{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:16:50Z","timestamp":1778782610445,"version":"3.51.4"},"reference-count":30,"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"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M762553"],"award-info":[{"award-number":["2024M762553"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M783522"],"award-info":[{"award-number":["2025M783522"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471349"],"award-info":[{"award-number":["62471349"]}],"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":["62301378"],"award-info":[{"award-number":["62301378"]}],"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":["62501080"],"award-info":[{"award-number":["62501080"]}],"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":["62171340"],"award-info":[{"award-number":["62171340"]}],"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":["QTZX25076"],"award-info":[{"award-number":["QTZX25076"]}],"id":[{"id":"10.13039\/501100012226","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":[[2026,6]]},"DOI":"10.1016\/j.eswa.2026.131664","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T16:26:22Z","timestamp":1772209582000},"page":"131664","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HumanCrop-Thinker: An inference-driven framework with explicit thinking for explainable human-centric image cropping"],"prefix":"10.1016","volume":"316","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5929-2026","authenticated-orcid":false,"given":"Quan","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0908-2180","authenticated-orcid":false,"given":"Yipo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0509-3782","authenticated-orcid":false,"given":"Pengfei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9069-8796","authenticated-orcid":false,"given":"Leida","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131664_bib0001","article-title":"A grid anchor based cropping approach exploiting image aesthetics, geometric composition, and semantics","volume":"186","author":"Celona","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131664_bib0002","series-title":"Proceedings of the ACM international conference on multimedia","first-page":"37","article-title":"Learning to compose with professional photographs on the web","author":"Chen","year":"2017"},{"key":"10.1016\/j.eswa.2026.131664_bib0003","first-page":"183","article-title":"Deep learning based image aesthetic quality assessment: A review","volume":"57","author":"Chounchenani","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.131664_bib0004","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"Deepseek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.eswa.2026.131664_bib0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"7053","article-title":"Composing photos like a photographer","author":"Hong","year":"2021"},{"key":"10.1016\/j.eswa.2026.131664_bib0006","series-title":"Proceedings of the thirty-eighth AAAI conference on artificial intelligence (aaai)","first-page":"242","article-title":"Learning subject-aware cropping by outpainting professional photos","author":"Hong","year":"2024"},{"key":"10.1016\/j.eswa.2026.131664_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"2436","article-title":"Rethinking image cropping: Exploring diverse compositions from global views","author":"Jia","year":"2022"},{"key":"10.1016\/j.eswa.2026.131664_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"9579","article-title":"LISA: Reasoning segmentation via large language model","author":"Lai","year":"2024"},{"key":"10.1016\/j.eswa.2026.131664_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"30010","article-title":"Cropper: Vision-language model for image cropping through in-context learning","author":"Lee","year":"2025"},{"key":"10.1016\/j.eswa.2026.131664_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"4212","article-title":"Composing good shots by exploiting mutual relations","author":"Li","year":"2020"},{"key":"10.1016\/j.eswa.2026.131664_bib0011","series-title":"Proceedings of the ACM symposium on user interface software and technology (UIST)","first-page":"359","article-title":"Dynamic guidance for decluttering photographic compositions","author":"Lindell","year":"2021"},{"key":"10.1016\/j.eswa.2026.131664_bib0012","unstructured":"Liu, Z., & He, K. (2025). A decade\u2019s battle on dataset bias: Are we there yet?In International Conference on Learning Representations (ICLR), 2025, 41433\u201341449."},{"key":"10.1016\/j.eswa.2026.131664_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","article-title":"Visual-RFT: Visual reinforcement fine-tuning","author":"Liu","year":"2025"},{"key":"10.1016\/j.eswa.2026.131664_bib0014","doi-asserted-by":"crossref","first-page":"3618","DOI":"10.1109\/TMM.2020.3029882","article-title":"Learning the relation between interested objects and aesthetic region for image cropping","volume":"23","author":"Lu","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.131664_bib0015","doi-asserted-by":"crossref","first-page":"91904","DOI":"10.1109\/ACCESS.2019.2925430","article-title":"Listwise view ranking for image cropping","volume":"7","author":"Lu","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.131664_bib0016","doi-asserted-by":"crossref","first-page":"6836","DOI":"10.1109\/TMM.2022.3215003","article-title":"Composition-guided neural network for image cropping aesthetic assessment","volume":"25","author":"Ni","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.131664_bib0017","series-title":"Proceedings of the thirty-seventh AAAI conference on artificial intelligence (AAAI)","first-page":"224","article-title":"Find beauty in the rare: Contrastive composition feature clustering for nontrivial cropping box regression","author":"Pan","year":"2023"},{"key":"10.1016\/j.eswa.2026.131664_bib0018","doi-asserted-by":"crossref","first-page":"8157","DOI":"10.1109\/TMM.2024.3377125","article-title":"Pseudo label fusion with uncertainty estimation for semi-supervised cropping box regression","volume":"26","author":"Pan","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.131664_bib0019","series-title":"Proceedings of the thirty-eighth AAAI conference on artificial intelligence (AAAI)","first-page":"555","article-title":"Spatial-semantic collaborative cropping for user generated content","author":"Su","year":"2024"},{"key":"10.1016\/j.eswa.2026.131664_bib0020","series-title":"Proceedings of the thirty-fourth AAAI conference on artificial intelligence (AAAI)","first-page":"12104","article-title":"Image cropping with composition and saliency aware aesthetic score map","author":"Tu","year":"2020"},{"key":"10.1016\/j.eswa.2026.131664_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"10052","article-title":"Image cropping with spatial-aware feature and rank consistency","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.131664_bib0022","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., Fan, Y., Dang, K., Du, M., Ren, X., Men, R., Liu, D., Zhou, C., Zhou, J., & Lin, J. (2024). Qwen2-VL: Enhancing vision-language model perception at any resolution. Technical Report, arXiv preprint."},{"key":"10.1016\/j.eswa.2026.131664_bib0023","doi-asserted-by":"crossref","first-page":"1531","DOI":"10.1109\/TPAMI.2018.2840724","article-title":"A deep network solution for attention and aesthetics aware photo cropping","volume":"41","author":"Wang","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.131664_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Good view hunting: Learning photo composition from dense view pairs","author":"Wei","year":"2018"},{"key":"10.1016\/j.eswa.2026.131664_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114596","article-title":"Saliency aware image cropping with latent region pair","volume":"171","author":"Xu","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131664_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"19829","article-title":"Personalized image aesthetics assessment with rich attributes","author":"Yang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131664_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104316","article-title":"Aesthetic image cropping meets VLP: Enhancing good while reducing bad","volume":"105","author":"Yuan","year":"2024","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.eswa.2026.131664_bib0028","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/TPAMI.2020.3024207","article-title":"Grid anchor based image cropping: A new benchmark and an efficient model","volume":"44","author":"Zeng","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.131664_bib0029","series-title":"Computer vision - ECCV 2022: 17th European conference","first-page":"181","article-title":"Human-centric image cropping with partition-aware and content-preserving features","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131664_bib0030","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1145\/3719012","article-title":"Image cropping with content and composition attribute-aware global relation reasoning","volume":"21","author":"Zhu","year":"2025","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426005774?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426005774?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:51:59Z","timestamp":1778781119000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426005774"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":30,"alternative-id":["S0957417426005774"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131664","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HumanCrop-Thinker: An inference-driven framework with explicit thinking for explainable human-centric image cropping","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131664","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":"131664"}}