{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:57:27Z","timestamp":1776275847437,"version":"3.50.1"},"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612185","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"2131-2138","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["A Unified Query-based Paradigm for Camouflaged Instance Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6456-5452","authenticated-orcid":false,"given":"Bo","family":"Dong","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2630-2838","authenticated-orcid":false,"given":"Jialun","family":"Pei","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2979-9632","authenticated-orcid":false,"given":"Rongrong","family":"Gao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3321-1993","authenticated-orcid":false,"given":"Tian-Zhu","family":"Xiang","sequence":"additional","affiliation":[{"name":"G42, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7851-3824","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5401-7834","authenticated-orcid":false,"given":"Huan","family":"Xiong","sequence":"additional","affiliation":[{"name":"MBZUAI, Abu Dhabi, UAE"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Yolact: Real-time instance segmentation","author":"Bolya Daniel","year":"2019","unstructured":"Daniel Bolya, Chong Zhou, Fanyi Xiao, and Yong Jae Lee. 2019. Yolact: Real-time instance segmentation. In ICCV. IEEE, 9157--9166."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3014297"},{"key":"e_1_3_2_1_3_1","volume-title":"Cascade r-cnn: Delving into high quality object detection","author":"Cai Zhaowei","unstructured":"Zhaowei Cai and Nuno Vasconcelos. 2018. Cascade r-cnn: Delving into high quality object detection. In CVPR. IEEE, 6154--6162."},{"key":"e_1_3_2_1_4_1","volume-title":"End-to-end object detection with transformers","author":"Carion Nicolas","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-end object detection with transformers. In ECCV. Springer, 213--229."},{"key":"e_1_3_2_1_5_1","volume-title":"Blendmask: Top-down meets bottom-up for instance segmentation","author":"Chen Hao","year":"2020","unstructured":"Hao Chen, Kunyang Sun, Zhi Tian, Chunhua Shen, Yongming Huang, and Youliang Yan. 2020. Blendmask: Top-down meets bottom-up for instance segmentation. In CVPR. IEEE, 8573--8581."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Kai Chen Jiangmiao Pang Jiaqi Wang Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jianping Shi Wanli Ouyang et al. 2019. Hybrid task cascade for instance segmentation. In CVPR. IEEE 4974--4983.","DOI":"10.1109\/CVPR.2019.00511"},{"key":"e_1_3_2_1_7_1","volume-title":"Diffusion Model for Camouflaged Object Detection","author":"Chen Zhennan","unstructured":"Zhennan Chen, Rongrong Gao, Tian-Zhu Xiang, and Fan Lin. 2023. Diffusion Model for Camouflaged Object Detection. In ECAI. IOS Press."},{"key":"e_1_3_2_1_8_1","volume-title":"Masked-attention Mask Transformer for Universal Image Segmentation","author":"Cheng Bowen","unstructured":"Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, and Rohit Girdhar. 2022a. Masked-attention Mask Transformer for Universal Image Segmentation. In CVPR. IEEE, 1280--1289."},{"key":"e_1_3_2_1_9_1","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng, Alex Schwing, and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. NeurIPS, Vol. 34 (2021), 17864--17875.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_10_1","volume-title":"Sparse Instance Activation for Real-Time Instance Segmentation","author":"Cheng Tianheng","unstructured":"Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Wenqiang Zhang, Qian Zhang, Chang Huang, Zhaoxiang Zhang, and Wenyu Liu. 2022b. Sparse Instance Activation for Real-Time Instance Segmentation. In CVPR. IEEE, 4433--4442."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085766"},{"key":"e_1_3_2_1_12_1","volume-title":"Camouflaged Object Detection","author":"Fan Deng-Ping","unstructured":"Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, Ming-Ming Cheng, Jianbing Shen, and Ling Shao. 2020a. Camouflaged Object Detection. In CVPR. IEEE, 2774--2784."},{"key":"e_1_3_2_1_13_1","first-page":"263","article-title":"PraNet","volume":"12266","author":"Fan Deng-Ping","year":"2020","unstructured":"Deng-Ping Fan, Ge-Peng Ji, Tao Zhou, Geng Chen, Huazhu Fu, Jianbing Shen, and Ling Shao. 2020b. PraNet: Parallel Reverse Attention Network for Polyp Segmentation. MICCAI, Vol. 12266 (2020), 263--273.","journal-title":"Parallel Reverse Attention Network for Polyp Segmentation. MICCAI"},{"key":"e_1_3_2_1_14_1","volume-title":"Instances as queries","author":"Fang Yuxin","unstructured":"Yuxin Fang, Shusheng Yang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, and Wenyu Liu. 2021. Instances as queries. In ICCV. IEEE, 6910--6919."},{"key":"e_1_3_2_1_15_1","volume-title":"Ssap: Single-shot instance segmentation with affinity pyramid","author":"Gao Naiyu","year":"2019","unstructured":"Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Yinan Yu, Ming Yang, and Kaiqi Huang. 2019. Ssap: Single-shot instance segmentation with affinity pyramid. In ICCV. IEEE, 642--651."},{"key":"e_1_3_2_1_16_1","first-page":"2600","article-title":"TCNet: Co-Salient Object Detection via Parallel Interaction of Transformers and CNNs","volume":"33","author":"Ge Yanliang","year":"2023","unstructured":"Yanliang Ge, Qiao Zhang, Tian-Zhu Xiang, Cong Zhang, and Hongbo Bi. 2023. TCNet: Co-Salient Object Detection via Parallel Interaction of Transformers and CNNs. IEEE TCSVT, Vol. 33, 6 (2023), 2600--2615.","journal-title":"IEEE TCSVT"},{"key":"e_1_3_2_1_17_1","volume-title":"SOTR: Segmenting Objects with Transformers","author":"Guo Ruohao","year":"2021","unstructured":"Ruohao Guo, Dantong Niu, Liao Qu, and Zhenbo Li. 2021. SOTR: Segmenting Objects with Transformers. In ICCV. IEEE, 7157--7166."},{"key":"e_1_3_2_1_18_1","volume-title":"Mask R-CNN","author":"He Kaiming","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask R-CNN. In ICCV. IEEE, 2961--2969."},{"key":"e_1_3_2_1_19_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, 770--778."},{"key":"e_1_3_2_1_20_1","volume-title":"Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers","author":"Huang Zhou","unstructured":"Zhou Huang, Hang Dai, Tian-Zhu Xiang, Shuo Wang, Huai-Xin Chen, Jie Qin, and Huan Xiong. 2023. Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers. In CVPR. IEEE, 5557--5566."},{"key":"e_1_3_2_1_21_1","volume-title":"Mask scoring r-cnn","author":"Huang Zhaojin","unstructured":"Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, and Xinggang Wang. 2019. Mask scoring r-cnn. In CVPR. IEEE, 6409--6418."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.07.014"},{"key":"e_1_3_2_1_23_1","volume-title":"Mask Transfiner for High-Quality Instance Segmentation","author":"Ke Lei","unstructured":"Lei Ke, Martin Danelljan, Xia Li, Yu-Wing Tai, Chi-Keung Tang, and Fisher Yu. 2022. Mask Transfiner for High-Quality Instance Segmentation. In CVPR. IEEE, 4412--4421."},{"key":"e_1_3_2_1_24_1","volume-title":"Pointrend: Image segmentation as rendering","author":"Kirillov Alexander","year":"2020","unstructured":"Alexander Kirillov, Yuxin Wu, Kaiming He, and Ross Girshick. 2020. Pointrend: Image segmentation as rendering. In CVPR. IEEE, 9799--9808."},{"key":"e_1_3_2_1_25_1","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. NeurIPS, Vol. 25 (2012), 1106--1114.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_26_1","first-page":"287","article-title":"Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite","volume":"31","author":"Le Trung-Nghia","year":"2021","unstructured":"Trung-Nghia Le, Yubo Cao, Tan-Cong Nguyen, Minh-Quan Le, Khanh-Duy Nguyen, Thanh-Toan Do, Minh-Triet Tran, and Tam V Nguyen. 2021. Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite. IEEE TIP, Vol. 31 (2021), 287--300.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_27_1","volume-title":"Dn-detr: Accelerate detr training by introducing query denoising","author":"Li Feng","year":"2022","unstructured":"Feng Li, Hao Zhang, Shilong Liu, Jian Guo, Lionel M Ni, and Lei Zhang. 2022b. Dn-detr: Accelerate detr training by introducing query denoising. In CVPR. IEEE, 13619--13627."},{"key":"e_1_3_2_1_28_1","volume-title":"Trichomonas Vaginalis Segmentation in Microscope Images","author":"Li Lin","unstructured":"Lin Li, Jingyi Liu, Shuo Wang, Xunkun Wang, and Tian-Zhu Xiang. 2022a. Trichomonas Vaginalis Segmentation in Microscope Images. In MICCAI. Springer, 68--78."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2021.100008"},{"key":"e_1_3_2_1_30_1","volume-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu Ze","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV. IEEE, 10012--10022."},{"key":"e_1_3_2_1_31_1","volume-title":"Simultaneously localize, segment and rank the camouflaged objects","author":"Lv Yunqiu","unstructured":"Yunqiu Lv, Jing Zhang, Yuchao Dai, Aixuan Li, Bowen Liu, Nick Barnes, and Deng-Ping Fan. 2021. Simultaneously localize, segment and rank the camouflaged objects. In CVPR. IEEE, 11591--11601."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/beheco\/arv096"},{"key":"e_1_3_2_1_33_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, 2160--2170."},{"key":"e_1_3_2_1_34_1","volume-title":"OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers","author":"Pei Jialun","unstructured":"Jialun Pei, Tianyang Cheng, Deng-Ping Fan, He Tang, Chuanbo Chen, and Luc Van Gool. 2022. OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers. In ECCV. Springer, 19--37."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2015.2890"},{"key":"e_1_3_2_1_36_1","volume-title":"Boundary-Guided Camouflaged Object Detection","author":"Sun Yujia","unstructured":"Yujia Sun, Shuo Wang, Chenglizhao Chen, and Tian-Zhu Xiang. 2022. Boundary-Guided Camouflaged Object Detection. In IJCAI. AAAI Press, 1335--1341."},{"key":"e_1_3_2_1_37_1","volume-title":"Conditional convolutions for instance segmentation","author":"Tian Zhi","unstructured":"Zhi Tian, Chunhua Shen, and Hao Chen. 2020. Conditional convolutions for instance segmentation. In ECCV. Springer, 282--298."},{"key":"e_1_3_2_1_38_1","volume-title":"SOLO: Segmenting Objects by Locations. In ECCV","author":"Wang Xinlong","year":"2020","unstructured":"Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, and Lei Li. 2020a. SOLO: Segmenting Objects by Locations. In ECCV, Vol. 12363. Springer, 649--665."},{"key":"e_1_3_2_1_39_1","first-page":"17721","article-title":"SOLOv2","volume":"33","author":"Wang Xinlong","year":"2020","unstructured":"Xinlong Wang, Rufeng Zhang, Tao Kong, Lei Li, and Chunhua Shen. 2020b. SOLOv2: Dynamic and Fast Instance Segmentation. NeurIPS, Vol. 33 (2020), 17721--17732.","journal-title":"Dynamic and Fast Instance Segmentation. NeurIPS"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"e_1_3_2_1_41_1","unstructured":"Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"e_1_3_2_1_42_1","first-page":"545","article-title":"Fashionformer","volume":"13697","author":"Xu Shilin","year":"2022","unstructured":"Shilin Xu, Xiangtai Li, Jingbo Wang, Guangliang Cheng, Yunhai Tong, and Dacheng Tao. 2022. Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition. ECCV, Vol. 13697 (2022), 545--563.","journal-title":"ECCV"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/ma13245755"},{"key":"e_1_3_2_1_44_1","volume-title":"Mutual graph learning for camouflaged object detection","author":"Zhai Qiang","unstructured":"Qiang Zhai, Xin Li, Fan Yang, Chenglizhao Chen, Hong Cheng, and Deng-Ping Fan. 2021. Mutual graph learning for camouflaged object detection. In CVPR. IEEE, 12997--13007."},{"key":"e_1_3_2_1_45_1","volume-title":"Memory-Aided Contrastive Consensus Learning for Co-salient Object Detection","author":"Zheng Peng","unstructured":"Peng Zheng, Jie Qin, Shuo Wang, Tian-Zhu Xiang, and Huan Xiong. 2023. Memory-Aided Contrastive Consensus Learning for Co-salient Object Detection. In AAAI. AAAI Press, 3687--3695."},{"key":"e_1_3_2_1_46_1","unstructured":"Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In ICLR. OpenReview 1--16."}],"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\/3581783.3612185","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:44Z","timestamp":1755821204000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612185"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":46,"alternative-id":["10.1145\/3581783.3612185","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612185","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"}}]}}