{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:17:04Z","timestamp":1742941024525,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031476334"},{"type":"electronic","value":"9783031476341"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-47634-1_30","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:01:39Z","timestamp":1699128099000},"page":"400-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Object Detection Algorithm Based on\u00a0Bimodal Feature Alignment"],"prefix":"10.1007","author":[{"given":"Ying","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sugang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiulun","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D object detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Kim, S., Song, W.J., Kim, S.H.: Infrared variation optimized deep convolutional neural network for robust automatic ground target recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, pp. 1\u20138 (2017)","DOI":"10.1109\/CVPRW.2017.30"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Valverde, F.R., Hurtado, J.V., Valada, A.: There is more than meets the eye: self-supervised multi-object detection and tracking with sound by distilling multimodal knowledge. In: 2021 IEEE Conference on Computer Vision and Pattern Recognition, pp. 11612\u201311621 (2021)","DOI":"10.1109\/CVPR46437.2021.01144"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S., Wang, S.: Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644 (2016)","DOI":"10.5244\/C.30.73"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Konig, D., Adam, M., Jarvers, C., Layher, G.: Fully convolutional region proposal networks for multispectral person detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 49\u201356 (2017)","DOI":"10.1109\/CVPRW.2017.36"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Pfeuffer, A., Dietmayer, K.: Optimal sensor data fusion architecture for object detection in adverse weather conditions. In: International Conference on Information Fusion, England, UK, pp. 1\u20138 (2018)","DOI":"10.23919\/ICIF.2018.8455757"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"30_CR9","unstructured":"Ren, S., He, K., Girshick, R.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 91\u201399 (2015)"},{"key":"30_CR10","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). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"30_CR13","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"30_CR14","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv pre4print arXiv:2004.10934 (2020)"},{"key":"30_CR15","unstructured":"YOLOv5. https:\/\/github.com\/ultralytics\/yolov5. Accessed 4 Oct 2022"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: 2018 European Conference on Computer Vision, pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"30_CR17","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H.: FCOS: fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Devaguptapu, C., Akolekar, N., Sharma, M.: Borrow from anywhere: pseudo multi-modal object detection in thermal imagery. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 1029\u20131038 (2019)","DOI":"10.1109\/CVPRW.2019.00135"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Yang, L., Ma, R., Zakhor, A.: Drone object detection using RGB\/IR fusion. arXiv preprint arXiv:2201.03786 (2022)","DOI":"10.2352\/EI.2022.34.14.COIMG-179"},{"issue":"9","key":"30_CR21","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.3390\/rs14092020","volume":"14","author":"Q Wang","year":"2022","unstructured":"Wang, Q., Chi, Y., Shen, T., Song, J.: Improving RGB-infrared object detection by reducing cross-modality redundancy. Remote Sens. 14(9), 2020\u20132035 (2022)","journal-title":"Remote Sens."},{"issue":"22","key":"30_CR22","doi-asserted-by":"publisher","first-page":"23241","DOI":"10.1109\/JIOT.2022.3188270","volume":"9","author":"X Geng","year":"2022","unstructured":"Geng, X., Li, M., Liu, W., Zhu, S.: Person tracking by detection using dual visible-infrared cameras. IEEE Internet Things J. 9(22), 23241\u201323251 (2022)","journal-title":"IEEE Internet Things J."},{"key":"30_CR23","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.: 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_CR24","doi-asserted-by":"crossref","unstructured":"Fang, Q., Han, D., Wang, Z.: Cross-modality fusion transformer for multispectral object detection. arXiv preprint arXiv:2111.00273 (2021)","DOI":"10.2139\/ssrn.4227745"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, W., Ji, G.P., Wang, Z., Fu, K.: Depth quality-inspired feature manipulation for efficient RGB-D salient object detection. In: The 29th ACM International Conference on Multimedia, Chengdu, China, pp. 731\u2013740 (2021)","DOI":"10.1145\/3474085.3475240"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N.: Multispectral pedestrian detection: benchmark dataset and baseline. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"30_CR27","unstructured":"Li, C., Song, D., Tong, R.: Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv preprint arXiv:1808.04818 (2018)"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Li, C., Zhao, N., Lu, Y.: Weighted sparse representation regularized graph learning for RGB-T object tracking. In: 2017 Proceedings of the 25th ACM International Conference on Multimedia, pp. 1856\u20131864 (2017)","DOI":"10.1145\/3123266.3123289"},{"key":"30_CR29","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"issue":"10","key":"30_CR30","doi-asserted-by":"publisher","first-page":"6700","DOI":"10.1109\/TCSVT.2022.3168279","volume":"32","author":"Y Sun","year":"2019","unstructured":"Sun, Y., Cao, B., Zhu, P., Hu, Q.: Drone-based RGB-infrared cross-modality vehicle detection via uncertainty-aware learning. IEEE Trans. Circuits Syst. Video Technol. 32(10), 6700\u20136713 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Q., Chi, Y., Shen, T., Song, J.: Improving RGB-infrared object detection by reducing cross-modality redundancy. Remote Sens. 14(9) (2020)","DOI":"10.3390\/rs14092020"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47634-1_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:05:29Z","timestamp":1699128329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47634-1_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031476334","9783031476341"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47634-1_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ericlab.org\/acpr2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","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":"93","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":"57% - 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":"2","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":"5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}