{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:29:45Z","timestamp":1770226185582,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030678319","type":"print"},{"value":"9783030678326","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-67832-6_32","type":"book-chapter","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T17:44:48Z","timestamp":1611337488000},"page":"391-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Robust Multispectral Pedestrian Detection via Uncertainty-Aware Cross-Modal Learning"],"prefix":"10.1007","author":[{"given":"Sungjune","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung Uk","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeon Gyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang-Keun","family":"Moon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"32_CR1","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.isprsjprs.2019.02.005","volume":"150","author":"Y Cao","year":"2019","unstructured":"Cao, Y., Guan, D., Wu, Y., Yang, J., Cao, Y., Yang, M.Y.: Box-level segmentation supervised deep neural networks for accurate and real-time multispectral pedestrian detection. ISPRS J. Photogramm. Remote Sens. 150, 70\u201379 (2019)","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Chang, J., Lan, Z., Cheng, C., Wei, Y.: Data uncertainty learning in face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5710\u20135719 (2020)","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"32_CR3","unstructured":"Choi, H., Kim, S., Park, K., Sohn, K.: Multi-spectral pedestrian detection based on accumulated object proposal with fully convolutional networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 621\u2013626. IEEE (2016)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 304\u2013311. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206631"},{"key":"32_CR5","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050\u20131059 (2016)"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"6","key":"32_CR8","doi-asserted-by":"publisher","first-page":"820","DOI":"10.3390\/s16060820","volume":"16","author":"A Gonz\u00e1lez","year":"2016","unstructured":"Gonz\u00e1lez, A., et al.: Pedestrian detection at day\/night time with visible and fir cameras: a comparison. Sensors 16(6), 820 (2016)","journal-title":"Sensors"},{"key":"32_CR9","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":"32_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345\u2013360. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23"},{"key":"32_CR11","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":"32_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Zhu, C., Wang, J., Savvides, M., Zhang, X.: Bounding box regression with uncertainty for accurate object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2888\u20132897 (2019)","DOI":"10.1109\/CVPR.2019.00300"},{"key":"32_CR13","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., So Kweon, I.: Multispectral pedestrian detection: benchmark dataset and baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"32_CR15","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574\u20135584 (2017)"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Kim, J.U., Kwon, J., Kim, H.G., Lee, H., Ro, Y.M.: Object bounding box-critic networks for occlusion-robust object detection in road scene. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1313\u20131317. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451034"},{"issue":"4","key":"32_CR17","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1109\/TCSVT.2019.2900709","volume":"30","author":"JU Kim","year":"2019","unstructured":"Kim, J.U., Kwon, J., Kim, H.G., Ro, Y.M.: BBC net: bounding-box critic network for occlusion-robust object detection. IEEE Trans. Circuits Syst. Video Technol. 30(4), 1037\u20131050 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Kim, J.U., Park, S., Ro, Y.M.: Towards human-like interpretable object detection via spatial relation encoding. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 3284\u20133288. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9190724"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Kim, J.U., Ro, Y.M.: Attentive layer separation for object classification and object localization in object detection. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 3995\u20133999. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803439"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Konig, D., Adam, M., Jarvers, C., Layher, G., Neumann, H., Teutsch, M.: Fully convolutional region proposal networks for multispectral person detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 49\u201356 (2017)","DOI":"10.1109\/CVPRW.2017.36"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Smola, A.J., Canu, S.: Heteroscedastic Gaussian process regression. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 489\u2013496 (2005)","DOI":"10.1145\/1102351.1102413"},{"key":"32_CR22","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv preprint arXiv:1808.04818 (2018)"},{"key":"32_CR23","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","volume":"85","author":"C Li","year":"2019","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Illumination-aware faster R-CNN for robust multispectral pedestrian detection. Pattern Recognit. 85, 161\u2013171 (2019)","journal-title":"Pattern Recognit."},{"key":"32_CR24","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":"32_CR25","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":"32_CR26","doi-asserted-by":"crossref","unstructured":"Nix, D.A., Weigend, A.S.: Estimating the mean and variance of the target probability distribution. In: Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN 1994), vol. 1, pp. 55\u201360. IEEE (1994)","DOI":"10.1109\/ICNN.1994.374138"},{"key":"32_CR27","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.patcog.2018.03.007","volume":"80","author":"K Park","year":"2018","unstructured":"Park, K., Kim, S., Sohn, K.: Unified multi-spectral pedestrian detection based on probabilistic fusion networks. Pattern Recognit. 80, 143\u2013155 (2018)","journal-title":"Pattern Recognit."},{"key":"32_CR28","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"32_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"32_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 808\u2013816 (2016)","DOI":"10.1109\/CVPR.2016.94"},{"issue":"2","key":"32_CR32","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.cviu.2011.10.006","volume":"116","author":"A Torabi","year":"2012","unstructured":"Torabi, A., Mass\u00e9, G., Bilodeau, G.A.: An iterative integrated framework for thermal-visible image registration, sensor fusion, and people tracking for video surveillance applications. Comput. Vis. Image Underst. 116(2), 210\u2013221 (2012)","journal-title":"Comput. Vis. Image Underst."},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1365\u20131374 (2019)","DOI":"10.1109\/ICCV.2019.00145"},{"issue":"2","key":"32_CR34","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1109\/TPAMI.2013.124","volume":"36","author":"X Wang","year":"2013","unstructured":"Wang, X., Wang, M., Li, W.: Scene-specific pedestrian detection for static video surveillance. IEEE Trans. Pattern Anal. Mach. Intell. 36(2), 361\u2013374 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR35","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":"32_CR36","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 International Conference on Computer Vision, pp. 5127\u20135137 (2019)","DOI":"10.1109\/ICCV.2019.00523"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67832-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T08:23:52Z","timestamp":1623659032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67832-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030678319","9783030678326"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67832-6_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 January 2021","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":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2021.cz\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","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":"73","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":"35% - 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":"2,63","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":"2,5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}