{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:48:17Z","timestamp":1742914097422,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533044"},{"type":"electronic","value":"9783031533051"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53305-1_34","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"448-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Detail-Guided Multi-source Fusion Network for\u00a0Remote Sensing Object Detection"],"prefix":"10.1007","author":[{"given":"Xiaoting","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shouhong","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hantao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiquan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Cai, R., Li, Z., Zhao, X., Huang, K.: Locality-sensitive deconvolution networks with gated fusion for RGB-D indoor semantic segmentation. In: IEEE Conference on Computer Vision & Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.161"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Chu, S.Y., Lee, M.S.: MT-DETR: robust end-to-end multimodal detection with confidence fusion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5252\u20135261 (2023)","DOI":"10.1109\/WACV56688.2023.00522"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Chudasama, V., Kar, P., Gudmalwar, A., Shah, N., Wasnik, P., Onoe, N.: M2FNet: multi-modal fusion network for emotion recognition in conversation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4652\u20134661 (2022)","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Frigo, O., Martin-Gaffe, L., Wacongne, C.: DooDLeNet: Double deepLab enhanced feature fusion for thermal-color semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3021\u20133029 (2022)","DOI":"10.1109\/CVPRW56347.2022.00341"},{"key":"34_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-020-3077-5","volume":"64","author":"S Fu","year":"2021","unstructured":"Fu, S., Xu, F., Jin, Y.Q.: Reciprocal translation between SAR and optical remote sensing images with cascaded-residual adversarial networks. Sci. China Inf. Sci. 64, 1\u201315 (2021)","journal-title":"Sci. China Inf. Sci."},{"key":"34_CR6","unstructured":"Huang, M., et al.: The QXS-SAROPT dataset for deep learning in SAR-optical data fusion (2021)"},{"key":"34_CR7","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., Wu, X.J.: DenseFuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28, 2614\u20132623 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"99","key":"34_CR8","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.1109\/TIP.2020.2966075","volume":"29","author":"H Jung","year":"2020","unstructured":"Jung, H., Kim, Y., Jang, H., Ha, N., Sohn, K.: Unsupervised deep image fusion with structure tensor representations. IEEE Trans. Image Process. 29(99), 3845\u20133858 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"34_CR9","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.inffus.2020.01.003","volume":"59","author":"SC Kulkarni","year":"2020","unstructured":"Kulkarni, S.C., Rege, P.P.: Pixel level fusion techniques for SAR and optical images: a review. Inf. Fusion 59, 13\u201329 (2020)","journal-title":"Inf. Fusion"},{"key":"34_CR10","unstructured":"Li, C., et al.: Yolov6 v3. 0: A full-scale reloading. arXiv preprint arXiv:2301.05586 (2023)"},{"key":"34_CR11","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":"34_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: DeepFusion: lidar-camera deep fusion for multi-modal 3D object detection (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"34_CR13","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":"7","key":"34_CR14","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. Automatica Sinica 9(7), 1200\u20131217 (2022)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Schmitt, M., Hughes, L.H., Qiu, C., Zhu, X.X.: SEN12MS - a curated dataset of georeferenced multi-spectral sentinel-1\/2 imagery for deep learning and data fusion (2019)","DOI":"10.5194\/isprs-annals-IV-2-W7-153-2019"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Schmitt, M., Hughes, L.H., Zhu, X.X.: The sen1-2 dataset for deep learning in SAR-optical data fusion (2018)","DOI":"10.5194\/isprs-annals-IV-1-141-2018"},{"key":"34_CR17","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":"34_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv (2017)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, X., Cao, L., Huang, W., Sun, F., Wang, Y.: Multimodal token fusion for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12186\u201312195 (2022)","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhu, X.X., Zeisl, B., Pollefeys, M.: Fusing meter-resolution 4-D InSAR point clouds and optical images for semantic urban infrastructure monitoring. IEEE Trans. Geosci. Remote Sens. 1\u201313 (2017)","DOI":"10.1109\/TGRS.2016.2554563"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: 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"},{"issue":"3","key":"34_CR22","doi-asserted-by":"publisher","first-page":"660","DOI":"10.3390\/rs15030660","volume":"15","author":"J Wu","year":"2023","unstructured":"Wu, J., Shen, T., Wang, Q., Tao, Z., Zeng, K., Song, J.: Local adaptive illumination-driven input-level fusion for infrared and visible object detection. Remote Sens. 15(3), 660 (2023)","journal-title":"Remote Sens."},{"key":"34_CR23","doi-asserted-by":"publisher","first-page":"2573","DOI":"10.1109\/JSTARS.2023.3250461","volume":"16","author":"W Wu","year":"2023","unstructured":"Wu, W., Guo, S., Shao, Z., Li, D.: CroFuseNet: a semantic segmentation network for urban impervious surface extraction based on cross fusion of optical and SAR images. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 16, 2573\u20132588 (2023)","journal-title":"IEEE J. Sel. Top. Appl. Earth Observations Remote Sens."},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhang, H., Zhang, L., Fan, Z.: Cloud removal of optical remote sensing imagery with multitemporal SAR-optical data using X-Mtgan. In: IGARSS 2019\u20132019 IEEE International Geoscience and Remote Sensing Symposium, pp. 3396\u20133399. IEEE (2019)","DOI":"10.1109\/IGARSS.2019.8899105"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Yang, M., Li, C., Liu, L., Tang, J.: Attribute-based progressive fusion network for RGBT tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2831\u20132838 (2022)","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"34_CR26","first-page":"1","volume":"70","author":"H Xu","year":"2021","unstructured":"Xu, H., Wang, X., Ma, J.: DRF: disentangled representation for visible and infrared image fusion. IEEE Trans. Instrum. Meas. 70, 1\u201313 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Yao, Y., Mihalcea, R.: Modality-specific learning rates for effective multimodal additive late-fusion. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 1824\u20131834 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.143"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, H., Ma, J.: SDNet: a versatile squeeze-and-decomposition network for real-time image fusion. Int. J. Comput. Vis. 129, 2761\u20132785 (2021)","DOI":"10.1007\/s11263-021-01501-8"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., Pang, Y., Lu, H., Zhang, L.: A single stream network for robust and real-time RGB-D salient object detection (2020)","DOI":"10.1007\/978-3-030-58542-6_39"},{"key":"34_CR30","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)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53305-1_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:04:48Z","timestamp":1710331488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53305-1_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533044","9783031533051"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53305-1_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","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":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}