{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T04:18:26Z","timestamp":1744345106982,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784929"},{"type":"electronic","value":"9789819784936"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-8493-6_1","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T20:02:16Z","timestamp":1730404936000},"page":"3-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scale-Adaptive Modulation Meet Compact Axial Transformer for\u00a0Small Object Detection in\u00a0UAV-Vision"],"prefix":"10.1007","author":[{"given":"Yangyang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijie","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"1_CR1","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":"1_CR2","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":"12","key":"1_CR3","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2021","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S., Zhou, J.: A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans. Neural Networks Learn. Syst. 33(12), 6999\u20137019 (2021)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"6","key":"1_CR4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"1_CR5","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR7","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.psep.2021.06.005","volume":"152","author":"P Dey","year":"2021","unstructured":"Dey, P., Chaulya, S., Kumar, S.: Hybrid CNN-LSTM and IoT-based coal mine hazards monitoring and prediction system. Process Saf. Environ. Prot. 152, 249\u2013263 (2021)","journal-title":"Process Saf. Environ. Prot."},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Pu, Y., Wang, Y., Xia, Z., Han, Y., Wang, Y., Gan, W., Wang, Z., Song, S., Huang, G.: Adaptive rotated convolution for rotated object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6589\u20136600 (2023)","DOI":"10.1109\/ICCV51070.2023.00606"},{"key":"1_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.isprsjprs.2021.09.005","volume":"181","author":"R Li","year":"2021","unstructured":"Li, R., Zheng, S., Zhang, C., Duan, C., Wang, L., Atkinson, P.M.: ABCNet: attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remotely sensed imagery. ISPRS J. Photogramm. Remote. Sens. 181, 84\u201398 (2021)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Li, J., Tian, P., Song, R., Xu, H., Li, Y., Du, Q.: PCViT: a pyramid convolutional vision transformer detector for object detection in remote sensing imagery. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3360456"},{"key":"1_CR15","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Schiele, B., Vedaldi, A., Rupprecht, C.: Continual detection transformer for incremental object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23799\u201323808 (2023)","DOI":"10.1109\/CVPR52729.2023.02279"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Qiao, S., Zhao, Z., Xie, C., Chen, X., Xia, C.: Rethinking lightweight salient object detection via network depth-width tradeoff. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3318959"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., Wang, S., Ge, Y., Shan, Y., Wang, X.: Unleashing vanilla vision transformer with masked image modeling for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6244\u20136253 (2023)","DOI":"10.1109\/ICCV51070.2023.00574"},{"key":"1_CR19","first-page":"1","volume":"61","author":"P Song","year":"2022","unstructured":"Song, P., Li, J., An, Z., Fan, H., Fan, L.: CTMFNet: CNN and transformer multiscale fusion network of remote sensing urban scene imagery. IEEE Trans. Geosci. Remote Sens. 61, 1\u201314 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1_CR20","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","volume":"190","author":"L Wang","year":"2022","unstructured":"Wang, L., Li, R., Zhang, C., Fang, S., Duan, C., Meng, X., Atkinson, P.M.: UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS J. Photogramm. Remote. Sens. 190, 196\u2013214 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Varghese, R., Sambath, M.: Yolov8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/ADICS58448.2024.10533619"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8493-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T19:08:31Z","timestamp":1744312111000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8493-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819784929","9789819784936"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8493-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}