{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T07:07:36Z","timestamp":1773212856154,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031189067","type":"print"},{"value":"9783031189074","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\/978-3-031-18907-4_30","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"382-393","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Attention-Guided Multi-modal and\u00a0Multi-scale Fusion for\u00a0Multispectral Pedestrian Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2578-1574","authenticated-orcid":false,"given":"Wei","family":"Bao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueshuang","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Kim, J.U., Park, S., Ro, Y.M.: Towards versatile pedestrian detector with multisensory-matching and multispectral recalling memory. In: 36th AAAI Conference on Artificial Intelligence (AAAI 2022). Association for the Advancement of Artificial Intelligence (2022)","DOI":"10.1609\/aaai.v36i1.20001"},{"key":"30_CR2","first-page":"509","volume":"587","author":"J Wagner","year":"2016","unstructured":"Wagner, J., Fischer, V., Herman, M., Behnke, S., et al.: Multispectral pedestrian detection using deep fusion convolutional neural networks. ESANN 587, 509\u2013514 (2016)","journal-title":"ESANN"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., Avignon, B.: Multispectral fusion for object detection with cyclic fuse-and-refine blocks. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 276\u2013280. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., Avignon, B.: Guided attentive feature fusion for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 72\u201380 (2021)","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"30_CR5","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_CR6","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"},{"issue":"9","key":"30_CR7","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., Zhang, Z., Zhu, Y.: Improving RGB-infrared object detection by reducing cross-modality redundancy. Remote Sens. 14(9), 2020 (2022)","journal-title":"Remote Sens."},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Li, Q., Zhang, C., Hu, Q., Fu, H., Zhu, P.: Confidence-aware fusion using dempster-shafer theory for multispectral pedestrian detection. IEEE Trans. Multimedia (2022)","DOI":"10.1109\/TMM.2022.3160589"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Sun, Y., Cao, B., Zhu, P., Hu, Q.: Drone-based RGB-infrared cross-modality vehicle detection via uncertainty-aware learning. IEEE Trans. Circ. Syst. Video Technol. (2022)","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Mohamed, A., Kingsbury, B., Ramabhadran, B.: Deep convolutional neural networks for LVCSR. In: IEEE International Conference on Acoustics, Speech and Signal Processing 2013, pp. 8614\u20138618. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhu, C., Li, M., Tang, W., Zhou, W.: LLVIP: a visible-infrared paired dataset for low-light vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3496\u20133504 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"30_CR13","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Proceedings of NIPS, pp. 91\u201399 (2015)"},{"key":"30_CR14","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"30_CR15","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_CR16","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.-Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"30_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"30_CR19","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, .: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"30_CR20","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_CR21","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_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"30_CR23","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection. arXiv preprint arXiv:1911.09516 (2019)"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.N.: 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":"30_CR25","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":"30_CR26","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_CR27","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. In: Proceedings of IJCV, vol. 115, no. 3, pp. 211\u2013252 (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"30_CR28","doi-asserted-by":"publisher","first-page":"8941","DOI":"10.1109\/JSTARS.2021.3109002","volume":"14","author":"W Bao","year":"2021","unstructured":"Bao, W., Huang, M., Zhang, Y., Yao, X., Liu, X., Xiang, X.: Boosting ship detection in SAR images with complementary pretraining techniques. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 14, 8941\u20138954 (2021)","journal-title":"IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens."}],"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\/978-3-031-18907-4_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:09:14Z","timestamp":1666825754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_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":"27 October 2022","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":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}