{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:39Z","timestamp":1750309479312,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":46,"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":"the Key Laboratory of Cognitive Radio and Information Processing , Ministry of Education","award":["CRKL230204"],"award-info":[{"award-number":["CRKL230204"]}]},{"name":"the National Natural Science Foundation of China","award":["62302355"],"award-info":[{"award-number":["62302355"]}]},{"name":"the Fundamental Research Funds for the Central University","award":["XJSJ24071"],"award-info":[{"award-number":["XJSJ24071"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["XJSJ24072"],"award-info":[{"award-number":["XJSJ24072"]}]},{"name":"The project of Science and Technology Development Plan in HangZhou","award":["202202B38"],"award-info":[{"award-number":["202202B38"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681700","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"4358-4367","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable Matching of Optical-SAR Image via Dynamically Conditioned Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2619-6481","authenticated-orcid":false,"given":"Shuiping","family":"Gou","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5698-1120","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1224-4611","authenticated-orcid":false,"given":"Xinlin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7173-8581","authenticated-orcid":false,"given":"Yunzhi","family":"Chen","sequence":"additional","affiliation":[{"name":"Hangzhou Vocational and Technical College, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Protein structure and sequence generation with equivariant denoising diffusion probabilistic models. arXiv preprint arXiv:2205.15019","author":"Anand Namrata","year":"2022","unstructured":"Namrata Anand and Tudor Achim. 2022. Protein structure and sequence generation with equivariant denoising diffusion probabilistic models. arXiv preprint arXiv:2205.15019 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGE.1970.271435"},{"key":"e_1_3_2_1_3_1","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Daniel D Johnson, Jonathan Ho, Daniel Tarlow, and Rianne Van Den Berg. 2021. Structured denoising diffusion models in discrete state-spaces. Advances in Neural Information Processing Systems, Vol. 34 (2021), 17981--17993.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_2_1_5_1","volume-title":"Conditional Diffusion for SAR to Optical Image Translation","author":"Bai Xinyu","year":"2023","unstructured":"Xinyu Bai, Xinyang Pu, and Feng Xu. 2023. Conditional Diffusion for SAR to Optical Image Translation. IEEE Geoscience and Remote Sensing Letters (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"e_1_3_2_1_8_1","volume-title":"Generating long sequences with sparse transformers. arXiv","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. 2019. Generating long sequences with sparse transformers. arXiv 2019. arXiv preprint arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU48272.2019.8946408"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"SAR-optical image matching by integrating Siamese U-Net with FFT correlation","volume":"19","author":"Fang Yuyuan","year":"2021","unstructured":"Yuyuan Fang, Jun Hu, Chuan Du, Zhibo Liu, and Lei Zhang. 2021. SAR-optical image matching by integrating Siamese U-Net with FFT correlation. IEEE Geoscience and Remote Sensing Letters, Vol. 19 (2021), 1--5.","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3077-5"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0333-9"},{"key":"e_1_3_2_1_15_1","volume-title":"MARU-Net: Multi-Scale Attention Gated Residual U-Net With Contrastive Loss for SAR-Optical Image Matching","author":"Gazzea Michele","year":"2023","unstructured":"Michele Gazzea, Oscar Sommervold, and Reza Arghandeh. 2023. MARU-Net: Multi-Scale Attention Gated Residual U-Net With Contrastive Loss for SAR-Optical Image Matching. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 3279--3286","author":"Han Xufeng","year":"2015","unstructured":"Xufeng Han, Thomas Leung, Yangqing Jia, Rahul Sukthankar, and Alexander C Berg. 2015. Matchnet: Unifying feature and metric learning for patch-based matching. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3279--3286."},{"key":"e_1_3_2_1_17_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2799232"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2004.835294"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959244"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs9060586"},{"volume-title":"A CNN for the identification of corresponding patches in SAR and optical imagery of urban scenes. In 2017 Joint Urban Remote Sensing Event (JURSE)","author":"Mou Lichao","key":"e_1_3_2_1_25_1","unstructured":"Lichao Mou, Michael Schmitt, Yuanyuan Wang, and Xiao Xiang Zhu. 2017. A CNN for the identification of corresponding patches in SAR and optical imagery of urban scenes. In 2017 Joint Urban Remote Sensing Event (JURSE). IEEE, 1--4."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475644"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 8162--8171","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International conference on machine learning. PMLR, 8162--8171."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs14122946"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_30_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_31_1","volume-title":"The SEN1--2 dataset for deep learning in SAR-optical data fusion. arXiv","author":"Schmitt M","year":"2018","unstructured":"M Schmitt, LH Hughes, and XX Zhu. [n.,d.]. The SEN1--2 dataset for deep learning in SAR-optical data fusion. arXiv 2018. arXiv preprint arXiv:1807.01569 ( [n.,d.])."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1352841"},{"key":"e_1_3_2_1_33_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"Spacenet: A remote sensing dataset and challenge series. arXiv preprint arXiv:1807.01232","author":"Etten Adam Van","year":"2018","unstructured":"Adam Van Etten, Dave Lindenbaum, and Todd M Bacastow. 2018. Spacenet: A remote sensing dataset and challenge series. arXiv preprint arXiv:1807.01232 (2018)."},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2892432"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2014.2330593"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2011.2177437"},{"key":"e_1_3_2_1_39_1","volume-title":"Crossformer: A versatile vision transformer hinging on cross-scale attention","author":"Wang Wenxiao","year":"2023","unstructured":"Wenxiao Wang, Wei Chen, Qibo Qiu, Long Chen, Boxi Wu, Binbin Lin, Xiaofei He, and Wei Liu. 2023. Crossformer: A versatile vision transformer hinging on cross-scale attention. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3026162"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2924684"},{"key":"e_1_3_2_1_43_1","first-page":"9","article-title":"Hopc: A novel similarity metric based on geometric structural properties for multi-modal remote sensing image matching. ISPRS Annals of the Photogrammetry","volume":"3","author":"Ye Yuanxin","year":"2016","unstructured":"Yuanxin Ye and Li Shen. 2016. Hopc: A novel similarity metric based on geometric structural properties for multi-modal remote sensing image matching. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 3 (2016), 9--16.","journal-title":"Remote Sensing and Spatial Information Sciences"},{"key":"e_1_3_2_1_44_1","first-page":"1","article-title":"Explore better network framework for high-resolution optical and SAR image matching","volume":"60","author":"Zhang Han","year":"2021","unstructured":"Han Zhang, Lin Lei, Weiping Ni, Tao Tang, Junzheng Wu, Deliang Xiang, and Gangyao Kuang. 2021. Explore better network framework for high-resolution optical and SAR image matching. IEEE Transactions on Geoscience and Remote Sensing, Vol. 60 (2021), 1--18.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2017.08.013"},{"key":"e_1_3_2_1_46_1","unstructured":"Lei Zhu Xinjiang Wang Zhanghan Ke Wayne Zhang and Rynson Lau. [n.d.]. BiFormer: Vision Transformer with Bi-Level Routing Attention-Supplemental. ([n.d.])."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681700","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:28Z","timestamp":1750295848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681700","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681700","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"}}]}}