{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T10:16:44Z","timestamp":1779877004996,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"name":"National Key Projects of China under Grant","award":["2021XJTU0040"],"award-info":[{"award-number":["2021XJTU0040"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755562","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"1987-1996","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Frequency Meets Semantics: Text-Visual Fusion with Directional Spectral Enhancement for Salient Object Detection in Optical Remote Sensing Images"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8687-1657","authenticated-orcid":false,"given":"Lamei","family":"Di","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4936-0061","authenticated-orcid":false,"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0436-5209","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8418-2826","authenticated-orcid":false,"given":"Wenxia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ordos Institute of Technology, Ordos, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/buildings14082344"},{"key":"e_1_3_2_1_2_1","volume-title":"Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance. arXiv preprint arXiv:2408.04224","author":"Arrabi Ahmad","year":"2024","unstructured":"Ahmad Arrabi, Xiaohan Zhang, Waqas Sultani, Chen Chen, and Safwan Wshah. 2024. Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance. arXiv preprint arXiv:2408.04224 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Scale in remote sensing","author":"Cao Changyong","unstructured":"Changyong Cao and Nina Siu-Ngan Lam. 2023. Understanding the scale and resolution effects in remote sensing and GIS. In Scale in remote sensing and GIS. Routledge, 57-72."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology Vol. 15 3 (2024) 1-45.","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110600"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1107\/S0021889897006729"},{"key":"e_1_3_2_1_7_1","volume-title":"Simvg: A simple framework for visual grounding with decoupled multi-modal fusion. Advances in neural information processing systems","author":"Dai Ming","year":"2024","unstructured":"Ming Dai, Lingfeng Yang, Yihao Xu, Zhenhua Feng, and Wankou Yang. 2024. Simvg: A simple framework for visual grounding with decoupled multi-modal fusion. Advances in neural information processing systems, Vol. 37 (2024), 121670-121698."},{"key":"e_1_3_2_1_8_1","first-page":"7109","article-title":"Multi-scale and multi-dimensional weighted network for salient object detection in optical remote sensing images","volume":"5625114","author":"Di Lamei","year":"2024","unstructured":"Lamei Di, Bin Zhang, and Yiming Wang. 2024. Multi-scale and multi-dimensional weighted network for salient object detection in optical remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 5625114 (2024), 7109-7120.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103917"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00264"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275252"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111478"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3336952"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00018-1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528347"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681132"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Enkelejda Kasneci Kathrin Se\u00dfler Stefan K\u00fcchemann Maria Bannert Daryna Dementieva Frank Fischer Urs Gasser Georg Groh Stephan G\u00fcnnemann Eyke H\u00fcllermeier et al. 2023. ChatGPT for good? On opportunities and challenges of large language models for education. Learning and individual differences Vol. 103 (2023) 102274.","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs15122954"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2925070"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3314285"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3162945"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/e26060445"},{"key":"e_1_3_2_1_24_1","volume-title":"Object detection in optical remote sensing images: A survey and a new benchmark. ISPRS journal of photogrammetry and remote sensing","author":"Li Ke","year":"2020","unstructured":"Ke Li, Gang Wan, Gong Cheng, Liqiu Meng, and Junwei Han. 2020. Object detection in optical remote sensing images: A survey and a new benchmark. ISPRS journal of photogrammetry and remote sensing, Vol. 159 (2020), 296-307."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121778"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02517"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3439401"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs11091089"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3545681"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16203852"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2024.2429784"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.seta.2023.103270"},{"key":"e_1_3_2_1_33_1","first-page":"1","article-title":"ORSI salient object detection via multiscale joint region and boundary model","volume":"60","author":"Tu Zhengzheng","year":"2021","unstructured":"Zhengzheng Tu, Chao Wang, Chenglong Li, Minghao Fan, Haifeng Zhao, and Bin Luo. 2021. ORSI salient object detection via multiscale joint region and boundary model. IEEE Transactions on Geoscience and Remote Sensing, Vol. 60 (2021), 1-13.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2024.01.007"},{"key":"e_1_3_2_1_35_1","volume-title":"Pvt v2: Improved baselines with pyramid vision transformer. Computational visual media","author":"Wang Wenhai","year":"2022","unstructured":"Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2022b. Pvt v2: Improved baselines with pyramid vision transformer. Computational visual media, Vol. 8, 3 (2022), 415-424."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224815"},{"key":"e_1_3_2_1_37_1","first-page":"76656","article-title":"Frequency-domain mlps are more effective learners in time series forecasting","volume":"36","author":"Yi Kun","year":"2023","unstructured":"Kun Yi, Qi Zhang, Wei Fan, Shoujin Wang, Pengyang Wang, Hui He, Ning An, Defu Lian, Longbing Cao, and Zhendong Niu. 2023. Frequency-domain mlps are more effective learners in time series forecasting. Advances in Neural Information Processing Systems, Vol. 36 (2023), 76656-76679.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02314-0"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3300317","article-title":"Adaptive edge-aware semantic interaction network for salient object detection in optical remote sensing images","volume":"61","author":"Zeng Xiangyu","year":"2023","unstructured":"Xiangyu Zeng, Mingzhu Xu, Yijun Hu, Haoyu Tang, Yupeng Hu, and Liqiang Nie. 2023. Adaptive edge-aware semantic interaction network for salient object detection in optical remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, Vol. 61 (2023), 1-16.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3372416"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2019.1608384"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042084"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3421950"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301279"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00446"},{"key":"e_1_3_2_1_47_1","volume-title":"Mesam: Multiscale enhanced segment anything model for optical remote sensing images","author":"Zhou Xichuan","year":"2024","unstructured":"Xichuan Zhou, Fu Liang, Lihui Chen, Haijun Liu, Qianqian Song, Gemine Vivone, and Jocelyn Chanussot. 2024. Mesam: Multiscale enhanced segment anything model for optical remote sensing images. IEEE Transactions on Geoscience and Remote Sensing (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163152"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3196040"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16122134"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:07:22Z","timestamp":1765310842000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755562","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755562","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}