{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:47:48Z","timestamp":1774540068250,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T00:00:00Z","timestamp":1711756800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T00:00:00Z","timestamp":1711756800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province under Grant","award":["2020B0909020001"],"award-info":[{"award-number":["2020B0909020001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61573113"],"award-info":[{"award-number":["61573113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s11554-024-01446-4","type":"journal-article","created":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T17:01:50Z","timestamp":1711818110000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["GAN-STD: small target detection based on generative adversarial network"],"prefix":"10.1007","volume":"21","author":[{"given":"Huilin","family":"Wang","sequence":"first","affiliation":[]},{"given":"Huaming","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"1446_CR1","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2021.0121094","author":"I Ahmad","year":"2021","unstructured":"Ahmad, I., AlQurashi, F., Abozinadah, E., Mehmood, R.: A novel deep learning-based online proctoring system using face recognition, eye blinking, and object detection techniques. Int. J. Adv. Comput. Sci. Appl. (2021). https:\/\/doi.org\/10.14569\/ijacsa.2021.0121094","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"1446_CR2","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: 2010 IEEE computer society conference on computer vision and pattern recognition, pp. 73\u201380. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"1446_CR3","doi-asserted-by":"crossref","unstructured":"Bell, S., Zitnick, C.L., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2874\u20132883 (2016)","DOI":"10.1109\/CVPR.2016.314"},{"key":"1446_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106730","volume":"194","author":"M Billah","year":"2022","unstructured":"Billah, M., Wang, X., Yu, J., Jiang, Y.: Real-time goat face recognition using convolutional neural network. Comput. Electron. Agric. 194, 106730 (2022)","journal-title":"Comput. Electron. Agric."},{"key":"1446_CR5","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1446_CR6","doi-asserted-by":"crossref","unstructured":"Cui, J.: Image style migration algorithm based on hsv color model. In: 2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), pp. 111\u2013114. IEEE (2022)","DOI":"10.1109\/AEECA55500.2022.9919019"},{"key":"1446_CR7","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-fcn: Object detection via region-based fully convolutional networks. Adv. Neural Inform. Process. Syst. 29 (2016)"},{"issue":"6","key":"1446_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3456726","volume":"12","author":"FA Dharejo","year":"2021","unstructured":"Dharejo, F.A., Deeba, F., Zhou, Y., Das, B., Jatoi, M.A., Zawish, M., Du, Y., Wang, X.: Twist-GAN: Towards wavelet transform and transferred GAN for spatio-temporal single image super resolution. ACM Trans. Intell. Syst. Technol. (TIST) 12(6), 1\u201320 (2021)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"1446_CR9","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"1446_CR10","unstructured":"Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)"},{"key":"1446_CR11","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: Proceedings of the IEEE international conference on computer vision, pp. 1134\u20131142 (2015)","DOI":"10.1109\/ICCV.2015.135"},{"key":"1446_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-CNN. In: Proceedings of the IEEE international conference on computer vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1446_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"11","key":"1446_CR14","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"1446_CR15","doi-asserted-by":"crossref","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., et\u00a0al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7310\u20137311 (2017)","DOI":"10.1109\/CVPR.2017.351"},{"issue":"7","key":"1446_CR16","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.3390\/rs14071552","volume":"14","author":"H Jiang","year":"2022","unstructured":"Jiang, H., Peng, M., Zhong, Y., Xie, H., Hao, Z., Lin, J., Ma, X., Hu, X.: A survey on deep learning-based change detection from high-resolution remote sensing images. Remote Sens. 14(7), 1552 (2022)","journal-title":"Remote Sens."},{"key":"1446_CR17","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Tan, C., Liu, H., Huang, W.: Deep feature pyramid reconfiguration for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp. 169\u2013185 (2018)","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"1446_CR18","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: object localization by efficient subwindow search. In: 2008 IEEE conference on computer vision and pattern recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587586"},{"key":"1446_CR19","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1446_CR20","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et\u00a0al.: Yolov6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"1446_CR21","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.Y., et\u00a0al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. arXiv preprint arXiv:2206.02777 (2022)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"1446_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1222\u20131230 (2017)","DOI":"10.1109\/CVPR.2017.211"},{"key":"1446_CR23","unstructured":"Li, Z., Zhou, F.: Fssd: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960 (2017)"},{"key":"1446_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1446_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European conference on computer vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1446_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. Springer, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1446_CR27","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1446_CR28","doi-asserted-by":"publisher","first-page":"5184","DOI":"10.1109\/ACCESS.2022.3140876","volume":"10","author":"S Luo","year":"2022","unstructured":"Luo, S., Yu, J., Xi, Y., Liao, X.: Aircraft target detection in remote sensing images based on improved yolov5. IEEE Access 10, 5184\u20135192 (2022)","journal-title":"IEEE Access"},{"issue":"1","key":"1446_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-12646-y","volume":"12","author":"D Mukherkjee","year":"2022","unstructured":"Mukherkjee, D., Saha, P., Kaplun, D., Sinitca, A., Sarkar, R.: Brain tumor image generation using an aggregation of GAN models with style transfer. Sci. Rep. 12(1), 1\u201316 (2022)","journal-title":"Sci. Rep."},{"issue":"1","key":"1446_CR30","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/0031-3203(95)00067-4","volume":"29","author":"T Ojala","year":"1996","unstructured":"Ojala, T., Pietik\u00e4inen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recogn. 29(1), 51\u201359 (1996)","journal-title":"Pattern Recogn."},{"key":"1446_CR31","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1016\/j.procs.2022.12.278","volume":"217","author":"D Pasanisi","year":"2023","unstructured":"Pasanisi, D., Rota, E., Ermidoro, M., Fasanotti, L.: On domain randomization for object detection in real industrial scenarios using synthetic images. Procedia Comput. Sci. 217, 816\u2013825 (2023)","journal-title":"Procedia Comput. Sci."},{"issue":"10","key":"1446_CR32","doi-asserted-by":"publisher","first-page":"6657","DOI":"10.1109\/TCSVT.2022.3177238","volume":"32","author":"F Peng","year":"2022","unstructured":"Peng, F., Yin, L., Long, M.: Bdc-GAN: bidirectional conversion between computer-generated and natural facial images for anti-forensics. IEEE Trans. Circuits Syst. Video Technol. 32(10), 6657\u20136670 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1446_CR33","doi-asserted-by":"crossref","unstructured":"Qi, D., Tan, W., Yao, Q., Liu, J.: Yolo5face: why reinventing a face detector. In: Computer Vision\u2013ECCV 2022 Workshops: Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part V, pp. 228\u2013244. Springer (2023)","DOI":"10.1007\/978-3-031-25072-9_15"},{"issue":"1","key":"1446_CR34","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11554-023-01258-y","volume":"20","author":"H Qian","year":"2023","unstructured":"Qian, H., Wang, H., Feng, S., Yan, S.: Fessd: Ssd target detection based on feature fusion and feature enhancement. J. Real-Time Image Proc. 20(1), 2 (2023)","journal-title":"J. Real-Time Image Proc."},{"key":"1446_CR35","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: you only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1446_CR36","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1446_CR37","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1446_CR38","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","volume":"81","author":"J Shotton","year":"2009","unstructured":"Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int. J. Comput. Vis. 81, 2\u201323 (2009)","journal-title":"Int. J. Comput. Vis."},{"key":"1446_CR39","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57, 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1446_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-023-05380-3","volume":"79","author":"H Wang","year":"2023","unstructured":"Wang, H., Qian, H., Feng, S., Yan, S.: Calyolov4: lightweight yolov4 target detection based on coordinated attention. J. Supercomput. 79, 1\u201323 (2023)","journal-title":"J. Supercomput."},{"key":"1446_CR41","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1109\/TETCI.2023.3235381","volume":"7","author":"H Wang","year":"2023","unstructured":"Wang, H., Xu, Y., Wang, Z., Cai, Y., Chen, L., Li, Y.: Centernet-auto: a multi-object visual detection algorithm for autonomous driving scenes based on improved centernet. IEEE Trans. Emerg. Topics Comput. Intell. 7, 742\u2013752 (2023)","journal-title":"IEEE Trans. Emerg. Topics Comput. Intell."},{"key":"1446_CR42","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, Y., Fan, Y., Wang, J., Chen, Q.: High-fidelity GAN inversion for image attribute editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11379\u201311388 (2022)","DOI":"10.1109\/CVPR52688.2022.01109"},{"key":"1446_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102827","volume":"189","author":"J Yi","year":"2019","unstructured":"Yi, J., Wu, P., Metaxas, D.N.: Assd: attentive single shot multibox detector. Comput. Vis. Image Understand 189, 102827 (2019)","journal-title":"Comput. Vis. Image Understand"},{"key":"1446_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Qiao, S., Xie, C., Shen, W., Wang, B., Yuille, A.L.: Single-shot object detection with enriched semantics. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5813\u20135821 (2018)","DOI":"10.1109\/CVPR.2018.00609"},{"issue":"1","key":"1446_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-1207-x","volume":"17","author":"H Zhao","year":"2023","unstructured":"Zhao, H., Min, W., Xu, J., Wang, Q., Zou, Y., Fu, Q.: Scene-adaptive crowd counting method based on meta learning with dual-input network dmnet. Front. Comp. Sci. 17(1), 171304 (2023)","journal-title":"Front. Comp. Sci."},{"key":"1446_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2022.116874","volume":"110","author":"X Zhao","year":"2023","unstructured":"Zhao, X., Xiao, J., Zhang, B., Zhang, Q., Waleed, A.N.: Weight-guided loss for long-tailed object detection and instance segmentation. Signal Process. Image Commun. 110, 116874 (2023)","journal-title":"Signal Process. Image Commun."},{"key":"1446_CR47","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, pp. 391\u2013405 (2014)","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01446-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01446-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01446-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T08:33:28Z","timestamp":1717662808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01446-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,30]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1446"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01446-4","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,30]]},"assertion":[{"value":"21 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"65"}}