{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:32:42Z","timestamp":1774398762677,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T00:00:00Z","timestamp":1620950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T00:00:00Z","timestamp":1620950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871024"],"award-info":[{"award-number":["61871024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Science Projects of Shanxi Province","award":["201903D03111114"],"award-info":[{"award-number":["201903D03111114"]}]},{"name":"Science and technology project of Shanxi Jinzhong Development Zone"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s10489-021-02445-9","type":"journal-article","created":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T06:02:48Z","timestamp":1620972168000},"page":"967-981","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Data augmentation for thermal infrared object detection with cascade pyramid generative adversarial network"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7094-108X","authenticated-orcid":false,"given":"Xuerui","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueye","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,14]]},"reference":[{"key":"2445_CR1","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J et al (2018) Recent advances in convolutional neural networks. Pattern Recog 77:354\u2013377","journal-title":"Pattern Recog"},{"issue":"6","key":"2445_CR2","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton G et al (2012) Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Proc Mag 29(6):82\u201397","journal-title":"IEEE Signal Proc Mag"},{"issue":"6","key":"2445_CR3","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R et al (2015) Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2445_CR4","doi-asserted-by":"crossref","unstructured":"Redmon J et al (2016) You only look once: Unified real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.91"},{"issue":"4","key":"2445_CR5","first-page":"640","volume":"39","author":"J Long","year":"2014","unstructured":"Long J, Shelhamer E, Darrell T (2014) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"2445_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen LC et al (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2445_CR7","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"2445_CR8","doi-asserted-by":"crossref","unstructured":"Gaidon A, Wang Q, Cabon Y, Vig E (2016) Virtual worlds as proxy for multi-object tracking analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4340\u20134349","DOI":"10.1109\/CVPR.2016.470"},{"key":"2445_CR9","volume-title":"A naturalistic open source movie for optical flow evaluation European conference on computer vision","author":"DJ Butler","year":"2012","unstructured":"Butler DJ et al (2012) A naturalistic open source movie for optical flow evaluation European conference on computer vision. Springer, Berlin Heidelberg"},{"key":"2445_CR10","unstructured":"Denton EL, Chintala S, Fergus R (2015) Deep generative image models using a laplacian pyramid of adversarial networks. In: Advances in neural information processing systems, pp 1486\u20131494"},{"key":"2445_CR11","doi-asserted-by":"crossref","unstructured":"Zhu JY, Krahenbhl P, Shechtman E, Efros AA (2016) Generative visual manipulation on the natural image manifold. In: European conference on computer vision. Springer, Cham, pp 597\u2013613","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"2445_CR12","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu JY, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"2445_CR13","unstructured":"Zhu JY, Zhang R, Pathak D, Darrell T, Efros AA, Wang O, Shechtman E (2017) Toward multimodal image-to-image translation. In: Advances in neural information processing systems, pp 465\u2013476"},{"key":"2445_CR14","doi-asserted-by":"crossref","unstructured":"Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"2445_CR15","doi-asserted-by":"crossref","unstructured":"Ciregan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3642\u20133649","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"2445_CR16","unstructured":"Karras T et al (2017) Progressive growing of gans for improved quality, stability, and variation. arXiv:1710.10196"},{"key":"2445_CR17","doi-asserted-by":"crossref","unstructured":"Chen Q, Koltun V (2017) Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE international conference on computer vision","DOI":"10.1109\/ICCV.2017.168"},{"key":"2445_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2445_CR19","doi-asserted-by":"crossref","unstructured":"Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: AAAI, pp 13001\u201313008","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"2445_CR20","unstructured":"Girshick R, Radosavovic I, Gkioxari G, Dollr P, He K (2018) Detectron. https:\/\/github.com\/facebookresearch\/detectron"},{"key":"2445_CR21","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2445_CR22","unstructured":"Yin D, Lopes RG, Shlens J, Cubuk ED, Gilmer J (2019) A fourier perspective on model robustness in computer vision. In: Advances in Neural Information Processing Systems, pp 13276\u2013 13286"},{"key":"2445_CR23","unstructured":"Lopes RG, Yin D, Poole B, Gilmer J, Cubuk ED (2019) Improving robustness without sacrificing accuracy with patch gaussian augmentation. arXiv:1906.02611"},{"key":"2445_CR24","doi-asserted-by":"crossref","unstructured":"Wang X, Shrivastava A, Gupta A (2017) A-fast-rcnn: Hard positive generation via adversary for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2606\u20132615","DOI":"10.1109\/CVPR.2017.324"},{"key":"2445_CR25","doi-asserted-by":"crossref","unstructured":"Dwibedi D, Misra I, Hebert M (2017) Cut, paste and learn: Surprisingly easy synthesis for instance detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1301\u20131310","DOI":"10.1109\/ICCV.2017.146"},{"key":"2445_CR26","doi-asserted-by":"crossref","unstructured":"Ros G, Sellart L, Materzynska J, Vazquez D, Lopez AM (2016) The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3234\u20133243","DOI":"10.1109\/CVPR.2016.352"},{"key":"2445_CR27","doi-asserted-by":"crossref","unstructured":"Handa A, Patraucean V, Badrinarayanan V et al (2015) SceneNet: understanding real world indoor scenes with synthetic data.arXiv:1511.07041","DOI":"10.1109\/CVPR.2016.442"},{"key":"2445_CR28","doi-asserted-by":"crossref","unstructured":"Gaidon A, Wang Q, Cabon Y, Vig E (2016) Virtual worlds as proxy for multi-object tracking analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4340\u20134349","DOI":"10.1109\/CVPR.2016.470"},{"key":"2445_CR29","doi-asserted-by":"crossref","unstructured":"Hinterstoisser Stefan et al (2018) On pre-trained image features and synthetic images for deep learning. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-11009-3_42"},{"key":"2445_CR30","doi-asserted-by":"crossref","unstructured":"Tobin J, Fong R, Ray A, Schneider J, Zaremba W, Abbeel P (2017) Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 23\u201330","DOI":"10.1109\/IROS.2017.8202133"},{"key":"2445_CR31","doi-asserted-by":"crossref","unstructured":"Sundermeyer M, Marton ZC, Durner M, Brucker M, Triebel R (2018) Implicit 3d orientation learning for 6d object detection from rgb images. In: Proceedings of the european conference on computer vision (ECCV), pp 699\u2013715","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"2445_CR32","doi-asserted-by":"crossref","unstructured":"Tremblay J, Prakash A, Acuna D, Brophy M, Jampani V, Anil C, Birchfield S (2018) Training deep networks with synthetic data: Bridging the reality gap by domain randomization. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 969\u2013977","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"2445_CR33","unstructured":"Zhu Y, Urtasun R, Salakhutdinov R, Fidler S (2015) segdeepm: Exploiting segmentation and context in deep neural networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4703\u20134711"},{"key":"2445_CR34","doi-asserted-by":"crossref","unstructured":"Georgakis G, Mousavian A, Berg AC, Kosecka J (2017) Synthesizing training data for object detection in indoor scenes. arXiv:1702.07836","DOI":"10.15607\/RSS.2017.XIII.043"},{"key":"2445_CR35","doi-asserted-by":"crossref","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision. Springer, Cham, pp 694\u2013711","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"2445_CR36","doi-asserted-by":"crossref","unstructured":"Kaneko T, Hiramatsu K, Kashino K (2017) Generative attribute controller with conditional filtered generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6089\u20136098","DOI":"10.1109\/CVPR.2017.741"},{"key":"2445_CR37","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:1411.1784"},{"key":"2445_CR38","doi-asserted-by":"crossref","unstructured":"Chen Q, Koltun V (2017) Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE international conference on computer vision, pp 1511\u20131520","DOI":"10.1109\/ICCV.2017.168"},{"key":"2445_CR39","unstructured":"Dosovitskiy A, Brox T (2016) Generating images with perceptual similarity metrics based on deep networks. In: Advances in neural information processing systems, pp 658\u2013666"},{"issue":"10","key":"2445_CR40","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1109\/TPAMI.2017.2753232","volume":"40","author":"Y Aytar","year":"2017","unstructured":"Aytar Y, Castrejon L, Vondrick C, Pirsiavash H, Torralba A (2017) Cross-modal scene networks. IEEE Trans Pattern Anal Mach Intell 40(10):2303\u20132314","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2445_CR41","unstructured":"Liu MY, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems, pp 700\u2013708"},{"key":"2445_CR42","doi-asserted-by":"crossref","unstructured":"Huang X, Liu MY, Belongie S, Kautz J (2018) Multimodal unsupervised image-to-image translation. In: Proceedings of the european conference on computer vision (ECCV), pp 172\u2013189","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"2445_CR43","doi-asserted-by":"crossref","unstructured":"Wang TC et al (2018) High-resolution image synthesis and semantic manipulation with conditional gans. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00917"},{"key":"2445_CR44","doi-asserted-by":"crossref","unstructured":"Cho W, Choi S, Park DK, Shin I, Choo J (2019) Image-to-image translation via group-wise deep whitening-and-coloring transformation. In: Proceedings of the IEEE conference on computer vision pattern recognition, pp 10639\u201310647","DOI":"10.1109\/CVPR.2019.01089"},{"key":"2445_CR45","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE international conference on computer vision, pp 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2445_CR46","unstructured":"Kingma DP, Ba LJ (2014) Adam: A method for stochastic optimization. arXiv:1412.6980"},{"key":"2445_CR47","doi-asserted-by":"publisher","unstructured":"Dai X, Yuan X, Wei X (2020) TIRNet: Object detection in thermal infrared images for autonomous driving. Appl Intell. https:\/\/doi.org\/10.1007\/s10489-020-01882-2","DOI":"10.1007\/s10489-020-01882-2"},{"key":"2445_CR48","unstructured":"Li Y, He K, Sun J et al (2016) R-FCN: Object detection via region-based fully convolutional networks. In: NIPS"},{"key":"2445_CR49","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.690"},{"key":"2445_CR50","unstructured":"Redmon J, Yolov3 AF (2018) An incremental improvement. arXiv:1804.02767"},{"key":"2445_CR51","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: Optimal speed and accuracy of object detection. arXiv:2004.10934"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02445-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02445-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02445-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T06:42:33Z","timestamp":1642142553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02445-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,14]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["2445"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02445-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,14]]},"assertion":[{"value":"18 April 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}