{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T07:24:44Z","timestamp":1778570684183,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"name":"China NSF","award":["62427801"],"award-info":[{"award-number":["62427801"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3728482.3757382","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T21:21:35Z","timestamp":1762204895000},"page":"47-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Perception for Indoor Fire Rescue UAVs: A Unified Multimodal Semantic Fusion Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1085-5941","authenticated-orcid":false,"given":"Weitao","family":"Han","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1359-7079","authenticated-orcid":false,"given":"Hairen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3603-3886","authenticated-orcid":false,"given":"Guangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 2017 20th International Conference on Information Fusion. 1-9.","author":"Bavirisetti D. P.","unstructured":"D. P. Bavirisetti, G. Xiao, and G. Liu. 2017. Multi-sensor image fusion based on fourth order partial differential equations. In Proceedings of the 2017 20th International Conference on Information Fusion. 1-9."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.877507"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2696055"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.310"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096088"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2887342"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2244222"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01952-1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2618776"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.004"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977573"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.010"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3192661"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234340"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2018.2877285"},{"key":"e_1_3_2_1_16_1","volume-title":"Information Fusion","volume":"98","author":"Wang D.","year":"2023","unstructured":"D. Wang, J. Liu, R. Liu, and X. Fan. 2023a. An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Information Fusion, Vol. 98 (2023). Article no. 101828."},{"key":"e_1_3_2_1_17_1","volume-title":"The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective. In Proceedings of the 33rd ACM International Conference on Multimedia Workshop.","author":"Wang Tingyu","year":"2025","unstructured":"Tingyu Wang, Yujiao Shi, Fabian Deuser, Shaofei Huang, Guosheng Hu, Si Liu, Zhedong Zheng, and Roger Zimmermann. 2025. The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective. In Proceedings of the 33rd ACM International Conference on Multimedia Workshop."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239627"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3414610"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3322851"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3266980"},{"key":"e_1_3_2_1_22_1","volume-title":"Information Fusion","volume":"98","author":"H. Xie","year":"2023","unstructured":"H. Xie et al., 2023. Semantics lead all: Towards unified image registration and fusion from a semantic perspective. Information Fusion, Vol. 98 (2023). Article no. 101835."},{"key":"e_1_3_2_1_23_1","volume-title":"Computer Vision and Image Understanding","volume":"218","author":"Xu H.","year":"2022","unstructured":"H. Xu, J. Ma, J. Huang, and J. Ma. 2022a. CUFD: An encoder decoder network for visible and infrared image fusion based on common and unique feature decomposition. Computer Vision and Image Understanding, Vol. 218 (2022). Article no. 103407."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3108233"},{"key":"e_1_3_2_1_26_1","article-title":"Infrared and visible image fusion using visual saliency sparse representation and detail injection model","volume":"70","author":"Yang Y.","year":"2021","unstructured":"Y. Yang, Y. Zhang, S. Huang, Y. Zuo, and J. Sun. 2021. Infrared and visible image fusion using visual saliency sparse representation and detail injection model. IEEE Transactions on Instrumentation and Measurement, Vol. 70 (2021). Article no. 5001715.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.07.011"},{"key":"e_1_3_2_1_28_1","first-page":"970","article-title":"DIDFuse: Deep image decomposition for infrared and visible image fusion","author":"Zhao Z.","year":"2020","unstructured":"Z. Zhao, S. Xu, C. Zhang, J. Liu, P. Li, and J. Zhang. 2020. DIDFuse: Deep image decomposition for infrared and visible image fusion. In IJCAI. 970-976.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129609"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.09.010"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 3rd International Workshop on UAVs in Multimedia: Capturing the World from a New Perspective"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3728482.3757382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T21:21:40Z","timestamp":1762204900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728482.3757382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":30,"alternative-id":["10.1145\/3728482.3757382","10.1145\/3728482"],"URL":"https:\/\/doi.org\/10.1145\/3728482.3757382","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-11-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}