{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T13:48:25Z","timestamp":1782481705983,"version":"3.54.5"},"reference-count":27,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007224","name":"National Foundation for Science & Technology Development","doi-asserted-by":"publisher","award":["102.05-2023.31"],"award-info":[{"award-number":["102.05-2023.31"]}],"id":[{"id":"10.13039\/100007224","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":[[2026,9]]},"DOI":"10.1016\/j.patrec.2026.06.011","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T23:58:43Z","timestamp":1781827123000},"page":"102-108","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["You can see me: Retrieval-augmented framework for divergent perception in animal art generation"],"prefix":"10.1016","volume":"207","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1773-1520","authenticated-orcid":false,"given":"Quoc-Duy","family":"Tran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3547-9907","authenticated-orcid":false,"given":"Anh-Tuan","family":"Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0236-7992","authenticated-orcid":false,"given":"Tam V.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7363-2610","authenticated-orcid":false,"given":"Trung-Nghia","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.patrec.2026.06.011_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2022.105103","article-title":"Processing visual ambiguity in fractal patterns: Pareidolia as a sign of creativity","volume":"25","author":"Bellemare-Pepin","year":"2022","journal-title":"Iscience"},{"key":"10.1016\/j.patrec.2026.06.011_bib0002","first-page":"167","article-title":"Rock art and pareidolia","volume":"33","author":"Bednarik","year":"2016","journal-title":"Rock Art Res."},{"key":"10.1016\/j.patrec.2026.06.011_bib0003","series-title":"CVPR","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.patrec.2026.06.011_bib0004","series-title":"ICCV","first-page":"3836","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patrec.2026.06.011_bib0005","series-title":"ICICC","article-title":"Before a computer can draw, it must first learn to see","author":"Heath","year":"2016"},{"key":"10.1016\/j.patrec.2026.06.011_bib0006","unstructured":"H. Ye, J. Zhang, S. Liu, X. Han, W. Yang, Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models, (2023). arXiv preprint arXiv: 2308.06721."},{"key":"10.1016\/j.patrec.2026.06.011_bib0007","unstructured":"Q.-D. Tran, A.-T. Vo, D.-K. Vo, T.V. Nguyen, M.-T. Tran, T.-N. Le, Shape2Animal: creative animal generation from natural silhouettes, (2025a) arXiv preprint arXiv: 2506.20616."},{"key":"10.1016\/j.patrec.2026.06.011_bib0008","series-title":"SoICT","article-title":"Visual retrieval-augmented generation for silhouette-guided animal art","author":"Tran","year":"2025"},{"key":"10.1016\/j.patrec.2026.06.011_bib0009","series-title":"AAAI","article-title":"Imagination machines: a new challenge for artificial intelligence","author":"Mahadevan","year":"2018"},{"issue":"2","key":"10.1016\/j.patrec.2026.06.011_bib0010","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"key":"10.1016\/j.patrec.2026.06.011_bib0011","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.cobeha.2018.12.011","article-title":"Analogues of mental simulation and imagination in deep learning","volume":"29","author":"Hamrick","year":"2019","journal-title":"Curr. Opin. Behav. Sci."},{"key":"10.1016\/j.patrec.2026.06.011_bib0012","series-title":"CVPR","first-page":"2236","article-title":"Pareidolia face reenactment","author":"Song","year":"2021"},{"key":"10.1016\/j.patrec.2026.06.011_bib0013","series-title":"ACM Multimedia","first-page":"2441","article-title":"Cloud2Sketch: augmenting clouds with imaginary sketches","author":"Wan","year":"2022"},{"issue":"1","key":"10.1016\/j.patrec.2026.06.011_bib0014","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s11023-007-9066-2","article-title":"Some empirical criteria for attributing creativity to a computer program","volume":"17","author":"Ritchie","year":"2007","journal-title":"Minds Mach."},{"key":"10.1016\/j.patrec.2026.06.011_bib0015","series-title":"CVPR","first-page":"24185","article-title":"Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024"},{"key":"10.1016\/j.patrec.2026.06.011_bib0016","series-title":"CVPR","first-page":"13305","article-title":"Shapewords: guiding text-to-image synthesis with 3d shape-aware prompts","author":"Petrov","year":"2025"},{"issue":"2","key":"10.1016\/j.patrec.2026.06.011_bib0017","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":"IJCV"},{"key":"10.1016\/j.patrec.2026.06.011_bib0018","series-title":"EACL","first-page":"3666","article-title":"Retrieval-augmented image captioning","author":"Ramos","year":"2023"},{"key":"10.1016\/j.patrec.2026.06.011_bib0019","unstructured":"R. Shalev-Arkushin, R. Gal, A.H. Bermano, O. Fried, Imagerag: dynamic image retrieval for reference-guided image generation, (2025). arXiv preprint arXiv: 2502.09411."},{"key":"10.1016\/j.patrec.2026.06.011_bib0020","unstructured":"Y. Lyu, X. Zheng, L. Jiang, Y. Yan, X. Zou, H. Zhou, L. Zhang, X. Hu, Realrag: retrieval-augmented realistic image generation via self-reflective contrastive learning, (2025). arXiv preprint arXiv: 2502.00848."},{"key":"10.1016\/j.patrec.2026.06.011_bib0021","first-page":"28514","article-title":"Ar-rag: autoregressive retrieval augmentation for image generation","volume":"38","author":"Qi","year":"2026","journal-title":"NeurIPS"},{"key":"10.1016\/j.patrec.2026.06.011_bib0022","series-title":"ECCV","first-page":"38","article-title":"Grounding dino: marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.patrec.2026.06.011_bib0023","series-title":"ICCV","first-page":"3992","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.patrec.2026.06.011_bib0024","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-020-01316-z","article-title":"The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale","author":"Kuznetsova","year":"2020","journal-title":"IJCV"},{"key":"10.1016\/j.patrec.2026.06.011_bib0025","unstructured":"J. Taylor, W. Agnew, M. Sap, S.E. Fox, H. Zhu, The algorithmic gaze: an audit and ethnography of the LAION-aesthetics predictor model, (2026). arXiv preprint arXiv: 2601.09896."},{"key":"10.1016\/j.patrec.2026.06.011_bib0026","series-title":"EuroVis Workshop","article-title":"Integrating layer-wise relevance propagation with stable diffusion for enhanced interpretability","author":"Auman","year":"2025"},{"key":"10.1016\/j.patrec.2026.06.011_bib0027","series-title":"CCWC","first-page":"00441","article-title":"Neural network interpretability with layer-wise relevance propagation: novel techniques for neuron selection and visualization","author":"Bhati","year":"2025"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526002138?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526002138?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T13:03:14Z","timestamp":1782478994000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526002138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":27,"alternative-id":["S0167865526002138"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.06.011","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"You can see me: Retrieval-augmented framework for divergent perception in animal art generation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.06.011","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"}]}}