{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T15:55:33Z","timestamp":1785167733973,"version":"3.55.0"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:00:00Z","timestamp":1708387200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:00:00Z","timestamp":1708387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00371-024-03284-8","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T07:03:26Z","timestamp":1708412606000},"page":"8927-8944","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["I-YOLO: a novel single-stage framework for small object detection"],"prefix":"10.1007","volume":"40","author":[{"given":"Kang","family":"Tong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiquan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"issue":"1","key":"3284_CR1","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"J Li","year":"2022","unstructured":"Li, J., et al.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Industr. Inf. 18(1), 163\u2013173 (2022)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"9","key":"3284_CR2","doi-asserted-by":"crossref","first-page":"4267","DOI":"10.1007\/s00371-022-02589-w","volume":"39","author":"Z Guo","year":"2023","unstructured":"Guo, Z., Shuai, H., Liu, G., Zhu, Y., Wang, W.: Multi-level feature fusion pyramid network for object detection. Vis. Comput. 39(9), 4267\u20134277 (2023)","journal-title":"Vis. Comput."},{"issue":"4","key":"3284_CR3","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/s00138-023-01402-5","volume":"34","author":"Y Ma","year":"2023","unstructured":"Ma, Y., Wang, Y.: Feature refinement with multi-level context for object detection. Mach. Vis. Appl. 34(4), 49 (2023)","journal-title":"Mach. Vis. Appl."},{"key":"3284_CR4","doi-asserted-by":"crossref","first-page":"103260","DOI":"10.1016\/j.jvcir.2021.103260","volume":"79","author":"Q Wang","year":"2021","unstructured":"Wang, Q., Zhou, L., Yao, Y., Wang, Y., Li, J., Yang, W.: An interconnected feature pyramid Networks for object detection. J. Vis. Commun. Image Represent.Commun. Image Represent. 79, 103260 (2021)","journal-title":"J. Vis. Commun. Image Represent.Commun. Image Represent."},{"issue":"2","key":"3284_CR5","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., et al.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128(2), 261\u2013318 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"3284_CR6","doi-asserted-by":"crossref","unstructured":"Tong, K., Wu, Y.: Object detection with shallow feature learning network. Presented at the 10th International Conference on Computing and Pattern Recognition, Shanghai, China (2021).","DOI":"10.1145\/3497623.3497642"},{"issue":"2","key":"3284_CR7","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1007\/s00371-021-02363-4","volume":"39","author":"H Wang","year":"2023","unstructured":"Wang, H., Chen, Y., Wu, M., Zhang, X., Huang, Z., Mao, W.: Attentional and adversarial feature mimic for efficient object detection. Vis. Comput. 39(2), 639\u2013650 (2023)","journal-title":"Vis. Comput."},{"key":"3284_CR8","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"3284_CR9","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, B., Hong, D., Yao, J., Chanussot, J.: LRR-Net: An interpretable deep unfolding network for hyperspectral anomaly detection. IEEE Trans. Geosci. Remote Sensing 61 (2023).","DOI":"10.1109\/TGRS.2023.3279834"},{"key":"3284_CR10","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","volume":"117","author":"G Cheng","year":"2016","unstructured":"Cheng, G., Han, J.: A survey on object detection in optical remote sensing images. ISPRS J. Photogramm. Remote Sens. 117, 11\u201328 (2016)","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"3284_CR11","doi-asserted-by":"crossref","first-page":"113856","DOI":"10.1016\/j.rse.2023.113856","volume":"299","author":"D Hong","year":"2023","unstructured":"Hong, D., et al.: Cross-city matters: a multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks. Remote Sensing Environ. 299, 113856 (2023)","journal-title":"Remote Sensing Environ."},{"issue":"5","key":"3284_CR12","doi-asserted-by":"crossref","first-page":"4340","DOI":"10.1109\/TGRS.2020.3016820","volume":"59","author":"D Hong","year":"2021","unstructured":"Hong, D., et al.: More diverse means better: multimodal deep learning meets remote-sensing imagery classification. IEEE Trans. Geosci. Remote Sens. 59(5), 4340\u20134354 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"3284_CR13","first-page":"3939","volume":"46","author":"SU Amin","year":"2023","unstructured":"Amin, S.U., Kim, Y., Sami, I., Park, S., Seo, S.: An efficient attention-based strategy for anomaly detection in surveillance video. Comput. Syst. Sci. Eng.. Syst. Sci. Eng. 46(3), 3939\u20133958 (2023)","journal-title":"Comput. Syst. Sci. Eng.. Syst. Sci. Eng."},{"issue":"5","key":"3284_CR14","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1007\/s00371-022-02442-0","volume":"39","author":"H \u00dczen","year":"2023","unstructured":"\u00dczen, H., Turkoglu, M., Aslan, M., Hanbay, D.: Depth-wise squeeze and excitation block-based efficient-unet model for surface defect detection. Vis. Comput. 39(5), 1745\u20131764 (2023)","journal-title":"Vis. Comput."},{"key":"3284_CR15","first-page":"1","volume":"72","author":"X Yu","year":"2023","unstructured":"Yu, X., Li, H.-X., Yang, H.: Collaborative learning classification model for PCBs defect detection against image and label uncertainty. IEEE Trans. Instrum. Meas. 72, 1\u20138 (2023)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"3284_CR16","doi-asserted-by":"crossref","first-page":"104471","DOI":"10.1016\/j.imavis.2022.104471","volume":"123","author":"K Tong","year":"2022","unstructured":"Tong, K., Wu, Y.: Deep learning-based detection from the perspective of small or tiny objects: a survey. Image Vis. Comput.Comput. 123, 104471 (2022)","journal-title":"Image Vis. Comput.Comput."},{"key":"3284_CR17","doi-asserted-by":"crossref","first-page":"105504","DOI":"10.1016\/j.engappai.2022.105504","volume":"117","author":"S-Y Wang","year":"2023","unstructured":"Wang, S.-Y., Qu, Z., Li, C.-J., Gao, L.: BANet: small and multi-object detection with a bidirectional attention network for traffic scenes. Eng. Appl. Artific. Intell. 117, 105504 (2023)","journal-title":"Eng. Appl. Artific. Intell."},{"key":"3284_CR18","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/j.neunet.2022.08.029","volume":"155","author":"K Min","year":"2022","unstructured":"Min, K., Lee, G.-H., Lee, S.-W.: Attentional feature pyramid network for small object detection. Neural Netw. 155, 439\u2013450 (2022)","journal-title":"Neural Netw."},{"issue":"2","key":"3284_CR19","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1109\/TSMC.2020.3005231","volume":"52","author":"G Chen","year":"2022","unstructured":"Chen, G., et al.: A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal. IEEE Trans. Syst. Man Cybern. Syst. 52(2), 936\u2013953 (2022)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"3284_CR20","doi-asserted-by":"crossref","first-page":"103830","DOI":"10.1016\/j.jvcir.2023.103830","volume":"93","author":"K Tong","year":"2023","unstructured":"Tong, K., Wu, Y.: Rethinking PASCAL-VOC and MS-COCO dataset for small object detection. J. Vis. Commun. Image Represent.Commun. Image Represent. 93, 103830 (2023)","journal-title":"J. Vis. Commun. Image Represent.Commun. Image Represent."},{"issue":"16","key":"3284_CR21","doi-asserted-by":"crossref","first-page":"19449","DOI":"10.1007\/s10489-023-04544-1","volume":"53","author":"L Gong","year":"2023","unstructured":"Gong, L., Huang, X., Chao, Y., Chen, J., Lei, B.: An enhanced SSD with feature cross-reinforcement for small-object detection. Appl. Intell. 53(16), 19449\u201319465 (2023)","journal-title":"Appl. Intell."},{"issue":"6","key":"3284_CR22","doi-asserted-by":"crossref","first-page":"3311","DOI":"10.1007\/s10489-020-01949-0","volume":"51","author":"C Sun","year":"2021","unstructured":"Sun, C., Ai, Y., Wang, S., Zhang, W.: Mask-guided SSD for Small-object detection. Appl. Intell. 51(6), 3311\u20133322 (2021)","journal-title":"Appl. Intell."},{"key":"3284_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: Common objects in context. Presented at the Proceedings of European Conference on Computer Vision, Zurich, Switzerland (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3284_CR24","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: WIDER FACE: a face detection benchmark. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV (2016).","DOI":"10.1109\/CVPR.2016.596"},{"key":"3284_CR25","doi-asserted-by":"crossref","unstructured":"Ji, Z., Kong, Q., Wang, H., Pang, Y.: Small and dense commodity object detection with multi-scale receptive field attention. Presented at the ACM International Conference on Multimedia, Nice, France (2019).","DOI":"10.1145\/3343031.3351064"},{"key":"3284_CR26","doi-asserted-by":"crossref","unstructured":"Chen, C., Liu, M.-Y., Tuzel, O., Xiao, J.: R-CNN for small object detection. Presented at the Asian Conference on Computer Vision, Taipei, Taiwan (2016).","DOI":"10.1007\/978-3-319-54193-8_14"},{"key":"3284_CR27","doi-asserted-by":"crossref","unstructured":"Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z.: Scale match for tiny person detection. Presented at the IEEE Winter Conference on Applications of Computer Vision, Snowmass Village, CO (2020).","DOI":"10.1109\/WACV45572.2020.9093394"},{"issue":"2","key":"3284_CR28","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1049\/trit.2019.0019","volume":"4","author":"R Ding","year":"2019","unstructured":"Ding, R., Dai, L., Li, G., Liu, H.: TDD-net: a tiny defect detection network for printed circuit boards. CAAI Trans. Intell. Technol. 4(2), 110\u2013116 (2019)","journal-title":"CAAI Trans. Intell. Technol."},{"key":"3284_CR29","unstructured":"He, F., Tang, S., Mehrkanoon, S., Huang, X., Yang, J.: A real-time PCB defect detector based on supervised and semi-supervised learning. Presented at the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium (2020)."},{"key":"3284_CR30","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. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI (2017).","DOI":"10.1109\/CVPR.2017.211"},{"issue":"6","key":"3284_CR31","doi-asserted-by":"crossref","first-page":"1810","DOI":"10.1007\/s11263-020-01301-6","volume":"128","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Bai, Y., Ding, M., Ghanem, B.: Multi-task generative adversarial network for detecting small objects in the wild. Int. J. Comput. Vision 128(6), 1810\u20131828 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"3284_CR32","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M., Ghanem, B.: SOD-MTGAN: small object detection via multi-task generative adversarial network. Presented at the Proceedings of European Conference on Computer Vision, Munich, Germany, (2018).","DOI":"10.1007\/978-3-030-01261-8_13"},{"issue":"2","key":"3284_CR33","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1109\/TII.2019.2945403","volume":"16","author":"J Lian","year":"2020","unstructured":"Lian, J., et al.: Deep-learning-based small surface defect detection via an exaggerated local variation-based generative adversarial network. IEEE Trans. Industr. Inf. 16(2), 1343\u20131351 (2020)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"3284_CR34","doi-asserted-by":"crossref","first-page":"104197","DOI":"10.1016\/j.imavis.2021.104197","volume":"111","author":"G Liu","year":"2021","unstructured":"Liu, G., Han, J., Rong, W.: Feedback-driven loss function for small object detection. Image Vis. Comput.Comput. 111, 104197 (2021)","journal-title":"Image Vis. Comput.Comput."},{"issue":"2","key":"3284_CR35","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T-Y Lin","year":"2020","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318\u2013327 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3284_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Fang, J., Dou, J., Xue, J.: Small object detection on road by embedding focal-area loss. Resented at the 10th International Conference on Image and Graphics, Beijing, China (2019).","DOI":"10.1007\/978-3-030-34120-6_53"},{"key":"3284_CR37","doi-asserted-by":"crossref","first-page":"115673","DOI":"10.1016\/j.eswa.2021.115673","volume":"185","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Jiang, L., Li, C.: CS-ResNet: Cost-sensitive residual convolutional neural network for PCB cosmetic defect detection. Exp. Syst. Appl. 185, 115673 (2021)","journal-title":"Exp. Syst. Appl."},{"key":"3284_CR38","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.neucom.2020.12.093","volume":"433","author":"J Leng","year":"2021","unstructured":"Leng, J., Ren, Y., Jiang, W., Sun, X., Wang, Y.: Realize your surroundings: exploiting context information for small object detection. Neurocomputing 433, 287\u2013299 (2021)","journal-title":"Neurocomputing"},{"key":"3284_CR39","doi-asserted-by":"crossref","unstructured":"Lim, J.-S., Astrid, M., Yoon, H.-J., Lee, S.-I.: Small object detection using context and attention. Presented at the International Conference on Artificial Intelligence in Information and Communication, Jeju Island, South Korea (2021)","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"issue":"3","key":"3284_CR40","doi-asserted-by":"crossref","first-page":"1921","DOI":"10.1007\/s11063-021-10493-y","volume":"53","author":"Z Yan","year":"2021","unstructured":"Yan, Z., Zheng, H., Li, Y., Chen, L.: Detection-oriented backbone trained from near scratch and local feature refinement for small object detection. Neural. Process. Lett. 53(3), 1921\u20131943 (2021)","journal-title":"Neural. Process. Lett."},{"key":"3284_CR41","first-page":"1","volume":"71","author":"W Liang","year":"2022","unstructured":"Liang, W., Sun, Y.: ELCNN: a deep neural network for small object defect detection of magnetic tile. IEEE Trans. Instrum. Meas.Instrum. Meas. 71, 1\u201310 (2022)","journal-title":"IEEE Trans. Instrum. Meas.Instrum. Meas."},{"key":"3284_CR42","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. Presented at the Proceedings of European Conference on Computer Vision, Amsterdam, The Netherlands (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3284_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3284_CR44","first-page":"1","volume":"71","author":"N Zeng","year":"2022","unstructured":"Zeng, N., Wu, P., Wang, Z., Li, H., Liu, W., Liu, X.: A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection. IEEE Trans. Instrum. Meas.Instrum. Meas. 71, 1\u201314 (2022)","journal-title":"IEEE Trans. Instrum. Meas.Instrum. Meas."},{"key":"3284_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Gao, G., Sun, L., Fang, L.: IPG-Net: image pyramid guidance network for small object detection. Presented at the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA (2020).","DOI":"10.1109\/CVPRW50498.2020.00521"},{"key":"3284_CR46","doi-asserted-by":"crossref","first-page":"104128","DOI":"10.1016\/j.imavis.2021.104128","volume":"108","author":"Q Zheng","year":"2021","unstructured":"Zheng, Q., Chen, Y.: Interactive multi-scale feature representation enhancement for small object detection. Image Vis. Comput.Comput. 108, 104128 (2021)","journal-title":"Image Vis. Comput.Comput."},{"key":"3284_CR47","unstructured":"Cao, G., Xie, X., Yang, W., Liao, Q., Shi, G., Wu, J.: Feature-fused SSD: fast detection for small objects. Presented at the 9th International Conference on Graphic and Image Processing, Qindao, China (2017)."},{"key":"3284_CR48","unstructured":"Li, Z., Zhou, F.: FSSD: feature fusion single shot multibox detector. Comput. Res. Reposit. 5 (2018)."},{"issue":"6","key":"3284_CR49","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1109\/TCSVT.2019.2905881","volume":"30","author":"X Liang","year":"2020","unstructured":"Liang, X., Zhang, J., Zhuo, L., Li, Y., Tian, Q.: Small object detection in unmanned aerial vehicle images using feature fusion and scaling-based single shot detector with spatial context analysis. IEEE Trans. Circuits Syst. Video Technol. 30(6), 1758\u20131770 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3284_CR50","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. Presented at the Neural Information Processing Systems, Montreal, Quebec, Canada (2014)"},{"key":"3284_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Liang, D., Zhang, S.-H., Huang, X., Li, B., Hu, S.-M.: Traffic-sign detection and classification in the wild. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV (2016)","DOI":"10.1109\/CVPR.2016.232"},{"key":"3284_CR52","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.-S.: Tiny object detection in aerial images. Presented at the International Conference on Pattern Recognition Milan, Italy (2021).","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"3284_CR53","doi-asserted-by":"crossref","unstructured":"Yang, C., Huang, Z., Wang, N.: QueryDet: cascaded sparse query for accelerating high-resolution small object detection. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, LA (2022).","DOI":"10.1109\/CVPR52688.2022.01330"},{"issue":"12","key":"3284_CR54","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci.Cogn. Sci. 11(12), 520\u2013527 (2007)","journal-title":"Trends Cogn. Sci.Cogn. Sci."},{"key":"3284_CR55","doi-asserted-by":"crossref","unstructured":"Leng, J., Liu, Y., Gao, X., Wang, Z.: CRNet: context-guided reasoning network for detecting hard objects. IEEE Trans. Multimed. pp 1\u201313 (2023).","DOI":"10.1109\/TMM.2023.3315558"},{"issue":"3","key":"3284_CR56","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1109\/TCSVT.2022.3210207","volume":"33","author":"J Leng","year":"2023","unstructured":"Leng, J., Mo, M., Zhou, Y., Gao, C., Li, W., Gao, X.: Pareto refocusing for drone-view object detection. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1320\u20131334 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3284_CR57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2022.3214929","volume":"19","author":"M Hong","year":"2022","unstructured":"Hong, M., Li, S., Yang, Y., Zhu, F., Zhao, Q., Lu, L.: SSPNet: scale selection pyramid network for tiny person detection from UAV images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"3284_CR58","doi-asserted-by":"crossref","unstructured":"Gong, Y., Yu, X., Ding, Y., Peng, X., Zhao, J., Han, Z.: Effective fusion factor in FPN for tiny object detection. Presented at the IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI (2021).","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"3284_CR59","doi-asserted-by":"crossref","first-page":"1968","DOI":"10.1109\/TMM.2021.3074273","volume":"24","author":"C Deng","year":"2022","unstructured":"Deng, C., Wang, M., Liu, L., Liu, Y., Jiang, Y.: Extended feature pyramid network for small object detection. IEEE Trans. Multimedia 24, 1968\u20131979 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"3284_CR60","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1109\/TIP.2022.3228497","volume":"32","author":"X Wu","year":"2023","unstructured":"Wu, X., Hong, D., Chanussot, J.: UIU-Net: U-Net in U-Net for infrared small object detection. IEEE Trans. Image Process. 32, 364\u2013376 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"3284_CR61","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"3284_CR62","doi-asserted-by":"crossref","unstructured":"Lee, Y., Hwang, J.-W., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. Presented at the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA (2019).","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"3284_CR63","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: CenterMask: real-time anchor-free instance segmentation. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA (2020).","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"3284_CR64","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT (2018).","DOI":"10.1109\/CVPR.2018.00913"},{"key":"3284_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT (2018).","DOI":"10.1109\/CVPR.2018.00716"},{"key":"3284_CR66","doi-asserted-by":"crossref","unstructured":"Krishna, H., Jawahar, C.V.: Improving small object detection. Presented at the Asian Conference on Pattern Recognition, Nanjing, China (2017).","DOI":"10.1109\/ACPR.2017.149"},{"key":"3284_CR67","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.isprsjprs.2022.06.002","volume":"190","author":"C Xu","year":"2022","unstructured":"Xu, C., Wang, J., Yang, W., Yu, H., Yu, L., Xia, G.-S.: Detecting tiny objects in aerial images: a normalized wasserstein distance and a new benchmark. ISPRS J. Photogramm. Remote Sens. 190, 79\u201393 (2022)","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"3284_CR68","doi-asserted-by":"crossref","unstructured":"Sun P., et al.: Sparse R-CNN: End-to-end object detection with learnable proposals. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Virtual (2021).","DOI":"10.1109\/CVPR46437.2021.01422"},{"issue":"6","key":"3284_CR69","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3284_CR70","first-page":"1922","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: a simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 1922\u20131933 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3284_CR71","doi-asserted-by":"crossref","unstructured":"Liu Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. Presented at the IEEE International Conference on Computer Vision, Montreal, QC, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"3","key":"3284_CR72","first-page":"3139","volume":"45","author":"X Li","year":"2023","unstructured":"Li, X., Lv, C., Wang, W., Li, G., Yang, L., Yang, J.: Generalized focal loss: towards efficient representation learning for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3139\u20133153 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3284_CR73","doi-asserted-by":"crossref","unstructured":"Dai, X. et al.: Dynamic head: unifying object detection heads with attentions, Presented at the IEEE Conference on Computer Vision and Pattern Recognition, virtual (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"3284_CR74","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: TOOD: task-aligned one-stage object detection. Presented at the IEEE International Conference on Computer Vision, Montreal, QC, Canada (2021).","DOI":"10.1109\/ICCV48922.2021.00349"},{"issue":"5","key":"3284_CR75","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2021","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3284_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA (2020).","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"3284_CR77","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. Presented at the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA (2019).","DOI":"10.1109\/CVPR.2019.00093"},{"key":"3284_CR78","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.-X.: Scale-aware trident networks for object detection. Presented at the IEEE International Conference on Computer Vision, Seoul, South Korea (2019).","DOI":"10.1109\/ICCV.2019.00615"},{"issue":"4","key":"3284_CR79","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1109\/TIP.2018.2878958","volume":"28","author":"D Hong","year":"2019","unstructured":"Hong, D., Yokoya, N., Chanussot, J., Zhu, X.X.: An augmented linear mixing model to address spectral variability for hyperspectral unmixing. IEEE Trans. Image Process. 28(4), 1923\u20131938 (2019)","journal-title":"IEEE Trans. Image Process."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03284-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03284-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03284-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T09:14:29Z","timestamp":1731402869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03284-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,20]]},"references-count":79,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3284"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03284-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,20]]},"assertion":[{"value":"20 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2024","order":2,"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 or personal relationships related to the work in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}