{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:59:48Z","timestamp":1775145588838,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"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_16","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:25:36Z","timestamp":1733185536000},"page":"236-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["DEYOLO: Dual-Feature-Enhancement YOLO for\u00a0Cross-Modality Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6853-5734","authenticated-orcid":false,"given":"Yishuo","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7626-1154","authenticated-orcid":false,"given":"Boran","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6472-1719","authenticated-orcid":false,"given":"Xinyu","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2416-9332","authenticated-orcid":false,"given":"Wenbin","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3224-1284","authenticated-orcid":false,"given":"Jiasheng","family":"He","sequence":"additional","affiliation":[]},{"given":"Xiaobin","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5495-684X","authenticated-orcid":false,"given":"Jing","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"16_CR1","unstructured":"FLIR: FLIR thermal dataset for algorithm training (2018). https:\/\/www.flir.in\/oem\/adas\/adas-dataset-form"},{"key":"16_CR2","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":"16_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"11","key":"16_CR5","doi-asserted-by":"publisher","first-page":"9813","DOI":"10.1109\/TGRS.2020.3044958","volume":"59","author":"Y Dai","year":"2021","unstructured":"Dai, Y., Wu, Y., Zhou, F., Barnard, K.: Attentional local contrast networks for infrared small target detection. IEEE Trans. Geosci. Remote Sens. 59(11), 9813\u20139824 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"16_CR6","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":"16_CR7","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":"16_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"16_CR9","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":"16_CR10","doi-asserted-by":"publisher","unstructured":"Jocher, G.: YOLOv5 by ultralytics (2020). https:\/\/doi.org\/10.5281\/zenodo.3908559. https:\/\/github.com\/ultralytics\/yolov5","DOI":"10.5281\/zenodo.3908559"},{"key":"16_CR11","unstructured":"Jocher, G.: ultralytics\/yolov8: v8.1.0 - YOLOv8 oriented bounding boxes (OBB) (2024). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Kieu, M., Bagdanov, A.D., Bertini, M., Del\u00a0Bimbo, A.: Task-conditioned domain adaptation for pedestrian detection in thermal imagery. In: European Conference on Computer Vision, pp. 546\u2013562. Springer (2020)","DOI":"10.1007\/978-3-030-58542-6_33"},{"key":"16_CR13","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":"16_CR14","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":"16_CR15","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"},{"issue":"1","key":"16_CR16","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/TCSVT.2021.3056725","volume":"32","author":"J Liu","year":"2021","unstructured":"Liu, J., Fan, X., Jiang, J., Liu, R., Luo, Z.: Learning a deep multi-scale feature ensemble and an edge-attention guidance for image fusion. IEEE Trans. Circuits Syst. Video Technol. 32(1), 105\u2013119 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"7","key":"16_CR18","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1109\/JAS.2022.105686","volume":"9","author":"J Ma","year":"2022","unstructured":"Ma, J., Tang, L., Fan, F., Huang, J., Mei, X., Ma, Y.: SwinFusion: cross-domain long-range learning for general image fusion via swin transformer. IEEE\/CAA J. Autom. Sin. 9(7), 1200\u20131217 (2022)","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"16_CR19","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 Recogn. 80, 143\u2013155 (2018)","journal-title":"Pattern Recogn."},{"key":"16_CR20","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":"16_CR21","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":"16_CR22","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Sun, Y., Cao, B., Zhu, P., Hu, Q.: DetFusion: a detection-driven infrared and visible image fusion network. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4003\u20134011 (2022)","DOI":"10.1145\/3503161.3547902"},{"key":"16_CR24","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","volume":"82","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Ma, J.: Image fusion in the loop of high-level vision tasks: a semantic-aware real-time infrared and visible image fusion network. Inf. Fusion 82, 28\u201342 (2022)","journal-title":"Inf. Fusion"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","volume":"83","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Zhang, H., Jiang, X., Ma, J.: PIAFusion: a progressive infrared and visible image fusion network based on illumination aware. Inf. Fusion 83, 79\u201392 (2022)","journal-title":"Inf. Fusion"},{"key":"16_CR26","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.dib.2017.09.038","volume":"15","author":"A Toet","year":"2017","unstructured":"Toet, A.: The TNO multiband image data collection. Data Brief 15, 249\u2013251 (2017)","journal-title":"Data Brief"},{"key":"16_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"16_CR28","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":"16_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101828","volume":"98","author":"D Wang","year":"2023","unstructured":"Wang, D., Liu, J., Liu, R., Fan, X.: An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Inf. Fusion 98, 101828 (2023)","journal-title":"Inf. Fusion"},{"key":"16_CR30","doi-asserted-by":"publisher","unstructured":"Hou, Q., Zhang, L., Tan, F., Xi, Y., Zheng, H., Li, N.: ISTDU-Net: infrared small-target detection U-Net. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022). Art no. 7506205. https:\/\/doi.org\/10.1109\/LGRS.2022.3141584","DOI":"10.1109\/LGRS.2022.3141584"},{"issue":"1","key":"16_CR31","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2020","unstructured":"Xu, H., Ma, J., Jiang, J., Guo, X., Ling, H.: U2Fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502\u2013518 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Xu, H., Ma, J., Le, Z., Jiang, J., Guo, X.: FusionDN: a unified densely connected network for image fusion. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6936"},{"key":"16_CR33","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"},{"issue":"5","key":"16_CR34","doi-asserted-by":"publisher","first-page":"4481","DOI":"10.1109\/TGRS.2020.3012981","volume":"59","author":"B Zhao","year":"2020","unstructured":"Zhao, B., Wang, C., Fu, Q., Han, Z.: A novel pattern for infrared small target detection with generative adversarial network. IEEE Trans. Geosci. Remote Sens. 59(5), 4481\u20134492 (2020)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: CDDFuse: correlation-driven dual-branch feature decomposition for multi-modality image fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5906\u20135916 (2023)","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"16_CR36","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. arXiv preprint arXiv:2103.07461 (2021)"}],"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_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T01:06:50Z","timestamp":1733188010000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78447-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784460","9783031784477"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78447-7_16","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"}}]}}