{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:02:40Z","timestamp":1780495360274,"version":"3.54.1"},"reference-count":54,"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":["62276271"],"award-info":[{"award-number":["62276271"]}],"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":["62325604"],"award-info":[{"award-number":["62325604"]}],"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":["62406100"],"award-info":[{"award-number":["62406100"]}],"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":["62506371"],"award-info":[{"award-number":["62506371"]}],"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":["62441618"],"award-info":[{"award-number":["62441618"]}],"id":[{"id":"10.13039\/501100001809","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.2026.113450","type":"journal-article","created":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:46:01Z","timestamp":1773589561000},"page":"113450","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["Object style diffusion for generalized object detection in urban scene"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1752-5167","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3036-6022","authenticated-orcid":false,"given":"Xiangyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1059-0441","authenticated-orcid":false,"given":"Mengzhu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4837-455X","authenticated-orcid":false,"given":"Ke","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-1475","authenticated-orcid":false,"given":"Xinwang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2635-7716","authenticated-orcid":false,"given":"Kenli","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113450_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111717","article-title":"Real-time small object detection using adaptive weighted fusion of efficient positional features","volume":"167","author":"Ding","year":"2025","journal-title":"Pattern Recognit."},{"issue":"10","key":"10.1016\/j.patcog.2026.113450_bib0002","doi-asserted-by":"crossref","first-page":"6768","DOI":"10.1007\/s11263-025-02465-9","article-title":"Robust object detection with domain-invariant training and continual test-time adaptation","volume":"133","author":"Fan","year":"2025","journal-title":"Int. J. Comput. Vis."},{"issue":"6","key":"10.1016\/j.patcog.2026.113450_bib0003","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s10462-025-11186-x","article-title":"Context in object detection: a systematic literature review","volume":"58","author":"Jamali","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.patcog.2026.113450_bib0004","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"834","article-title":"Learning to diversify for single domain generalization","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113450_bib0005","doi-asserted-by":"crossref","first-page":"2680","DOI":"10.1109\/TIP.2025.3563775","article-title":"Learning to see low-light images via feature domain adaptation","volume":"34","author":"Yang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113450_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111550","article-title":"Concept-guided domain generalization for semantic segmentation","volume":"164","author":"Liao","year":"2025","journal-title":"Pattern Recognit."},{"issue":"10","key":"10.1016\/j.patcog.2026.113450_bib0007","doi-asserted-by":"crossref","first-page":"9043","DOI":"10.1109\/TPAMI.2025.3582689","article-title":"From concrete to abstract: multi-view clustering on relational knowledge","volume":"47","author":"Liang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113450_bib0008","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"11400","article-title":"Adversarial Bayesian augmentation for single-source domain generalization","author":"Cheng","year":"2023"},{"issue":"1","key":"10.1016\/j.patcog.2026.113450_bib0009","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/TCSVT.2025.3596089","article-title":"Phrase grounding-based style transfer for single-domain generalized object detection","volume":"36","author":"Li","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113450_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3219","article-title":"CLIP the gap: a single domain generalization approach for object detection","author":"Vidit","year":"2023"},{"key":"10.1016\/j.patcog.2026.113450_bib0011","series-title":"Proceedings of the International Conference on Machine Learning (ICML)","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113450_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.patcog.2026.113450_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111561","article-title":"Identity-aware infrared person image generation and re-identification via controllable diffusion model","volume":"165","author":"Yu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113450_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","article-title":"DGInStyle: domain-generalizable semantic segmentation with image diffusion models and stylized semantic control","author":"Jia","year":"2023"},{"key":"10.1016\/j.patcog.2026.113450_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108998","article-title":"A full data augmentation pipeline for small object detection based on generative adversarial networks","volume":"133","author":"Bosquet","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113450_bib0016","series-title":"International Conference on Learning Representations (ICLR)","article-title":"AugMix: a simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2020"},{"key":"10.1016\/j.patcog.2026.113450_bib0017","series-title":"European Conference on Computer Vision (ECCV)","first-page":"623","article-title":"PRIME: a few primitives can boost robustness to common corruptions","author":"Modas","year":"2022"},{"key":"10.1016\/j.patcog.2026.113450_bib0018","series-title":"International Conference on Learning Representations (ICLR)","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2019"},{"key":"10.1016\/j.patcog.2026.113450_bib0019","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"issue":"11","key":"10.1016\/j.patcog.2026.113450_bib0020","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.patcog.2026.113450_bib0021","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2014"},{"key":"10.1016\/j.patcog.2026.113450_bib0022","series-title":"British Machine Vision Conference (BMVC)","article-title":"Prompting diffusion representations for cross-domain semantic segmentation","author":"Gong","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0023","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"54683","article-title":"DatasetDM: synthesizing data with perception annotations using diffusion models","volume":"Vol. 36","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113450_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6232","article-title":"InstanceDiffusion: instance-level control for image generation","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0025","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2947","article-title":"Object-aware domain generalization for object detection","volume":"Vol. 38","author":"Lee","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0026","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5958","article-title":"G-NAS: generalizable neural architecture search for single domain generalization object detection","volume":"Vol. 38","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0027","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Tag2Text: guiding vision-language model via image tagging","author":"Huang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0028","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113450_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9307","article-title":"Rethinking FID: towards a better evaluation metric for image generation","author":"Jayasumana","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0030","unstructured":"K. Thurnhofer-Hemsi, E. L\u00f3pez-Rubio, M.A. Molina-Cabello, K. Najarian, Radial basis function kernel optimization for support vector machine classifiers, (2020) arXiv preprint arXiv: 2007.08233."},{"key":"10.1016\/j.patcog.2026.113450_bib0031","unstructured":"D. Ulyanov, A. Vedaldi, V. Lempitsky, Instance normalization: the missing ingredient for fast stylization, (2016) arXiv preprint arXiv: 1607.08022."},{"key":"10.1016\/j.patcog.2026.113450_bib0032","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"Huang","year":"2017"},{"key":"10.1016\/j.patcog.2026.113450_bib0033","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3616","article-title":"Style blind domain generalized semantic segmentation via covariance alignment and semantic consistence contrastive learning","author":"Ahn","year":"2024"},{"key":"10.1016\/j.patcog.2026.113450_bib0034","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.patcog.2026.113450_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"847","article-title":"Single-domain generalized object detection in urban scene via cyclic-disentangled self-distillation","author":"Wu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113450_bib0036","unstructured":"C. Michaelis, B. Mitzkus, R. Geirhos, E. Rusak, O. Bringmann, A.S. Ecker, M. Bethge, W. Brendel, Benchmarking robustness in object detection: autonomous driving when winter is coming, (2019) arXiv preprint arXiv: 1907.07484."},{"issue":"6","key":"10.1016\/j.patcog.2026.113450_bib0037","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.2026.113450_bib0038","series-title":"International Conference on Learning Representations (ICLR)","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113450_bib0039","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"1863","article-title":"Switchable whitening for deep representation learning","author":"Pan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113450_bib0040","series-title":"European Conference on Computer Vision (ECCV)","first-page":"464","article-title":"Two at once: enhancing learning and generalization capacities via IBN-Net","author":"Pan","year":"2018"},{"key":"10.1016\/j.patcog.2026.113450_bib0041","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4874","article-title":"Iterative normalization: beyond standardization towards efficient whitening","author":"Huang","year":"2019"},{"key":"10.1016\/j.patcog.2026.113450_bib0042","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11580","article-title":"RobustNet: improving domain generalization in urban-scene segmentation via instance selective whitening","author":"Choi","year":"2021"},{"issue":"7","key":"10.1016\/j.patcog.2026.113450_bib0043","doi-asserted-by":"crossref","first-page":"12497","DOI":"10.1109\/TNNLS.2024.3480120","article-title":"SRCD: Semantic reasoning with compound domains for single-domain generalized object detection","volume":"36","author":"Rao","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"10.1016\/j.patcog.2026.113450_bib0044","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1007\/s11263-023-01911-w","article-title":"Style-hallucinated dual consistency learning: a unified framework for visual domain generalization","volume":"132","author":"Zhao","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113450_bib0045","series-title":"European Conference on Computer Vision (ECCV)","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.113450_bib0046","first-page":"45678","article-title":"Domain generalization for object detection with style randomization","volume":"10","author":"Zhang","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113450_bib0047","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014"},{"key":"10.1016\/j.patcog.2026.113450_bib0048","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.patcog.2026.113450_bib0049","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"8026","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"issue":"2","key":"10.1016\/j.patcog.2026.113450_bib0050","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The Pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113450_bib0051","series-title":"European Conference on Computer Vision (ECCV)","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.113450_bib0052","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.patcog.2026.113450_bib0053","unstructured":"J. Redmon, A. Farhadi, YOLOv3: An incremental improvement, (2018) arXiv preprint arXiv: 1804.02767."},{"key":"10.1016\/j.patcog.2026.113450_bib0054","series-title":"International Conference on Learning Representations (ICLR)","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004164?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004164?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:01:21Z","timestamp":1780491681000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":54,"alternative-id":["S0031320326004164"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113450","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":"Object style diffusion for generalized object detection in urban scene","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113450","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":"113450"}}