{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:30:24Z","timestamp":1792787424827,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":46,"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":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["14201620 and 14201321"],"award-info":[{"award-number":["14201620 and 14201321"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902139"],"award-info":[{"award-number":["61902139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611811","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"2139-2147","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2630-2838","authenticated-orcid":false,"given":"Jialun","family":"Pei","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3872-4581","authenticated-orcid":false,"given":"Zhangjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-3877","authenticated-orcid":false,"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8454-1407","authenticated-orcid":false,"given":"He","family":"Tang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3055-5034","authenticated-orcid":false,"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Frequency-tuned salient region detection","author":"Achanta Radhakrishna","unstructured":"Radhakrishna Achanta, Sheila Hemami, Francisco Estrada, and Sabine Susstrunk. 2009. Frequency-tuned salient region detection. In CVPR. IEEE, Miami, Florida, USA, 1597--1604."},{"key":"e_1_3_2_2_2_1","volume-title":"Linknet: Exploiting encoder representations for efficient semantic segmentation","author":"Chaurasia Abhishek","year":"2017","unstructured":"Abhishek Chaurasia and Eugenio Culurciello. 2017. Linknet: Exploiting encoder representations for efficient semantic segmentation. In VCIP. IEEE, Petersburg, FL, USA, 1--4."},{"key":"e_1_3_2_2_3_1","volume-title":"Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images","author":"Chen Wuyang","unstructured":"Wuyang Chen, Ziyu Jiang, Zhangyang Wang, Kexin Cui, and Xiaoning Qian. 2019. Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images. In CVPR. IEEE, Long Beach, CA, USA, 8924--8933."},{"key":"e_1_3_2_2_4_1","volume-title":"Global context-aware progressive aggregation network for salient object detection","author":"Chen Zuyao","unstructured":"Zuyao Chen, Qianqian Xu, Runmin Cong, and Qingming Huang. 2020. Global context-aware progressive aggregation network for salient object detection. In AAAI. AAAI Press, New York, NY, USA, 10599--10606."},{"key":"e_1_3_2_2_5_1","volume-title":"Cascadepsp: Toward class-agnostic and very high-resolution segmentation via global and local refinement","author":"Cheng Ho Kei","year":"2020","unstructured":"Ho Kei Cheng, Jihoon Chung, Yu-Wing Tai, and Chi-Keung Tang. 2020. Cascadepsp: Toward class-agnostic and very high-resolution segmentation via global and local refinement. In CVPR. IEEE, Seattle, WA, USA, 8890--8899."},{"key":"e_1_3_2_2_6_1","volume-title":"Imagenet: A large-scale hierarchical image database","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. IEEE, Miami, Florida, USA, 248--255."},{"key":"e_1_3_2_2_7_1","volume-title":"Structure-measure: A new way to evaluate foreground maps","author":"Fan Deng-Ping","year":"2017","unstructured":"Deng-Ping Fan, Ming-Ming Cheng, Yun Liu, Tao Li, and Ali Borji. 2017. Structure-measure: A new way to evaluate foreground maps. In ICCV. IEEE, Venice, Italy, 4548--4557."},{"key":"e_1_3_2_2_8_1","volume-title":"Enhanced-alignment measure for binary foreground map evaluation","author":"Fan Deng-Ping","unstructured":"Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, and Ali Borji. 2018. Enhanced-alignment measure for binary foreground map evaluation. In IJCAI. AAAI Press, Stockholm, Sweden, 1--10."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085766"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3166451"},{"key":"e_1_3_2_2_11_1","volume-title":"Rethinking bisenet for real-time semantic segmentation","author":"Fan Mingyuan","unstructured":"Mingyuan Fan, Shenqi Lai, Junshi Huang, Xiaoming Wei, Zhenhua Chai, Junfeng Luo, and Xiaolin Wei. 2021b. Rethinking bisenet for real-time semantic segmentation. In CVPR. IEEE, virtual, 9716--9725."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"e_1_3_2_2_13_1","volume-title":"Isdnet: Integrating shallow and deep networks for efficient ultra-high resolution segmentation","author":"Guo Shaohua","year":"2022","unstructured":"Shaohua Guo, Liang Liu, Zhenye Gan, Yabiao Wang, Wuhao Zhang, Chengjie Wang, Guannan Jiang, Wei Zhang, Ran Yi, Lizhuang Ma, et al. 2022. Isdnet: Integrating shallow and deep networks for efficient ultra-high resolution segmentation. In CVPR. IEEE, New Orleans, LA, USA, 4361--4370."},{"key":"e_1_3_2_2_14_1","volume-title":"Deep residual learning for image recognition","author":"He Kaiming","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. IEEE, Las Vegas, NV, USA, 770--778."},{"key":"e_1_3_2_2_15_1","volume-title":"Learning implicit feature alignment function for semantic segmentation","author":"Hu Hanzhe","unstructured":"Hanzhe Hu, Yinbo Chen, Jiarui Xu, Shubhankar Borse, Hong Cai, Fatih Porikli, and Xiaolong Wang. 2022. Learning implicit feature alignment function for semantic segmentation. In ECCV. Elsevier, Tel Aviv, Israel, 487--505."},{"key":"e_1_3_2_2_16_1","volume-title":"From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation","author":"Li Qi","unstructured":"Qi Li, Weixiang Yang, Wenxi Liu, Yuanlong Yu, and Shengfeng He. 2021. From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation. In ICCV. IEEE, Montreal, QC, Canada, 7252--7261."},{"key":"e_1_3_2_2_17_1","volume-title":"Real-time high-resolution background matting","author":"Lin Shanchuan","unstructured":"Shanchuan Lin, Andrey Ryabtsev, Soumyadip Sengupta, Brian L Curless, Steven M Seitz, and Ira Kemelmacher-Shlizerman. 2021. Real-time high-resolution background matting. In CVPR. IEEE, virtual, 8762--8771."},{"key":"e_1_3_2_2_18_1","volume-title":"How to evaluate foreground maps?","author":"Margolin Ran","unstructured":"Ran Margolin, Lihi Zelnik-Manor, and Ayellet Tal. 2014. How to evaluate foreground maps?. In CVPR. IEEE, Columbus, OH, USA, 248--255."},{"key":"e_1_3_2_2_19_1","volume-title":"Camouflaged object segmentation with distraction mining","author":"Mei Haiyang","unstructured":"Haiyang Mei, Ge-Peng Ji, Ziqi Wei, Xin Yang, Xiaopeng Wei, and Deng-Ping Fan. 2021. Camouflaged object segmentation with distraction mining. In CVPR. IEEE, virtual, 8772--8781."},{"key":"e_1_3_2_2_20_1","volume-title":"Zoom in and out: A mixed-scale triplet network for camouflaged object detection","author":"Pang Youwei","unstructured":"Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, and Huchuan Lu. 2022. Zoom in and out: A mixed-scale triplet network for camouflaged object detection. In CVPR. IEEE, New Orleans, LA, USA, 2160--2170."},{"key":"e_1_3_2_2_21_1","volume-title":"Saliency filters: Contrast based filtering for salient region detection","author":"Perazzi Federico","unstructured":"Federico Perazzi, Philipp Kr\u00e4henb\u00fchl, Yael Pritch, and Alexander Hornung. 2012. Saliency filters: Contrast based filtering for salient region detection. In CVPR. IEEE, Providence, RI, USA, 733--740."},{"key":"e_1_3_2_2_22_1","volume-title":"Full-resolution residual networks for semantic segmentation in street scenes","author":"Pohlen Tobias","unstructured":"Tobias Pohlen, Alexander Hermans, Markus Mathias, and Bastian Leibe. 2017. Full-resolution residual networks for semantic segmentation in street scenes. In CVPR. IEEE, Honolulu, HI, USA, 4151--4160."},{"key":"e_1_3_2_2_23_1","volume-title":"Highly accurate dichotomous image segmentation","author":"Qin Xuebin","unstructured":"Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, and Luc Van Gool. 2022. Highly accurate dichotomous image segmentation. In ECCV. Springer, Tel Aviv, Israel, 38--56."},{"key":"e_1_3_2_2_24_1","volume-title":"U2-Net: Going deeper with nested U-structure for salient object detection. Pattern recognition","author":"Qin Xuebin","year":"2020","unstructured":"Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R Zaiane, and Martin Jagersand. 2020. U2-Net: Going deeper with nested U-structure for salient object detection. Pattern recognition, Vol. 106 (2020), 107404."},{"key":"e_1_3_2_2_25_1","volume-title":"Basnet: Boundary-aware salient object detection","author":"Qin Xuebin","year":"2019","unstructured":"Xuebin Qin, Zichen Zhang, Chenyang Huang, Chao Gao, Masood Dehghan, and Martin Jagersand. 2019. Basnet: Boundary-aware salient object detection. In CVPR. IEEE, Long Beach, CA, USA, 7479--7489."},{"key":"e_1_3_2_2_26_1","first-page":"263","article-title":"Erfnet: Efficient residual factorized convnet for real-time semantic segmentation","volume":"19","author":"Romera Eduardo","year":"2017","unstructured":"Eduardo Romera, Jose M Alvarez, Luis M Bergasa, and Roberto Arroyo. 2017. Erfnet: Efficient residual factorized convnet for real-time semantic segmentation. IEEE TITS, Vol. 19, 1 (2017), 263--272.","journal-title":"IEEE TITS"},{"key":"e_1_3_2_2_27_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In MICCAI","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI, Vol. 9351. Springer, Munich, Germany, 234--241."},{"key":"e_1_3_2_2_28_1","volume-title":"High quality segmentation for ultra high-resolution images","author":"Shen Tiancheng","unstructured":"Tiancheng Shen, Yuechen Zhang, Lu Qi, Jason Kuen, Xingyu Xie, Jianlong Wu, Zhe Lin, and Jiaya Jia. 2022. High quality segmentation for ultra high-resolution images. In CVPR. IEEE, New Orleans, LA, USA, 1310--1319."},{"key":"e_1_3_2_2_29_1","volume-title":"Disentangled high quality salient object detection","author":"Tang Lv","unstructured":"Lv Tang, Bo Li, Yijie Zhong, Shouhong Ding, and Mofei Song. 2021. Disentangled high quality salient object detection. In ICCV. IEEE, Montreal, QC, Canada, 3580--3590."},{"key":"e_1_3_2_2_30_1","first-page":"1","article-title":"Kine-Appendage: Enhancing Freehand VR Interaction Through Transformations of Virtual Appendages","volume":"1","author":"Tian Yang","year":"2022","unstructured":"Yang Tian, Hualong Bai, Shengdong Zhao, Chi-Wing Fu, Chun Yu, Haozhao Qin, Qiong Wang, and Pheng-Ann Heng. 2022. Kine-Appendage: Enhancing Freehand VR Interaction Through Transformations of Virtual Appendages. IEEE TVCG, Vol. 1, 1 (2022), 1--17.","journal-title":"IEEE TVCG"},{"key":"e_1_3_2_2_31_1","volume-title":"Unext: Mlp-based rapid medical image segmentation network","author":"Jose Valanarasu Jeya Maria","year":"2022","unstructured":"Jeya Maria Jose Valanarasu and Vishal M Patel. 2022. Unext: Mlp-based rapid medical image segmentation network. In MICCAI. Springer, Singapore, 23--33."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"e_1_3_2_2_34_1","volume-title":"F3Net: fusion, feedback and focus for salient object detection","author":"Wei Jun","unstructured":"Jun Wei, Shuhui Wang, and Qingming Huang. 2020a. F3Net: fusion, feedback and focus for salient object detection. In AAAI. AAAI Press, New York, NY, USA, 12321--12328."},{"key":"e_1_3_2_2_35_1","volume-title":"Label decoupling framework for salient object detection","author":"Wei Jun","unstructured":"Jun Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, and Qi Tian. 2020b. Label decoupling framework for salient object detection. In CVPR. IEEE, Seattle, WA, USA, 13025--13034."},{"key":"e_1_3_2_2_36_1","volume-title":"Pyramid grafting network for one-stage high resolution saliency detection","author":"Xie Chenxi","unstructured":"Chenxi Xie, Changqun Xia, Mingcan Ma, Zhirui Zhao, Xiaowu Chen, and Jia Li. 2022. Pyramid grafting network for one-stage high resolution saliency detection. In CVPR. IEEE, New Orleans, LA, USA, 11717--11726."},{"key":"e_1_3_2_2_37_1","volume-title":"Bisenet: Bilateral segmentation network for real-time semantic segmentation","author":"Yu Changqian","year":"2018","unstructured":"Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, and Nong Sang. 2018. Bisenet: Bilateral segmentation network for real-time semantic segmentation. In ECCV. Elsevier, Munich, Germany, 325--341."},{"key":"e_1_3_2_2_38_1","volume-title":"Mask guided matting via progressive refinement network","author":"Yu Qihang","unstructured":"Qihang Yu, Jianming Zhang, He Zhang, Yilin Wang, Zhe Lin, Ning Xu, Yutong Bai, and Alan Yuille. 2021. Mask guided matting via progressive refinement network. In CVPR. IEEE, virtual, 1154--1163."},{"key":"e_1_3_2_2_39_1","volume-title":"Towards high-resolution salient object detection","author":"Zeng Yi","unstructured":"Yi Zeng, Pingping Zhang, Jianming Zhang, Zhe Lin, and Huchuan Lu. 2019. Towards high-resolution salient object detection. In ICCV. IEEE, Seoul, Korea (South), 7234--7243."},{"key":"e_1_3_2_2_40_1","volume-title":"Auto-msfnet: Search multi-scale fusion network for salient object detection. In Multimedia. ACM, Chengdu, China, 667--676.","author":"Zhang Miao","year":"2021","unstructured":"Miao Zhang, Tingwei Liu, Yongri Piao, Shunyu Yao, and Huchuan Lu. 2021a. Auto-msfnet: Search multi-scale fusion network for salient object detection. In Multimedia. ACM, Chengdu, China, 667--676."},{"key":"e_1_3_2_2_41_1","first-page":"3204","article-title":"Looking for the detail and context devils: High-resolution salient object detection","volume":"30","author":"Zhang Pingping","year":"2021","unstructured":"Pingping Zhang, Wei Liu, Yi Zeng, Yinjie Lei, and Huchuan Lu. 2021b. Looking for the detail and context devils: High-resolution salient object detection. IEEE TIP, Vol. 30 (2021), 3204--3216.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_2_42_1","volume-title":"Suppress and balance: A simple gated network for salient object detection","author":"Zhao Xiaoqi","unstructured":"Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, and Lei Zhang. 2020. Suppress and balance: A simple gated network for salient object detection. In ECCV. Elsevier, Glasgow, UK, 35--51."},{"key":"e_1_3_2_2_43_1","volume-title":"Trasetr: track-to-segment transformer with contrastive query for instance-level instrument segmentation in robotic surgery","author":"Zhao Zixu","unstructured":"Zixu Zhao, Yueming Jin, and Pheng-Ann Heng. 2022. Trasetr: track-to-segment transformer with contrastive query for instance-level instrument segmentation in robotic surgery. In ICRA. IEEE, Philadelphia, PA, USA, 11186--11193."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Zhirui Zhao Changqun Xia Chenxi Xie and Jia Li. 2021. Complementary trilateral decoder for fast and accurate salient object detection. In Multimedia. ACM Chengdu China 4967--4975.","DOI":"10.1145\/3474085.3475494"},{"key":"e_1_3_2_2_45_1","volume-title":"I can find you! Boundary-guided separated attention network for camouflaged object detection","author":"Zhu Hongwei","unstructured":"Hongwei Zhu, Peng Li, Haoran Xie, Xuefeng Yan, Dong Liang, Dapeng Chen, Mingqiang Wei, and Jing Qin. 2022. I can find you! Boundary-guided separated attention network for camouflaged object detection. In AAAI. AAAI Press, New York, NY, USA, 3608--3616."},{"key":"e_1_3_2_2_46_1","first-page":"3738","article-title":"Salient object detection via integrity learning","volume":"45","author":"Zhuge Mingchen","year":"2023","unstructured":"Mingchen Zhuge, Deng-Ping Fan, Nian Liu, Dingwen Zhang, Dong Xu, and Ling Shao. 2023. Salient object detection via integrity learning. IEEE TPAMI, Vol. 45, 3 (2023), 3738--3752.","journal-title":"IEEE TPAMI"}],"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\/3581783.3611811","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:10:18Z","timestamp":1755821418000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":46,"alternative-id":["10.1145\/3581783.3611811","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611811","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"}}]}}