{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:09:12Z","timestamp":1789124952357,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372802","type":"print"},{"value":"9783032372819","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37281-9_33","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:44:28Z","timestamp":1789123468000},"page":"541-559","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7029-5065","authenticated-orcid":false,"given":"Chao","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2687-7762","authenticated-orcid":false,"given":"Zikun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0426-3826","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8153-2636","authenticated-orcid":false,"given":"Guoqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2546-8721","authenticated-orcid":false,"given":"Zhenyu","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"33_CR1","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":"33_CR2","doi-asserted-by":"publisher","first-page":"110423","DOI":"10.1016\/j.knosys.2023.110423","volume":"268","author":"K Chen","year":"2023","unstructured":"Chen, K., Liu, J., Zhang, H.: IGT: illumination-guided RGB-T object detection with transformers. Knowl.-Based Syst. 268, 110423 (2023). https:\/\/doi.org\/10.1016\/j.knosys.2023.110423","journal-title":"Knowl.-Based Syst."},{"key":"33_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Y.T., Shi, J., Ye, Z., Mertz, C., Ramanan, D., Kong, S.: Multimodal object detection via probabilistic ensembling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 139\u2013158. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_9","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Deevi, S.A., Lee, C., Gan, L., Nagesh, S., Pandey, G., Chung, S.J.: RGB-X object detection via scene-specific fusion modules. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7366\u20137375 (2024)","DOI":"10.1109\/WACV57701.2024.00720"},{"key":"33_CR5","doi-asserted-by":"publisher","unstructured":"Dong, W., et al.: Fusion-mamba for cross-modality object detection. IEEE Trans. Multimedia 1\u201315 (2025). https:\/\/doi.org\/10.1109\/TMM.2025.3599020","DOI":"10.1109\/TMM.2025.3599020"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: TOOD: task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"33_CR7","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"33_CR8","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. In: First Conference on Language Modeling (2024)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"33_CR10","doi-asserted-by":"publisher","unstructured":"He, X., Tang, C., Zou, X., Zhang, W.: Multispectral object detection via cross-modal conflict-aware learning. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1465\u20131474. ACM, Ottawa ON Canada (2023). https:\/\/doi.org\/10.1145\/3581783.3612651","DOI":"10.1145\/3581783.3612651"},{"key":"33_CR11","doi-asserted-by":"publisher","unstructured":"Hu, K., He, Y., Li, Y., Zhao, J., Chen, S., Kang, Y.: $$\\text{Ei}^{2}\\text{ det }$$: edge-guided illumination-aware interactive learning for visible-infrared object detection. IEEE Trans. Circuits Syst. Video Technol. 35(7), 7101\u20137115 (2025). https:\/\/doi.org\/10.1109\/TCSVT.2025.3539625","DOI":"10.1109\/TCSVT.2025.3539625"},{"key":"33_CR12","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":"33_CR13","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":"3","key":"33_CR14","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TCSVT.2021.3076466","volume":"32","author":"JU Kim","year":"2022","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 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3076466","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"33_CR15","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.patrec.2024.02.012","volume":"179","author":"S Lee","year":"2024","unstructured":"Lee, S., Park, J., Park, J.: CrossFormer: cross-guided attention for multi-modal object detection. Pattern Recogn. Lett. 179, 144\u2013150 (2024)","journal-title":"Pattern Recogn. Lett."},{"key":"33_CR16","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":"33_CR17","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":"33_CR18","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21002\u201321012 (2020)"},{"key":"33_CR19","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":"33_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: 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":"33_CR21","unstructured":"Qingyun, F., Dapeng, H., Zhaokui, W.: Cross-modality fusion transformer for multispectral object detection. arXiv preprint arXiv:2111.00273 (2021)"},{"key":"33_CR22","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":"33_CR23","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"33_CR24","doi-asserted-by":"publisher","first-page":"109913","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":"33_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2025.05.005","volume":"196","author":"C Tian","year":"2025","unstructured":"Tian, C., Yang, C., Zhu, G., Wang, Q., He, Z.: Learning a robust RGB-thermal detector for extreme modality imbalance. Pattern Recogn. Lett. 196, 1\u20138 (2025). https:\/\/doi.org\/10.1016\/j.patrec.2025.05.005","journal-title":"Pattern Recogn. Lett."},{"key":"33_CR26","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. Multimedia 26, 6449\u20136461 (2024)","journal-title":"IEEE Trans. Multimedia"},{"key":"33_CR27","unstructured":"Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"33_CR28","unstructured":"Wagner, J., Fischer, V., Herman, M., Behnke, S.: Multispectral pedestrian detection using deep fusion convolutional neural networks. Comput. Intell. (2016)"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Wang, A., et al.: Yolov10: real-time end-to-end object detection. In: Advances in Neural Information Processing Systems, vol. 37, pp. 107984\u2013108011 (2024)","DOI":"10.52202\/079017-3429"},{"key":"33_CR30","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":"33_CR31","unstructured":"Xu, S., et al.: PP-YOLOE: an evolved version of YOLO. arXiv preprint arXiv:2203.16250 (2022)"},{"issue":"1","key":"33_CR32","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1109\/TCSVT.2024.3454631","volume":"35","author":"F Yang","year":"2025","unstructured":"Yang, F., Liang, B., Li, W., Zhang, J.: Multidimensional fusion network for multispectral object detection. IEEE Trans. Circuits Syst. Video Technol. 35(1), 547\u2013560 (2025). https:\/\/doi.org\/10.1109\/TCSVT.2024.3454631","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"33_CR33","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":"33_CR34","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":"33_CR35","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":"33_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\/CVF International Conference on Computer Vision, pp. 5127\u20135137 (2019)","DOI":"10.1109\/ICCV.2019.00523"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"33_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, X., et al.: Rethinking early-fusion strategies for improved multispectral object detection. IEEE Trans. Intell. Veh. 1\u201315 (2024). https:\/\/doi.org\/10.1109\/TIV.2024.3462488","DOI":"10.1109\/TIV.2024.3462488"},{"key":"33_CR39","doi-asserted-by":"publisher","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16965\u201316974. IEEE, Seattle, WA, USA (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605, https:\/\/ieeexplore.ieee.org\/document\/10657220\/","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"33_CR40","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":"33_CR41","doi-asserted-by":"publisher","unstructured":"Zhou, M., et al.: COFNet: contrastive object-aware fusion using box-level masks for multispectral object detection. IEEE Trans. Multimedia 1\u201315 (2025). https:\/\/doi.org\/10.1109\/TMM.2025.3599097","DOI":"10.1109\/TMM.2025.3599097"},{"key":"33_CR42","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37281-9_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:44:36Z","timestamp":1789123476000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37281-9_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372802","9783032372819"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37281-9_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}