{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:30:22Z","timestamp":1777656622214,"version":"3.51.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20077-9_30","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"509-525","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":105,"title":["Translation, Scale and\u00a0Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7463-7328","authenticated-orcid":false,"given":"Maoxun","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Yinyan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xingxing","family":"Wei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"issue":"4","key":"30_CR1","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1145\/146370.146374","volume":"24","author":"LG Brown","year":"1992","unstructured":"Brown, L.G.: A survey of image registration techniques. ACM Comput. Surv. (CSUR) 24(4), 325\u2013376 (1992)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"30_CR3","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"30_CR4","first-page":"1","volume":"60","author":"S Cui","year":"2021","unstructured":"Cui, S., Ma, A., Zhang, L., Xu, M., Zhong, Y.: MAP-Net: SAR and optical image matching via image-based convolutional network with attention mechanism and spatial pyramid aggregated pooling. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"30_CR5","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2849\u20132858 (2019)","DOI":"10.1109\/CVPR.2019.00296"},{"key":"30_CR6","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.inffus.2018.11.017","volume":"50","author":"D Guan","year":"2019","unstructured":"Guan, D., Cao, Y., Yang, J., Cao, Y., Yang, M.Y.: Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection. Inf. Fusion 50, 148\u2013157 (2019)","journal-title":"Inf. Fusion"},{"key":"30_CR7","first-page":"1","volume":"60","author":"J Han","year":"2021","unstructured":"Han, J., Ding, J., Li, J., Xia, G.S.: Align deep features for oriented object detection. IEEE Trans. Geosci. Remote Sens. 60, 1\u201311 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"30_CR8","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":"30_CR9","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TCSVT.2021.3076466","volume":"32","author":"JU Kim","year":"2021","unstructured":"Kim, J.U., Park, S., Ro, Y.M.: Uncertainty-guided cross-modal learning for robust multispectral pedestrian detection. IEEE Trans. Circuits Syst. Video Technol. 32, 1510\u20131523 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Lee, J., Seo, S., Kim, M.: SIPSA-Net: shift-invariant pan sharpening with moving object alignment for satellite imagery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10166\u201310174 (2021)","DOI":"10.1109\/CVPR46437.2021.01003"},{"key":"30_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977","volume":"96","author":"C Li","year":"2019","unstructured":"Li, C., Liang, X., Lu, Y., Zhao, N., Tang, J.: RGB-T object tracking: benchmark and baseline. Pattern Recogn. 96, 106977 (2019)","journal-title":"Pattern Recogn."},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., Xu, C., Cui, Z., Wang, D., Zhang, T., Yang, J.: Feature-attentioned object detection in remote sensing imagery. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 3886\u20133890. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803521"},{"key":"30_CR13","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":"30_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S., Wang, S., Metaxas, D.N.: Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644 (2016)","DOI":"10.5244\/C.30.73"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Liu, L., Chen, J., Wu, H., Li, G., Li, C., Lin, L.: Cross-modal collaborative representation learning and a large-scale RGBT benchmark for crowd counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4823\u20134833 (2021)","DOI":"10.1109\/CVPR46437.2021.00479"},{"issue":"8","key":"30_CR17","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., Weng, L., Yang, Y.: 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":"30_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yuan, L., Weng, L., Yang, Y.: A high resolution optical satellite image dataset for ship recognition and some new baselines. In: International Conference on Pattern Recognition Applications and Methods, vol. 2, pp. 324\u2013331. SCITEPRESS (2017)","DOI":"10.5220\/0006120603240331"},{"issue":"11","key":"30_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. Multimed. 20(11), 3111\u20133122 (2018)","journal-title":"IEEE Trans. Multimed."},{"issue":"7","key":"30_CR20","doi-asserted-by":"publisher","first-page":"4834","DOI":"10.1109\/TGRS.2019.2893310","volume":"57","author":"W Ma","year":"2019","unstructured":"Ma, W., Zhang, J., Wu, Y., Jiao, L., Zhu, H., Zhao, W.: A novel two-step registration method for remote sensing images based on deep and local features. IEEE Trans. Geosci. Remote Sens. 57(7), 4834\u20134843 (2019)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Pan, X., et al.: Dynamic refinement network for oriented and densely packed object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11207\u201311216 (2020)","DOI":"10.1109\/CVPR42600.2020.01122"},{"key":"30_CR22","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Richards, J.A., Richards, J.: Remote sensing digital image analysis, vol. 3. Springer (1999)","DOI":"10.1007\/978-3-662-03978-6"},{"key":"30_CR24","unstructured":"Sun, Y., Cao, B., Zhu, P., Hu, Q.: Drone-based RGB-infrared cross-modality vehicle detection via uncertainty-aware learning. arXiv e-prints pp. arXiv-2003 (2020)"},{"issue":"24","key":"30_CR25","doi-asserted-by":"publisher","first-page":"2930","DOI":"10.3390\/rs11242930","volume":"11","author":"J Wang","year":"2019","unstructured":"Wang, J., Ding, J., Guo, H., Cheng, W., Pan, T., Yang, W.: Mask OBB: a semantic attention-based mask oriented bounding box representation for multi-category object detection in aerial images. Remote Sens. 11(24), 2930 (2019)","journal-title":"Remote Sens."},{"key":"30_CR26","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.isprsjprs.2020.09.022","volume":"169","author":"H Wei","year":"2020","unstructured":"Wei, H., Zhang, Y., Chang, Z., Li, H., Wang, H., Sun, X.: Oriented objects as pairs of middle lines. ISPRS J. Photogramm. Remote. Sens. 169, 268\u2013279 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Xia, G.S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974\u20133983 (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3520\u20133529 (2021)","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Ricci, E., Wang, X., Sebe, N.: Learning cross-modal deep representations for robust pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5363\u20135371 (2017)","DOI":"10.1109\/CVPR.2017.451"},{"issue":"4","key":"30_CR30","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2020.2974745","volume":"43","author":"Y Xu","year":"2020","unstructured":"Xu, Y., et al.: Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1452\u20131459 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR31","unstructured":"Yang, X., Liu, Q., Yan, J., Li, A., Zhang, Z., Yu, G.: R3Det: refined single-stage detector with feature refinement for rotating object. arXiv preprint arXiv:1908.05612 2(4) (2019)"},{"key":"30_CR32","unstructured":"Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q.: Rethinking rotated object detection with Gaussian wasserstein distance loss. In: ICML, pp. 11830\u201311841. PMLR (2021)"},{"key":"30_CR33","first-page":"18381","volume":"34","author":"X Yang","year":"2021","unstructured":"Yang, X., et al.: Learning high-precision bounding box for rotated object detection via Kullback-Leibler divergence. Neurips 34, 18381\u201318394 (2021)","journal-title":"Neurips"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Yi, J., Wu, P., Liu, B., Huang, Q., Qu, H., Metaxas, D.: Oriented object detection in aerial images with box boundary-aware vectors. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2150\u20132159 (2021)","DOI":"10.1109\/WACV48630.2021.00220"},{"key":"30_CR35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3040221","volume":"60","author":"H Zhang","year":"2021","unstructured":"Zhang, H., et al.: Explore better network framework for high resolution optical and SAR image matching. IEEE Trans. Geosci. Remote Sens. 60, 1\u201318 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"30_CR36","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","volume":"50","author":"L Zhang","year":"2019","unstructured":"Zhang, L., et al.: Cross-modality interactive attention network for multispectral pedestrian detection. Inf. Fusion 50, 20\u201329 (2019)","journal-title":"Inf. Fusion"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, X., Chen, X., Yang, X., Lei, Z., Liu, Z.: Weakly aligned cross-modal learning for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5127\u20135137 (2019)","DOI":"10.1109\/ICCV.2019.00523"},{"key":"30_CR38","doi-asserted-by":"publisher","first-page":"3321","DOI":"10.1109\/TIP.2019.2959253","volume":"29","author":"Q Zhang","year":"2019","unstructured":"Zhang, Q., Huang, N., Yao, L., Zhang, D., Shan, C., Han, J.: RGB-T salient object detection via fusing multi-level CNN features. IEEE Trans. Image Process. 29, 3321\u20133335 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhao, S., Luo, Y., Zhang, D., Huang, N., Han, J.: ABMDRNet: adaptive-weighted bi-directional modality difference reduction network for RGB-T semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2633\u20132642 (2021)","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"30_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1007\/978-3-030-58523-5_46","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Zhou","year":"2020","unstructured":"Zhou, K., Chen, L., Cao, X.: Improving multispectral pedestrian detection by addressing modality imbalance problems. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 787\u2013803. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_46"},{"key":"30_CR41","doi-asserted-by":"publisher","first-page":"223373","DOI":"10.1109\/ACCESS.2020.3041025","volume":"8","author":"L Zhou","year":"2020","unstructured":"Zhou, L., Wei, H., Li, H., Zhao, W., Zhang, Y., Zhang, Y.: Arbitrary-oriented object detection in remote sensing images based on polar coordinates. IEEE Access 8, 223373\u2013223384 (2020)","journal-title":"IEEE Access"},{"issue":"11","key":"30_CR42","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1016\/S0262-8856(03)00137-9","volume":"21","author":"B Zitova","year":"2003","unstructured":"Zitova, B., Flusser, J.: Image registration methods: a survey. Image Vis. Comput. 21(11), 977\u20131000 (2003)","journal-title":"Image Vis. Comput."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20077-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:18:35Z","timestamp":1667866715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"6 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.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 (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}