.2026.05.006_bib0017","unstructured":"L. Gao, B. Jiao, P. Wang, S. Zhang, H. Zhang, Y. Zhang, Dual-modal prompting for sketch-based image retrieval, (2024). arXiv preprint arXiv: 2404.18695."},{"issue":"9","key":"10.1016\/j.patrec.2026.05.006_bib0018","first-page":"1","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patrec.2026.05.006_bib0019","doi-asserted-by":"crossref","unstructured":"B. Lester, R. Al-Rfou, N. Constant, The power of scale for parameter-efficient prompt tuning, (2021). arXiv preprint arXiv: 2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"10.1016\/j.patrec.2026.05.006_bib0020","unstructured":"X.L. Li, P. Liang, Prefix-tuning: optimizing continuous prompts for generation, (2021). arXiv preprint arXiv: 2101.00190."},{"key":"10.1016\/j.patrec.2026.05.006_bib0021","doi-asserted-by":"crossref","unstructured":"X. Liu, K. Ji, Y. Fu, W.L. Tam, Z. Du, Z. Yang, J. Tang, P-tuning v2: prompt tuning can be comparable to fine-tuning universally across scales and tasks, (2021). arXiv preprint arXiv: 2110.07602.","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"10.1016\/j.patrec.2026.05.006_bib0022","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.patrec.2026.05.006_bib0023","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19113","article-title":"Maple: multi-modal prompt learning","author":"Khattak","year":"2023"},{"key":"10.1016\/j.patrec.2026.05.006_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108343","article-title":"Robust and discrete matrix factorization hashing for cross-modal retrieval","volume":"122","author":"Zhang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patrec.2026.05.006_bib0025","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","first-page":"524","article-title":"Discrete bidirectional matrix factorization hashing for zero-shot cross-media retrieval","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patrec.2026.05.006_bib0026","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5656","article-title":"Multitask vision-language prompt tuning","author":"Shen","year":"2024"},{"key":"10.1016\/j.patrec.2026.05.006_bib0027","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5646","article-title":"Modality-aware representation learning for zero-shot sketch-based image retrieval","author":"Lyou","year":"2024"},{"issue":"11","key":"10.1016\/j.patrec.2026.05.006_bib0028","first-page":"12844","article-title":"TransZero++: cross attribute-guided transformer for zero-shot learning","volume":"45","author":"Chen","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.patrec.2026.05.006_bib0029","doi-asserted-by":"crossref","first-page":"4516","DOI":"10.1109\/TNNLS.2022.3155602","article-title":"GNDAN: graph navigated dual attention network for zero-shot learning","volume":"35","author":"Chen","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"7","key":"10.1016\/j.patrec.2026.05.006_bib0030","doi-asserted-by":"crossref","first-page":"4504","DOI":"10.1007\/s11263-025-02394-7","article-title":"Semantics-conditioned generative zero-shot learning via feature refinement","volume":"133","author":"Chen","year":"2025","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"10.1016\/j.patrec.2026.05.006_bib0031","doi-asserted-by":"crossref","first-page":"3806","DOI":"10.1007\/s11263-024-02053-3","article-title":"I2DFormer+: learning image to document summary attention for zero-shot image classification","volume":"132","author":"Naeem","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patrec.2026.05.006_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7612","article-title":"MSDN: mutually semantic distillation network for zero-shot learning","author":"Chen","year":"2022"},{"key":"10.1016\/j.patrec.2026.05.006_bib0033","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7462","article-title":"Sketch3t: test-time training for zero-shot sbir","author":"Sain","year":"2022"},{"key":"10.1016\/j.patrec.2026.05.006_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"677","article-title":"Generalising fine-grained sketch-based image retrieval","author":"Pang","year":"2019"},{"key":"10.1016\/j.patrec.2026.05.006_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2179","article-title":"Doodle to search: practical zero-shot sketch-based image retrieval","author":"Dey","year":"2019"},{"key":"10.1016\/j.patrec.2026.05.006_bib0036","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3662","article-title":"Semantic-aware knowledge preservation for zero-shot sketch-based image retrieval","author":"Liu","year":"2019"},{"key":"10.1016\/j.patrec.2026.05.006_bib0037","doi-asserted-by":"crossref","first-page":"2833","DOI":"10.1109\/TMM.2020.3017918","article-title":"StyleGuide: zero-shot sketch-based image retrieval using style-guided image generation","volume":"23","author":"Dutta","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patrec.2026.05.006_bib0038","series-title":"2020 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"Ocean: a dual learning approach for generalized zero-shot sketch-based image retrieval","author":"Zhu","year":"2020"},{"key":"10.1016\/j.patrec.2026.05.006_bib0039","doi-asserted-by":"crossref","unstructured":"Z. Wang, H. Wang, J. Yan, A. Wu, C. Deng, Domain-smoothing network for zero-shot sketch-based image retrieval, (2021a). arXiv preprint arXiv: 2106.11841.","DOI":"10.24963\/ijcai.2021\/158"},{"issue":"12","key":"10.1016\/j.patrec.2026.05.006_bib0040","doi-asserted-by":"crossref","first-page":"9181","DOI":"10.1109\/TPAMI.2021.3123315","article-title":"Transferable coupled network for zero-shot sketch-based image retrieval","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patrec.2026.05.006_bib0041","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neucom.2022.09.104","article-title":"BDA-SketRet: bi-level domain adaptation for zero-shot SBIR","volume":"514","author":"Chaudhuri","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patrec.2026.05.006_bib0042","series-title":"2024 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"Cross-domain feature semantic calibration for zero-shot sketch-based image retrieval","author":"He","year":"2024"},{"issue":"19","key":"10.1016\/j.patrec.2026.05.006_bib0043","doi-asserted-by":"crossref","first-page":"57811","DOI":"10.1007\/s11042-023-17675-x","article-title":"Task-like training paradigm in CLIP for zero-shot sketch-based image retrieval","volume":"83","author":"Zhang","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.patrec.2026.05.006_bib0044","unstructured":"L.S.F. Ribeiro, M.A. Ponti, Sketch-an-anchor: sub-epoch fast model adaptation for zero-shot sketch-based image retrieval, (2023). arXiv preprint arXiv: 2303.16769."},{"key":"10.1016\/j.patrec.2026.05.006_bib0045","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2862","article-title":"Deep sketch hashing: fast free-hand sketch-based image retrieval","author":"Liu","year":"2017"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016786552600173X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016786552600173X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T12:52:58Z","timestamp":1783169578000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S016786552600173X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":45,"alternative-id":["S016786552600173X"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.05.006","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VIP-CAN: Vision prompt-based cross-attention network for zero-shot sketch-based image retrieval","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.05.006","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"}]}}