{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T07:54:56Z","timestamp":1774511696209,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733826","type":"print"},{"value":"9783031733833","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73383-3_27","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:02:43Z","timestamp":1730548963000},"page":"464-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with\u00a0Competitive Query Selection and\u00a0Adaptive Feature Fusion"],"prefix":"10.1007","author":[{"given":"Junjie","family":"Guo","sequence":"first","affiliation":[]},{"given":"Chenqiang","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Fangcen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"27_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":"27_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Bin, J., Hamari, J., Blasch, E., Liu, Z.: Multimodal object detection by channel switching and spatial attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 403\u2013411 (2023)","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"27_CR3","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I","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.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I, pp. 213\u2013229. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"27_CR4","unstructured":"FLIR: Flir thermal dataset for algorithm training. https:\/\/www.flir.in\/oem\/adas\/adas-dataset-form (2018)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: LRAF-Net: long-range attention fusion network for visible\u2013infrared object detection. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3266452"},{"key":"27_CR6","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":"27_CR7","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"},{"issue":"4","key":"27_CR8","doi-asserted-by":"publisher","first-page":"7846","DOI":"10.1109\/LRA.2021.3099870","volume":"6","author":"J Kim","year":"2021","unstructured":"Kim, J., Kim, H., Kim, T., Kim, N., Choi, Y.: MLPD: multi-label pedestrian detector in multispectral domain. IEEE Robot. Autom. Lett. 6(4), 7846\u20137853 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"27_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(3), 1510\u20131523 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR10","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":"27_CR11","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv preprint arXiv:1808.04818 (2018)"},{"key":"27_CR12","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 Recogn. 85, 161\u2013171 (2019)","journal-title":"Pattern Recogn."},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: Accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"27_CR14","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":"27_CR15","doi-asserted-by":"crossref","unstructured":"Li, Q., Zhang, C., Hu, Q., Zhu, P., Fu, H., Chen, L.: Stabilizing multispectral pedestrian detection with evidential hybrid fusion. IEEE Trans. Circ. Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3306870"},{"key":"27_CR16","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":"27_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., Luo, Z.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135811 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"27_CR18","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"27_CR19","unstructured":"Lv, W., et al.: DETRs beat YOLOs on real-time object detection. arXiv preprint arXiv:2304.08069 (2023)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"issue":"15","key":"27_CR21","doi-asserted-by":"publisher","first-page":"2501","DOI":"10.3390\/rs12152501","volume":"12","author":"MT Pham","year":"2020","unstructured":"Pham, M.T., Courtrai, L., Friguet, C., Lef\u00e8vre, S., Baussard, A.: YOLO-fine: one-stage detector of small objects under various backgrounds in remote sensing images. Remote Sens. 12(15), 2501 (2020)","journal-title":"Remote Sens."},{"key":"27_CR22","unstructured":"Qingyun, F., Dapeng, H., Zhaokui, W.: Cross-modality fusion transformer for multispectral object detection. arXiv preprint arXiv:2111.00273 (2021)"},{"key":"27_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786","volume":"130","author":"F Qingyun","year":"2022","unstructured":"Qingyun, F., Zhaokui, W.: Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery. Pattern Recogn. 130, 108786 (2022)","journal-title":"Pattern Recogn."},{"key":"27_CR24","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.jvcir.2015.11.002","volume":"34","author":"S Razakarivony","year":"2016","unstructured":"Razakarivony, S., Jurie, F.: Vehicle detection in aerial imagery: a small target detection benchmark. J. Vis. Commun. Image Represent. 34, 187\u2013203 (2016)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"27_CR27","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"27_CR28","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, vol. 28 (2015)"},{"issue":"3","key":"27_CR29","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.3390\/s22031082","volume":"22","author":"K Roszyk","year":"2022","unstructured":"Roszyk, K., Nowicki, M.R., Skrzypczy\u0144ski, P.: Adopting the YOLOv4 architecture for low-latency multispectral pedestrian detection in autonomous driving. Sensors 22(3), 1082 (2022)","journal-title":"Sensors"},{"key":"27_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913","volume":"145","author":"J Shen","year":"2024","unstructured":"Shen, J., Chen, Y., Liu, Y., Zuo, X., Fan, H., Yang, W.: ICAFusion: iterative cross-attention guided feature fusion for multispectral object detection. Pattern Recogn. 145, 109913 (2024)","journal-title":"Pattern Recogn."},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"27_CR32","unstructured":"Xing, Y., et al.: Multispectral pedestrian detection via reference box constrained cross attention and modality balanced optimization. arXiv preprint arXiv:2302.00290 (2023)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Yang, X., Qian, Y., Zhu, H., Wang, C., Yang, M.: BAANet: learning bi-directional adaptive attention gates for multispectral pedestrian detection. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2920\u20132926. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811999"},{"key":"27_CR34","unstructured":"Yao, Z., Ai, J., Li, B., Zhang, C.: Efficient DETR: improving end-to-end object detector with dense prior. arXiv preprint arXiv:2104.01318 (2021)"},{"key":"27_CR35","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: VarifocalNet: An IoU-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lefevre, 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":"27_CR38","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":"27_CR39","unstructured":"Zhang, L., et al.: Weakly aligned feature fusion for multimodal object detection. IEEE Trans. Neural Netw. Learn. Syst. (2021)"},{"key":"27_CR40","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":"27_CR41","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":"27_CR42","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Sun, X., Wang, M., Huang, H.: Multi-modal feature pyramid transformer for RGB-infrared object detection. IEEE Trans. Intell. Transp. Syst. (2023)","DOI":"10.1109\/TITS.2023.3266487"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73383-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:12:44Z","timestamp":1730549564000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73383-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733826","9783031733833"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73383-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}