{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:00:57Z","timestamp":1765310457537,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"name":"the Science and Technology Innovation Plan of Shanghai Science and Technology Commission","award":["22511106005"],"award-info":[{"award-number":["22511106005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755175","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:39:06Z","timestamp":1761377946000},"page":"3741-3750","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9565-1571","authenticated-orcid":false,"given":"Chao","family":"Yin","sequence":"first","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8827-8351","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5084-3474","authenticated-orcid":false,"given":"Kequan","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0754-5842","authenticated-orcid":false,"given":"Jide","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9781-5429","authenticated-orcid":false,"given":"Pinpin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-2783","authenticated-orcid":false,"given":"Xiaoqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"1597","article-title":"Frequency-tuned salient region detection","author":"Achanta Radhakrishna","year":"2009","unstructured":"Radhakrishna Achanta, Sheila Hemami, Francisco Estrada, and Sabine Susstrunk. 2009. Frequency-tuned salient region detection. In CVPR. 1597-1604.","journal-title":"CVPR."},{"key":"e_1_3_2_1_2_1","first-page":"332","article-title":"Just a Hint","author":"Chen Huafeng","year":"2024","unstructured":"Huafeng Chen, Dian Shao, Guangqian Guo, and Shan Gao. 2024a. Just a Hint: Point-Supervised Camouflaged Object Detection. In ECCV. 332-348.","journal-title":"Point-Supervised Camouflaged Object Detection. In ECCV."},{"key":"e_1_3_2_1_3_1","volume-title":"SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection","author":"Chen Huafeng","year":"2024","unstructured":"Huafeng Chen, Pengxu Wei, Guangqian Guo, and Shan Gao. 2024c. SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_4_1","first-page":"3367","article-title":"Sam-adapter: Adapting segment anything in underperformed scenes","author":"Chen Tianrun","year":"2023","unstructured":"Tianrun Chen, Lanyun Zhu, Chaotao Deng, Runlong Cao, Yan Wang, Shangzhan Zhang, Zejian Li, Lingyun Sun, Ying Zang, and Papa Mao. 2023. Sam-adapter: Adapting segment anything in underperformed scenes. In ICCV. 3367-3375.","journal-title":"ICCV."},{"key":"e_1_3_2_1_5_1","first-page":"14162","article-title":"Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models","author":"Chen Wenqing","year":"2024","unstructured":"Wenqing Chen, Weicheng Wang, Zhixuan Chu, Kui Ren, Zibin Zheng, and Zhichao Lu. 2024b. Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models. In ACL. 14162-14167.","journal-title":"ACL."},{"key":"e_1_3_2_1_6_1","first-page":"4558","article-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. 4558-4567.","journal-title":"ICCV."},{"key":"e_1_3_2_1_7_1","first-page":"698","article-title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","author":"Fan Deng-Ping","year":"2018","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. 698-704.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_8_1","first-page":"2774","article-title":"Camouflaged Object Detection","author":"Fan Deng-Ping","year":"2020","unstructured":"Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, Ming-Ming Cheng, Jianbing Shen, and Ling Shao. 2020. Camouflaged Object Detection. In CVPR. 2774-2784.","journal-title":"CVPR."},{"key":"e_1_3_2_1_9_1","first-page":"4766","article-title":"Semi-supervised Camouflaged Object Detection from Noisy Data","author":"Fu Yuanbin","year":"2024","unstructured":"Yuanbin Fu, Jie Ying, Houlei Lv, and Xiaojie Guo. 2024. Semi-supervised Camouflaged Object Detection from Noisy Data. In ACM MM. 4766-4775.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_10_1","first-page":"22046","article-title":"Camouflaged Object Detection with Feature Decomposition and Edge Reconstruction","author":"He Chunming","year":"2023","unstructured":"Chunming He, Kai Li, Yachao Zhang, Longxiang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. 2023b. Camouflaged Object Detection with Feature Decomposition and Edge Reconstruction. In CVPR. 22046-22055.","journal-title":"CVPR."},{"key":"e_1_3_2_1_11_1","first-page":"30726","article-title":"Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping","volume":"36","author":"He Chunming","year":"2023","unstructured":"Chunming He, Kai Li, Yachao Zhang, Guoxia Xu, Longxiang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. 2023c. Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. In NeurIPS, Vol. 36. 30726-30737.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25156"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29144"},{"key":"e_1_3_2_1_14_1","first-page":"107171","article-title":"Leveraging hallucinations to reduce manual prompt dependency in promptable segmentation","volume":"37","author":"Hu Jian","year":"2024","unstructured":"Jian Hu, Jiayi Lin, Junchi Yan, and Shaogang Gong. 2024b. Leveraging hallucinations to reduce manual prompt dependency in promptable segmentation. In NeurIPS, Vol. 37. 107171-107197.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1365-9"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3881-x"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1526-0"},{"key":"e_1_3_2_1_18_1","first-page":"29914","article-title":"Segment Anything in High Quality","volume":"36","author":"Ke Lei","year":"2023","unstructured":"Lei Ke, Mingqiao Ye, Martin Danelljan, Yifan Liu, Yu-Wing Tai, Chi-Keung Tang, and Fisher Yu. 2023. Segment Anything in High Quality. In NeurIPS, Vol. 36. 29914-29934.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_19_1","first-page":"4015","article-title":"Segment anything","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C Berg, Wan-Yen Lo, et al., 2023. Segment anything. In ICCV. 4015-4026.","journal-title":"ICCV."},{"key":"e_1_3_2_1_20_1","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In NeurIPS, Vol. 35. 22199-22213.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_21_1","first-page":"438","article-title":"CamoTeacher","author":"Lai Xunfa","year":"2024","unstructured":"Xunfa Lai, Zhiyu Yang, Jie Hu, Shengchuan Zhang, Liujuan Cao, Guannan Jiang, Zhiyu Wang, Songan Zhang, and Rongrong Ji. 2024. CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection. In ECCV. 438-455.","journal-title":"Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection. In ECCV."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.04.006"},{"key":"e_1_3_2_1_23_1","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In ICML. 19730-19742.","journal-title":"ICML."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"e_1_3_2_1_25_1","first-page":"16907","article-title":"Tree energy loss: Towards sparsely annotated semantic segmentation","author":"Liang Zhiyuan","year":"2022","unstructured":"Zhiyuan Liang, Tiancai Wang, Xiangyu Zhang, Jian Sun, and Jianbing Shen. 2022. Tree energy loss: Towards sparsely annotated semantic segmentation. In CVPR. 16907-16916.","journal-title":"CVPR."},{"key":"e_1_3_2_1_26_1","first-page":"26296","article-title":"Improved baselines with visual instruction tuning","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024a. Improved baselines with visual instruction tuning. In CVPR. 26296-26306.","journal-title":"CVPR."},{"key":"e_1_3_2_1_27_1","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. In NeurIPS, Vol. 36. 34892-34916.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03766-1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104924"},{"key":"e_1_3_2_1_30_1","first-page":"1","article-title":"Improving underwater camouflage object segmentation with dual-decoder attention network","volume":"81","author":"Liu Yiwen","year":"2025","unstructured":"Yiwen Liu, Xiaoyu Zhang, Jinchao Zhu, and Panlong Tan. 2025b. Improving underwater camouflage object segmentation with dual-decoder attention network. The Journal of Supercomputing, Vol. 81, 1 (2025), 1-21.","journal-title":"The Journal of Supercomputing"},{"key":"e_1_3_2_1_31_1","first-page":"14420","article-title":"Compositional chain-of-thought prompting for large multimodal models","author":"Mitra Chancharik","year":"2024","unstructured":"Chancharik Mitra, Brandon Huang, Trevor Darrell, and Roei Herzig. 2024. Compositional chain-of-thought prompting for large multimodal models. In CVPR. 14420-14431.","journal-title":"CVPR."},{"key":"e_1_3_2_1_32_1","first-page":"6316","article-title":"MiNet: Weakly-Supervised Camouflaged Object Detection through Mutual Interaction between Region and Edge Cues","author":"Niu Yuzhen","year":"2024","unstructured":"Yuzhen Niu, Lifen Yang, Rui Xu, Yuezhou Li, and Yuzhong Chen. 2024. MiNet: Weakly-Supervised Camouflaged Object Detection through Mutual Interaction between Region and Edge Cues. In ACM MM. 6316-6325.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2024. GPT-4V: Enhancing GPT-4 for Visual Processing. https:\/\/www.openai.com Accessed: 2024-05-20."},{"key":"e_1_3_2_1_34_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In ICML. 8748-8763.","journal-title":"ICML."},{"key":"e_1_3_2_1_35_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan et al. 2024. Grounded sam: Assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)."},{"volume-title":"Animal camouflage analysis: Chameleon database. Unpublished manuscript","year":"2018","key":"e_1_3_2_1_36_1","unstructured":"2018. Animal camouflage analysis: Chameleon database. Unpublished manuscript, Vol. 2, 6 (2018), 7."},{"key":"e_1_3_2_1_37_1","first-page":"1335","article-title":"Boundary-Guided Camouflaged Object Detection","author":"Sun Yujia","year":"2022","unstructured":"Yujia Sun, Shuo Wang, Chenglizhao Chen, and Tian-Zhu Xiang. 2022. Boundary-Guided Camouflaged Object Detection. In IJCAI. 1335-1341.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_38_1","first-page":"343","article-title":"Frequency-spatial entanglement learning for camouflaged object detection","author":"Sun Yanguang","year":"2024","unstructured":"Yanguang Sun, Chunyan Xu, Jian Yang, Hanyu Xuan, and Lei Luo. 2024. Frequency-spatial entanglement learning for camouflaged object detection. In ECCV. 343-360.","journal-title":"ECCV."},{"key":"e_1_3_2_1_39_1","first-page":"8805","article-title":"Chain of visual perception: Harnessing multimodal large language models for zero-shot camouflaged object detection","author":"Tang Lv","year":"2024","unstructured":"Lv Tang, Peng-Tao Jiang, Zhi-Hao Shen, Hao Zhang, Jin-Wei Chen, and Bo Li. 2024. Chain of visual perception: Harnessing multimodal large language models for zero-shot camouflaged object detection. In ACM MM. 8805-8814.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_40_1","volume-title":"CSCE8","author":"Hang Truong Thi Thu","year":"2024","unstructured":"Thi Thu Hang Truong and Trung Kien Tran. 2024. A style transfer-based augmentation approach for detecting military camouflaged object. JMST's Section on Computer Science and Control Engineering., CSCE8 (2024), 44-54."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29884"},{"key":"e_1_3_2_1_42_1","first-page":"17201","article-title":"Depth-aware concealed crop detection in dense agricultural scenes","author":"Wang Liqiong","year":"2024","unstructured":"Liqiong Wang, Jinyu Yang, Yanfu Zhang, Fangyi Wang, and Feng Zheng. 2024c. Depth-aware concealed crop detection in dense agricultural scenes. In CVPR. 17201-17211.","journal-title":"CVPR."},{"key":"e_1_3_2_1_43_1","first-page":"4021","article-title":"Edge-Guided Pixel Level Connected Component Assisted Camouflaged Object Detection","author":"Wang Qingwang","year":"2024","unstructured":"Qingwang Wang, Xin Qu, Liyao Zhou, Pengcheng Jin, Chengbiao Fu, and Tao Shen. 2024b. Edge-Guided Pixel Level Connected Component Assisted Camouflaged Object Detection. In ICIP. 4021-4027.","journal-title":"ICIP."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102871"},{"key":"e_1_3_2_1_45_1","volume-title":"Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In ICLR."},{"key":"e_1_3_2_1_46_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. In NeurIPS, Vol. 35. 24824-24837.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_47_1","volume-title":"Deng-Ping Fan, Jingjing Wang, Shuo Wang, C\u00e9dric Demonceaux, Radu Timofte, and Luc Van Gool.","author":"Wu Zongwei","year":"2023","unstructured":"Zongwei Wu, Danda Pani Paudel, Deng-Ping Fan, Jingjing Wang, Shuo Wang, C\u00e9dric Demonceaux, Radu Timofte, and Luc Van Gool. 2023a. Source-free Depth for Object Pop-out. In ICCV. 1032-1042."},{"key":"e_1_3_2_1_48_1","first-page":"3455","article-title":"Object Segmentation by Mining Cross-Modal Semantics","author":"Wu Zongwei","year":"2023","unstructured":"Zongwei Wu, Jingjing Wang, Zhuyun Zhou, Zhaochong An, Qiuping Jiang, C\u00e9dric Demonceaux, Guolei Sun, and Radu Timofte. 2023b. Object Segmentation by Mining Cross-Modal Semantics. In ACM MM. 3455-3464.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_49_1","first-page":"1789","article-title":"Frequency representation integration for camouflaged object detection","author":"Xie Chenxi","year":"2023","unstructured":"Chenxi Xie, Changqun Xia, Tianshu Yu, and Jia Li. 2023. Frequency representation integration for camouflaged object detection. In ACM MM. 1789-1797.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105526"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3426979"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16434"},{"key":"e_1_3_2_1_53_1","first-page":"4322","article-title":"Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection","author":"Yu Zhenni","year":"2024","unstructured":"Zhenni Yu, Xiaoqin Zhang, Li Zhao, Yi Bin, and Guobao Xiao. 2024. Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection. In ACM MM. 4322-4330.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28521"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109356"},{"key":"e_1_3_2_1_56_1","first-page":"12546","article-title":"Weakly-supervised salient object detection via scribble annotations","author":"Zhang Jing","year":"2020","unstructured":"Jing Zhang, Xin Yu, Aixuan Li, Peipei Song, Bowen Liu, and Yuchao Dai. 2020. Weakly-supervised salient object detection via scribble annotations. In CVPR. 12546-12555.","journal-title":"CVPR."},{"key":"e_1_3_2_1_57_1","first-page":"158","article-title":"Learning Camouflaged Object Detection from Noisy Pseudo Label","author":"Zhang Jin","year":"2024","unstructured":"Jin Zhang, Ruiheng Zhang, Yanjiao Shi, Zhe Cao, Nian Liu, and Fahad Shahbaz Khan. 2024b. Learning Camouflaged Object Detection from Noisy Pseudo Label. In ECCV. 158-174.","journal-title":"ECCV."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4233-9"},{"key":"e_1_3_2_1_59_1","volume-title":"George Karypis, and Alex Smola.","author":"Zhang Zhuosheng","year":"2024","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, hai zhao, George Karypis, and Alex Smola. 2024a. Multimodal Chain-of-Thought Reasoning in Language Models. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_2_1_60_1","first-page":"181","article-title":"Focusdiffuser: Perceiving local disparities for camouflaged object detection","author":"Zhao Jianwei","year":"2024","unstructured":"Jianwei Zhao, Xin Li, Fan Yang, Qiang Zhai, Ao Luo, Zicheng Jiao, and Hong Cheng. 2024. Focusdiffuser: Perceiving local disparities for camouflaged object detection. In ECCV. 181-198.","journal-title":"ECCV."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128395"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.12.003"},{"key":"e_1_3_2_1_63_1","first-page":"15116","article-title":"Generalized decoding for pixel, image, and language","author":"Zou Xueyan","year":"2023","unstructured":"Xueyan Zou, Zi-Yi Dou, Jianwei Yang, Zhe Gan, Linjie Li, Chunyuan Li, Xiyang Dai, Harkirat Behl, Jianfeng Wang, Lu Yuan, et al., 2023a. Generalized decoding for pixel, image, and language. In CVPR. 15116-15127.","journal-title":"CVPR."},{"key":"e_1_3_2_1_64_1","first-page":"19769","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou Xueyan","year":"2023","unstructured":"Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, and Yong Jae Lee. 2023b. Segment everything everywhere all at once. In NeurIPS, Vol. 36. 19769-19782.","journal-title":"NeurIPS"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:58:44Z","timestamp":1765310324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755175"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3755175","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755175","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"}}]}}