{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:45:35Z","timestamp":1783147535745,"version":"3.54.6"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784460","type":"print"},{"value":"9783031784477","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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\/978-3-031-78447-7_19","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:24:31Z","timestamp":1733185471000},"page":"284-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["RGB-T Object Detection via\u00a0Group Shuffled Multi-receptive Attention and\u00a0Multi-modal Supervision"],"prefix":"10.1007","author":[{"given":"Jinzhong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuetao","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haorui","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"issue":"11","key":"19_CR1","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.3390\/s16111947","volume":"16","author":"T Alldieck","year":"2016","unstructured":"Alldieck, T., Bahnsen, C.H., Moeslund, T.B.: Context-aware fusion of RGB and thermal imagery for traffic monitoring. Sensors 16(11), 1947 (2016)","journal-title":"Sensors"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Yin, X., Liu, X.: Illuminating pedestrians via simultaneous detection & segmentation. In: ICCV, pp. 4950\u20134959 (2017)","DOI":"10.1109\/ICCV.2017.530"},{"key":"19_CR3","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: CVPR, pp. 403\u2013411 (2023)","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"issue":"9","key":"19_CR5","first-page":"15940","volume":"23","author":"K Dasgupta","year":"2022","unstructured":"Dasgupta, K., Das, A., Das, S., Bhattacharya, U., Yogamani, S.: Spatio-contextual deep network-based multimodal pedestrian detection for autonomous driving. TITS 23(9), 15940\u201315950 (2022)","journal-title":"TITS"},{"key":"19_CR6","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: CVPR, pp. 2849\u20132858 (2019)","DOI":"10.1109\/CVPR.2019.00296"},{"key":"19_CR7","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":"19_CR8","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., So\u00a0Kweon, I.: Multispectral pedestrian detection: benchmark dataset and baseline. In: CVPR, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"19_CR9","unstructured":"Jocher, G.: YOLOv5 release v6.1 (2020). https:\/\/github.com\/ultralytics\/yolov5\/releases\/tag\/v6.1"},{"issue":"3","key":"19_CR10","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":"19_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":"19_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":"19_CR13","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. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3160589"},{"key":"19_CR14","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TMM.2023.3272471","volume":"26","author":"R Li","year":"2024","unstructured":"Li, R., Xiang, J., Sun, F., Yuan, Y., Yuan, L., Gou, S.: Multiscale cross-modal homogeneity enhancement and confidence-aware fusion for multispectral pedestrian detection. IEEE Trans. Multimed. 26, 852\u2013863 (2024)","journal-title":"IEEE Trans. Multimed."},{"key":"19_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":"19_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: CVPR, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"19_CR17","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":"19_CR18","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":"10","key":"19_CR19","doi-asserted-by":"publisher","first-page":"6700","DOI":"10.1109\/TCSVT.2022.3168279","volume":"32","author":"Y Sun","year":"2022","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 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"19_CR20","doi-asserted-by":"publisher","first-page":"6449","DOI":"10.1109\/TMM.2024.3350926","volume":"26","author":"C Tian","year":"2024","unstructured":"Tian, C., Zhou, Z., Huang, Y., Li, G., He, Z.: Cross-modality proposal-guided feature mining for unregistered RGB-thermal pedestrian detection. IEEE Trans. Multimed. 26, 6449\u20136461 (2024)","journal-title":"IEEE Trans. Multimed."},{"key":"19_CR21","first-page":"1","volume":"61","author":"D Wang","year":"2022","unstructured":"Wang, D., et al.: Advancing plain vision transformer toward remote sensing foundation model. TGARS 61, 1\u201315 (2022)","journal-title":"TGARS"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: ECCV, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"1","key":"19_CR23","first-page":"537","volume":"23","author":"Y Xiao","year":"2020","unstructured":"Xiao, Y., Codevilla, F., Gurram, A., Urfalioglu, O., L\u00f3pez, A.M.: Multimodal end-to-end autonomous driving. TITS 23(1), 537\u2013547 (2020)","journal-title":"TITS"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: Learning a dynamic cross-modal network for multispectral pedestrian detection. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4043\u20134052 (2022)","DOI":"10.1145\/3503161.3547895"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: ICCV, pp. 3520\u20133529 (2021)","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"19_CR26","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: ICRA, pp. 2920\u20132926. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811999"},{"key":"19_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-030-58598-3_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Yang","year":"2020","unstructured":"Yang, X., Yan, J.: Arbitrary-oriented object detection with circular smooth label. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 677\u2013694. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_40"},{"key":"19_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/978-3-031-20077-9_30","volume-title":"ECCV 2022","author":"M Yuan","year":"2022","unstructured":"Yuan, M., Wang, Y., Wei, X.: Translation, scale and rotation: cross-modal alignment meets RGB-infrared vehicle detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 509\u2013525. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_30"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Yuan, M., Wei, X.: $$\\text{C}^2$$former: calibrated and complementary transformer for RGB-infrared object detection. TGARS (2024)","DOI":"10.1109\/TGRS.2024.3376819"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zu, K., Lu, J., Zou, Y., Meng, D.: EPSANet: an efficient pyramid squeeze attention block on convolutional neural network. In: Proceedings of the Asian Conference on Computer Vision, pp. 1161\u20131177 (2022)","DOI":"10.1007\/978-3-031-26313-2_33"},{"key":"19_CR31","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":"19_CR32","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: ICCV, pp. 5127\u20135137 (2019)","DOI":"10.1109\/ICCV.2019.00523"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, N., Liu, Y., Liu, H., Tian, T., Ma, J., Tian, J.: DTNet: a specialized dual-tuning network for infrared vehicle detection in aerial images. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3386309"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, N., Liu, Y., Liu, H., Tian, T., Tian, J.: Oriented infrared vehicle detection in aerial images via mining frequency and semantic information. TGARS (2023)","DOI":"10.1109\/TGRS.2023.3273818"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: CVPR, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"19_CR36","unstructured":"Zhang, X., Li, Y., Qi, Z., Sun, Y., Zhang, Y.: Learning multi-domain feature relation for visible and long-wave infrared image patch matching (2023)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Blasch, E., Liu, Z.: Multispectral Image Fusion and Colorization, vol. 481. SPIE Press Bellingham, Washington (2018)","DOI":"10.1117\/3.2316455"},{"key":"19_CR38","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78447-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T01:07:05Z","timestamp":1733188025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78447-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784460","9783031784477"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78447-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","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":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}