{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:19:17Z","timestamp":1784391557773,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Pujiang Program","award":["22PJ1406600"],"award-info":[{"award-number":["22PJ1406600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101092"],"award-info":[{"award-number":["62101092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","award":["VRLAB2022C02"],"award-info":[{"award-number":["VRLAB2022C02"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611983","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"7413-7423","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Recurrent Multi-scale Transformer for High-Resolution Salient Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1131-4710","authenticated-orcid":false,"given":"Xinhao","family":"Deng","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1206-1444","authenticated-orcid":false,"given":"Pingping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6351-9019","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"e_1_3_2_1_7_1","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. 9th International Conference on Learning Representations, ICLR (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_12"},{"key":"e_1_3_2_1_9_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_10_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 108--124","author":"Kim Taehun","year":"2022","unstructured":"Taehun Kim, Kunhee Kim, Joonyeong Lee, Dongmin Cha, Jiho Lee, and Daijin Kim. 2022. Revisiting Image Pyramid Structure for High Resolution Salient Object Detection. In Proceedings of the Asian Conference on Computer Vision. 108--124."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5455--5463","author":"Li Guanbin","year":"2015","unstructured":"Guanbin Li and Yizhou Yu. 2015. Visual saliency based on multiscale deep features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5455--5463."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.43"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00404"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16331"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.372"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"e_1_3_2_1_21_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00766"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2280096"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3580--3590","author":"Tang Lv","year":"2021","unstructured":"Lv Tang, Bo Li, Yijie Zhong, Shouhong Ding, and Mofei Song. 2021. Disentangled high quality salient object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3580--3590."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01304"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00736"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01142"},{"key":"e_1_3_2_1_32_1","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, Vol. 34 (2021), 12077--12090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.153"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107130"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045624"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.31"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00887"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_3"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475494"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611983","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:09:50Z","timestamp":1755821390000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":41,"alternative-id":["10.1145\/3581783.3611983","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611983","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}