{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:50:56Z","timestamp":1772905856126,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208929","type":"print"},{"value":"9783030208936","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20893-6_10","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:25:52Z","timestamp":1559013952000},"page":"150-165","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":209,"title":["Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6084-2272","authenticated-orcid":false,"given":"Seyed Majid","family":"Azimi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7015-6874","authenticated-orcid":false,"given":"Eleonora","family":"Vig","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6999-714X","authenticated-orcid":false,"given":"Reza","family":"Bahmanyar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9186-4175","authenticated-orcid":false,"given":"Marco","family":"K\u00f6rner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8122-1475","authenticated-orcid":false,"given":"Peter","family":"Reinartz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Improving object detection with one line of code. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"10_CR2","first-page":"7405","volume":"54","author":"G Cheng","year":"2016","unstructured":"Cheng, G., Zhou, P., Han, J.: Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE TGRS 54, 7405\u20137415 (2016)","journal-title":"IEEE TGRS"},{"key":"10_CR3","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: Object detection via region-based fully convolutional networks. In: NIPS (2016)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR6","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object classes (VOC) challenge. IJCV 88, 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"10_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-319-46487-9_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Ghiasi","year":"2016","unstructured":"Ghiasi, G., Fowlkes, C.C.: Laplacian pyramid reconstruction and refinement for semantic segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 519\u2013534. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46487-9_32"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-33712-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D Hoiem","year":"2012","unstructured":"Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 340\u2013353. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-33712-3_25"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Honari, S., Yosinski, J., Vincent, P., Pal, C.: Recombinator networks: learning coarse-to-fine feature aggregation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.619"},{"key":"10_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"10_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR16","first-page":"1938","volume":"12","author":"K Liu","year":"2015","unstructured":"Liu, K., Mattyus, G.: Fast multiclass vehicle detection on aerial images. IEEE TGRS Lett. 12, 1938\u20131942 (2015)","journal-title":"IEEE TGRS Lett."},{"key":"10_CR17","unstructured":"Liu, L., Pan, Z., Lei, B.: Learning a rotation invariant detector with rotatable bounding box. arXiv preprint \n                      arXiv:1711.09405\n                      \n                     (2017)"},{"key":"10_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia 20, 3111\u20133122 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"10_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"10_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-319-46448-0_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"PO Pinheiro","year":"2016","unstructured":"Pinheiro, P.O., Lin, T.-Y., Collobert, R., Doll\u00e1r, P.: Learning to refine object segments. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 75\u201391. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_5"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"10_CR23","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"10_CR24","unstructured":"Ross, G.: Fast R-CNN. In: CVPR (2015)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"10_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICRL (2015)"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Sommer, L.W., Schuchert, T., Beyerer, J.: Deep learning based multi-category object detection in aerial images. In: SPIE Defense and Security (2017)","DOI":"10.1117\/12.2262083"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"2","key":"10_CR29","first-page":"336","volume":"17","author":"T Tang","year":"2017","unstructured":"Tang, T., Zhou, S., Deng, Z., Zou, H., Lei, L.: Vehicle detection in aerial images based on region convolutional neural networks and hard negative example mining. Remote Sens. 17(2), 336 (2017)","journal-title":"Remote Sens."},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Xia, G., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"key":"10_CR31","doi-asserted-by":"publisher","first-page":"132","DOI":"10.3390\/rs10010132","volume":"10","author":"X Yang","year":"2018","unstructured":"Yang, X., et al.: Automatic ship detection in remote sensing images from Google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sens. 10, 132 (2018)","journal-title":"Remote Sens."},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Yang, X., Sun, H., Sun, X., Yan, M., Guo, Z., Fu, K.: Position detection and direction prediction for arbitrary-oriented ships via multiscale rotation region convolutional neural network. arXiv preprint \n                      arXiv:1806.04828\n                      \n                     (2018)","DOI":"10.1109\/ACCESS.2018.2869884"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. arXiv preprint \n                      arXiv:1704.08545\n                      \n                     (2017)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, H., Chen, X., Dai, W., Fu, K., Ye, Q., Ji, X.: Orientation robust object detection in aerial images using deep convolutional neural network. In: ICIP (2015)","DOI":"10.1109\/ICIP.2015.7351502"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20893-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T03:35:14Z","timestamp":1559014514000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}