{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:20:44Z","timestamp":1767982844785,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023-ZM01X018"],"award-info":[{"award-number":["2023-ZM01X018"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680738","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"9350-9359","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Perceiving Local Details via Adaptive Spatial-Frequency Information Integration for Multi-focus Image Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5527-4231","authenticated-orcid":false,"given":"Jingjia","family":"Huang","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8469-2068","authenticated-orcid":false,"given":"Jingyan","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1520-7533","authenticated-orcid":false,"given":"Ge","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3748-1191","authenticated-orcid":false,"given":"Yingying","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8974-8905","authenticated-orcid":false,"given":"Yuhang","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7190-2429","authenticated-orcid":false,"given":"Xiaotong","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2288-5287","authenticated-orcid":false,"given":"Xinghao","family":"Ding","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3913-9400","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1080\/09500340.2012.714802"},{"key":"e_1_3_2_1_2_1","first-page":"233","article-title":"Multi-focus image fusion in DCT domain using variance and energy of Laplacian and correlation coefficient for visual sensor networks","volume":"6","author":"Amin-Naji M","year":"2018","unstructured":"M Amin-Naji and A Aghagolzadeh. 2018. Multi-focus image fusion in DCT domain using variance and energy of Laplacian and correlation coefficient for visual sensor networks. Journal of AI and Data Mining, Vol. 6, 2 (2018), 233--250.","journal-title":"Journal of AI and Data Mining"},{"key":"e_1_3_2_1_3_1","volume-title":"A pixel based multi-focus image fusion method. Optics communications","author":"Aslantas Veysel","year":"2014","unstructured":"Veysel Aslantas and Ahmet Nusret Toprak. 2014. A pixel based multi-focus image fusion method. Optics communications, Vol. 332 (2014), 350--358."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.05.003"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01131-z"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.966501"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.010"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11122379"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2012.01.007"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.08.024"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1364\/ao.55.010352"},{"key":"e_1_3_2_1_13_1","unstructured":"Yuanshen Guan Ruikang Xu Mingde Yao Lizhi Wang and Zhiwei Xiong. [n. d.]. Mutual-Guided Dynamic Network for Image Fusion. ( [n. d.])."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.08.002"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.014"},{"key":"e_1_3_2_1_16_1","volume-title":"DP-INNet: Dual-Path Implicit Neural Network for Spatial and Spectral Features Fusion in Pan-Sharpening. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 268--279","author":"Huang Jingjia","year":"2023","unstructured":"Jingjia Huang, Ge Meng, Yingying Wang, Yunlong Lin, Yue Huang, and Xinghao Ding. 2023. DP-INNet: Dual-Path Implicit Neural Network for Spatial and Spectral Features Fusion in Pan-Sharpening. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 268--279."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISR.2018.8535690"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0191085"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optcom.2014.12.048"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612135"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202692"},{"key":"e_1_3_2_1_22_1","volume-title":"Gesenet: A general semantic-guided network with couple mask ensemble for medical image fusion","author":"Li Jiawei","year":"2023","unstructured":"Jiawei Li, Jinyuan Liu, Shihua Zhou, Qiang Zhang, and Nikola K Kasabov. 2023. Gesenet: A general semantic-guided network with couple mask ensemble for medical image fusion. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1228544.1228553"},{"key":"e_1_3_2_1_24_1","unstructured":"Mining Li Ronghao Pei Tianyou Zheng Yang Zhang and Weiwei Fu. [n. d.]. FusionDiff: Multi-focus image fusion using denoising diffusion probabilistic models. ( [n. d.])."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2020.3046189"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.07.001"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611894"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2016.12.001"},{"key":"e_1_3_2_1_29_1","volume-title":"A general framework for image fusion based on multi-scale transform and sparse representation. Information fusion","author":"Liu Yu","year":"2015","unstructured":"Yu Liu, Shuping Liu, and Zengfu Wang. 2015. A general framework for image fusion based on multi-scale transform and sparse representation. Information fusion, Vol. 24 (2015), 147--164."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.05.004"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05358-9"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28214"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.10.004"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126616501231"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPHOT.2021.3073022"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.12.004"},{"key":"e_1_3_2_1_39_1","volume-title":"Retentive network: A successor to transformer for large language models. arXiv preprint arXiv:2307.08621","author":"Sun Yutao","year":"2023","unstructured":"Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqing Xia, Jilong Xue, Jianyong Wang, and Furu Wei. 2023. Retentive network: A successor to transformer for large language models. arXiv preprint arXiv:2307.08621 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2022.108590"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.4304\/jcp.6.12.2559-2566"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611937"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971137"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6936"},{"key":"e_1_3_2_1_48_1","volume-title":"2020 d. MFFW: A new dataset for multi-focus image fusion","author":"Xu Shuang","year":"2020","unstructured":"Shuang Xu, Xiaoli Wei, Chunxia Zhang, Junmin Liu, and Jiangshe Zhang. 2020 d. MFFW: A new dataset for multi-focus image fusion. Cornell University - arXiv,Cornell University - arXiv (Feb 2020)."},{"key":"e_1_3_2_1_49_1","volume-title":"Multi-focus image fusion using an effective discrete wavelet transform based algorithm. Measurement science review","author":"Yang Yong","year":"2014","unstructured":"Yong Yang, Shuying Huang, Junfeng Gao, and Zhongsheng Qian. 2014. Multi-focus image fusion using an effective discrete wavelet transform based algorithm. Measurement science review, Vol. 14, 2 (2014), 102--108."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2822688"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4216204"},{"key":"e_1_3_2_1_52_1","unstructured":"Hao Zhai Wenyi Zheng Yuncan Ouyang Xin Pan and Wanli Zhang. [n. d.]. Multi-focus image fusion via interactive transformer and asymmetric soft sharing. ( [n. d.])."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.022"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01501-8"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.06.003"},{"key":"e_1_3_2_1_56_1","first-page":"4819","article-title":"Deep learning-based multi-focus image fusion: A survey and a comparative study","volume":"44","author":"Zhang Xingchen","year":"2021","unstructured":"Xingchen Zhang. 2021. Deep learning-based multi-focus image fusion: A survey and a comparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4819--4838.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_57_1","volume-title":"Boundary finding based multi-focus image fusion through multi-scale morphological focus-measure. Information fusion","author":"Zhang Yu","year":"2017","unstructured":"Yu Zhang, Xiangzhi Bai, and Tao Wang. 2017. Boundary finding based multi-focus image fusion through multi-scale morphological focus-measure. Information fusion, Vol. 35 (2017), 81--101."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2013.11.005"},{"key":"e_1_3_2_1_59_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.022"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680738","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:24Z","timestamp":1750291584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":60,"alternative-id":["10.1145\/3664647.3680738","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680738","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}