{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T02:27:50Z","timestamp":1773714470213,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620609","type":"print"},{"value":"9789819620616","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-2061-6_29","type":"book-chapter","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T05:46:21Z","timestamp":1735537581000},"page":"394-407","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MKSNet: Advanced Small Object Detection in\u00a0Remote Sensing Imagery with\u00a0Multi-Kernel and\u00a0Dual Attention Mechanisms"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0847-5805","authenticated-orcid":false,"given":"Jiahao","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Xiao","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0083-3016","authenticated-orcid":false,"given":"Guangyu","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Chen, H., Chu, X., Ren, Y., Zhao, X., Huang, K.: Pelk: parameter-efficient large kernel convnets with peripheral convolution. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 5557\u20135567 (2024)","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 11030\u201311039 (2020)","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proc. IEEE CVPR, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Long, Y., Xia, G.S., Lu, Q.: Learning roi transformer for oriented object detection in aerial images. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2849\u20132858 (2019)","DOI":"10.1109\/CVPR.2019.00296"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31x31: revisiting large kernel design in cnns. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11963\u201311975 (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"29_CR6","unstructured":"Everingham, M.: The pascal visual object classes challenge 2007. In: http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html (2009)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Han, J., Ding, J., Xue, N., Xia, G.S.: Redet: A rotation-equivariant detector for aerial object detection. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2786\u20132795 (2021)","DOI":"10.1109\/CVPR46437.2021.00281"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Hu, J., et\u00a0al.: Squeeze-and-excitation networks. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"29_CR11","unstructured":"Huang, Q., Li, W., Xie, X.: Convolutional neural network for medical hyperspectral image classification with kernel fusion. In: Proceedings of International Conference on BIBE, pp.\u00a01\u20134 (2018)"},{"key":"29_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"29_CR13","unstructured":"Lang, S., Ventola, F., Kersting, K.: Dafne: a one-stage anchor-free approach for oriented object detection. arXiv preprint arXiv:2109.06148 (2021)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Hou, Q., Zheng, Z., Cheng, M.M., Yang, J., Li, X.: Large selective kernel network for remote sensing object detection. In: Proc. IEEE International Conference on Computer Vision, pp. 16794\u201316805 (2023)","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"29_CR15","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: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proc. IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"29_CR18","unstructured":"Liu, B., Wang, M., Foroosh, H., Tappen, M., Pensky, M.: Sparse convolutional neural networks. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 806\u2013814 (2015)"},{"key":"29_CR19","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1016\/j.procs.2016.07.144","volume":"91","author":"Y Liu","year":"2016","unstructured":"Liu, Y., Wu, L.: Geological disaster recognition on optical remote sensing images using deep learning. Procedia Comput. Sci. 91, 566\u2013575 (2016)","journal-title":"Procedia Comput. Sci."},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"8","key":"29_CR21","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1109\/LGRS.2016.2565705","volume":"13","author":"Z Liu","year":"2016","unstructured":"Liu, Z., Wang, H., et al.: Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds. IEEE Geosci. Remote Sens. Lett. 13(8), 1074\u20131078 (2016)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"29_CR22","unstructured":"Lyu, C., et al.: Rtmdet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)"},{"key":"29_CR23","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? Proc. Neural Information Processing Systems 34, 12116\u201312128 (2021)","journal-title":"Proc. Neural Information Processing Systems"},{"key":"29_CR24","unstructured":"Tan, M., Le, Q.V.: Mixconv: mixed depthwise convolutional kernels. arXiv preprint arXiv:1907.09595 (2019)"},{"issue":"5","key":"29_CR25","doi-asserted-by":"publisher","first-page":"4307","DOI":"10.1109\/TGRS.2020.3010051","volume":"59","author":"J Wang","year":"2020","unstructured":"Wang, J., Yang, W., Li, H.C., Zhang, H., Xia, G.S.: Learning center probability map for detecting objects in aerial images. IEEE Trans. Geosci. Remote Sens. 59(5), 4307\u20134323 (2020)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., et\u00a0al.: Eca-net: efficient channel attention for deep convolutional neural networks. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"29_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103319","volume":"122","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Zhao, G., Xiong, K., Shi, G.: Msff-net: multi-scale feature fusing networks with dilated mixed convolution and cascaded parallel framework for sound event detection. Digital Signal Process. 122, 103319 (2022)","journal-title":"Digital Signal Process."},{"issue":"1","key":"29_CR28","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/rs11010020","volume":"11","author":"Y Wang","year":"2018","unstructured":"Wang, Y., Liang, B., Ding, M., Li, J.: Dense semantic labeling with atrous spatial pyramid pooling and decoder for high-resolution remote sensing imagery. Remote Sensing 11(1), 20 (2018)","journal-title":"Remote Sensing"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., et\u00a0al.: Cbam: Convolutional block attention module. In: Proc. European Conference on Computer Vision, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Xia, G.S., et al.: Dota: a large-scale dataset for object detection in aerial images. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974\u20133983 (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented r-cnn for object detection. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3520\u20133529 (2021)","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"29_CR32","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2061-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T06:07:48Z","timestamp":1735538868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2061-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"ISBN":["9789819620609","9789819620616"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2061-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]},"assertion":[{"value":"31 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}