{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:20:52Z","timestamp":1780053652470,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":93,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680609","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10392-10401","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Unleashing the Power of Generic Segmentation Model: A Simple Baseline for Infrared Small Target Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-9784","authenticated-orcid":false,"given":"Mingjin","family":"Zhang","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5574-9399","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0060-0543","authenticated-orcid":false,"given":"Qiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0234-6270","authenticated-orcid":false,"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-0037","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Post and Telecommunications, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01057"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02323"},{"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\/TGRS.2013.2242477"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"e_1_3_2_1_8_1","volume-title":"Per-pixel classification is not all you need for semantic segmentation. Advances in Neural Information Processing Systems","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. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Segment and track anything. arXiv preprint arXiv:2305.06558","author":"Cheng Yangming","year":"2023","unstructured":"Yangming Cheng, Liulei Li, Yuanyou Xu, Xiaodi Li, Zongxin Yang, Wenguan Wang, and Yi Yang. 2023. Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00099"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044958"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2015.140878"},{"key":"e_1_3_2_1_13_1","volume-title":"Ronda Venkateswarlu, and Philip Chan.","author":"Deshpande Suyog D","year":"1999","unstructured":"Suyog D Deshpande, Meng Hwa Er, Ronda Venkateswarlu, and Philip Chan. 1999. Max-mean and max-median filters for detection of small targets. In Signal and Data Processing of Small Targets, Vol. 3809. SPIE, 74--83."},{"key":"e_1_3_2_1_14_1","volume-title":"Medical infrared imaging","author":"Diakides Nicholas A","unstructured":"Nicholas A Diakides and Joseph D Bronzino. 2007. Advances in medical infrared imaging. In Medical infrared imaging. CRC press, 19--32."},{"key":"e_1_3_2_1_15_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Mozer, and Yoshua Bengio.","author":"Goyal Anirudh","year":"2021","unstructured":"Anirudh Goyal, Aniket Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Mozer, and Yoshua Bengio. 2021. Coordination among neural modules through a shared global workspace. arXiv preprint arXiv:2103.01197 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2917825"},{"key":"e_1_3_2_1_18_1","volume-title":"Multiple choice learning: Learning to produce multiple structured outputs. Advances in Neural Information Processing Systems","author":"Guzman-Rivera Abner","year":"2012","unstructured":"Abner Guzman-Rivera, Dhruv Batra, and Pushmeet Kohli. 2012. Multiple choice learning: Learning to produce multiple structured outputs. Advances in Neural Information Processing Systems (2012)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/31.1775"},{"key":"e_1_3_2_1_20_1","volume-title":"Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. Advances in Neural Information Processing Systems","author":"He Chunming","year":"2024","unstructured":"Chunming He, Kai Li, Yachao Zhang, Guoxia Xu, Longxiang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. 2024. Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"e_1_3_2_1_22_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_23_1","unstructured":"Andrew Jaegle Sebastian Borgeaud Jean-Baptiste Alayrac Carl Doersch Catalin Ionescu David Ding Skanda Koppula Daniel Zoran Andrew Brock Evan Shelhamer et al. 2021. Perceiver io: A general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning. PMLR, 4651--4664","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. 2021. Perceiver: General perception with iterative attention. In International Conference on Machine Learning. PMLR, 4651--4664."},{"key":"e_1_3_2_1_25_1","first-page":"47","article-title":"Infrared background suppression for segmenting and detecting small target","volume":"27","author":"Zhou Peng","year":"1999","unstructured":"Peng Jia-xiong and Zhou Wen-lin. 1999. Infrared background suppression for segmenting and detecting small target. Acta Electronica Sinica, Vol. 27, 12 (1999), 47--51.","journal-title":"Acta Electronica Sinica"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/03091900512331333158"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.746635"},{"key":"e_1_3_2_1_28_1","unstructured":"Lei Ke Mingqiao Ye Martin Danelljan Yu-Wing Tai Chi-Keung Tang Fisher Yu et al. 2024. Segment anything in high quality. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10762-009-9518-2"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00099"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3199107"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"e_1_3_2_1_35_1","volume-title":"Semantic-sam: Segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767","author":"Li Feng","year":"2023","unstructured":"Feng Li, Hao Zhang, Peize Sun, Xueyan Zou, Shilong Liu, Jianwei Yang, Chunyuan Li, Lei Zhang, and Jianfeng Gao. 2023. Semantic-sam: Segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00067"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/014311697219079"},{"key":"e_1_3_2_1_42_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/07060669509500707"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"e_1_3_2_1_48_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for Thin Deep Nets. arxiv: 1412.6550 [cs.LG]"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2012.06.001"},{"key":"e_1_3_2_1_53_1","volume-title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers. arXiv preprint arXiv:2311.17132","author":"Shi Dai","year":"2023","unstructured":"Dai Shi. 2023. TransNeXt: Robust Foveal Visual Perception for Vision Transformers. arXiv preprint arXiv:2311.17132 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"e_1_3_2_1_55_1","unstructured":"Quan Sun Yufeng Cui Xiaosong Zhang Fan Zhang Qiying Yu Zhengxiong Luo Yueze Wang Yongming Rao Jingjing Liu Tiejun Huang et al. 2023. Generative multimodal models are in-context learners. arXiv preprint arXiv:2312.13286 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Can sam segment anything? when sam meets camouflaged object detection. arXiv preprint arXiv:2304.04709","author":"Tang Lv","year":"2023","unstructured":"Lv Tang, Haoke Xiao, and Bo Li. 2023. Can sam segment anything? when sam meets camouflaged object detection. arXiv preprint arXiv:2304.04709 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSSC.2010.5730289"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2008.2000926"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.157758"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710815"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_1_62_1","volume-title":"Repvit: Revisiting mobile cnn from vit perspective. arXiv preprint arXiv:2307.09283","author":"Wang Ao","year":"2023","unstructured":"Ao Wang, Hui Chen, Zijia Lin, Hengjun Pu, and Guiguang Ding. 2023. Repvit: Revisiting mobile cnn from vit perspective. arXiv preprint arXiv:2307.09283 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"Tao","author":"Wang Di","year":"2024","unstructured":"Di Wang, Jing Zhang, Bo Du, Minqiang Xu, Lin Liu, and Dacheng et al. Tao. 2024. Samrs: Scaling-up remote sensing segmentation dataset with segment anything model. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00860"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2012.08.004"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2009.03.007"},{"key":"e_1_3_2_1_67_1","volume-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620","author":"Wu Junde","year":"2023","unstructured":"Junde Wu, Rao Fu, Huihui Fang, Yuanpei Liu, Zhaowei Wang, Yanwu Xu, Yueming Jin, and Tal Arbel. 2023. Medical sam adapter: Adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620 (2023)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228497"},{"key":"e_1_3_2_1_69_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_70_1","volume-title":"Efficientsam: Leveraged masked image pretraining for efficient segment anything. arXiv preprint arXiv:2312.00863","author":"Xiong Yunyang","year":"2023","unstructured":"Yunyang Xiong, Bala Varadarajan, Lemeng Wu, Xiaoyu Xiang, Fanyi Xiao, Chenchen Zhu, Xiaoliang Dai, Dilin Wang, Fei Sun, Forrest Iandola, et al. 2023. Efficientsam: Leveraged masked image pretraining for efficient segment anything. arXiv preprint arXiv:2312.00863 (2023)."},{"key":"e_1_3_2_1_71_1","volume-title":"Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968","author":"Yang Jinyu","year":"2023","unstructured":"Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, and Feng Zheng. 2023. Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"e_1_3_2_1_73_1","volume-title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation. arXiv preprint arXiv:2401.17904","author":"Ye Maoyuan","year":"2024","unstructured":"Maoyuan Ye, Jing Zhang, Juhua Liu, Chenyu Liu, Baocai Yin, Cong Liu, Bo Du, and Dacheng Tao. 2024. Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation. arXiv preprint arXiv:2401.17904 (2024)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01490"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2017.7991306"},{"key":"e_1_3_2_1_76_1","first-page":"6575","article-title":"Volo: Vision outlooker for visual recognition","volume":"45","author":"Yuan Li","year":"2022","unstructured":"Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, and Shuicheng Yan. 2022. Volo: Vision outlooker for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 5 (2022), 6575--6586.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28514"},{"key":"e_1_3_2_1_78_1","volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)."},{"key":"e_1_3_2_1_79_1","volume-title":"Sung-Ho Bae, Seungkyu Lee, and Choong Seon Hong.","author":"Zhang Chaoning","year":"2023","unstructured":"Chaoning Zhang, Dongshen Han, Yu Qiao, Jung Uk Kim, Sung-Ho Bae, Seungkyu Lee, and Choong Seon Hong. 2023. Faster segment anything: Towards lightweight sam for mobile applications. arXiv preprint arXiv:2306.14289 (2023)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs10111821"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547817"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28551"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548264"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00095"},{"key":"e_1_3_2_1_85_1","volume-title":"Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048","author":"Zhang Renrui","year":"2023","unstructured":"Renrui Zhang, Zhengkai Jiang, Ziyu Guo, Shilin Yan, Junting Pan, Hao Dong, Peng Gao, and Hongsheng Li. 2023. Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048 (2023)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs11050559"},{"key":"e_1_3_2_1_87_1","volume-title":"EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss. arXiv preprint arXiv:2402.05008","author":"Zhang Zhuoyang","year":"2024","unstructured":"Zhuoyang Zhang, Han Cai, and Song Han. 2024. EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss. arXiv preprint arXiv:2402.05008 (2024)."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3145502"},{"key":"e_1_3_2_1_89_1","volume-title":"Fast segment anything. arXiv preprint arXiv:2306.12156","author":"Zhao Xu","year":"2023","unstructured":"Xu Zhao, Wenchao Ding, Yongqi An, Yinglong Du, Tao Yu, Min Li, Ming Tang, and Jinqiao Wang. 2023. Fast segment anything. arXiv preprint arXiv:2306.12156 (2023)."},{"key":"e_1_3_2_1_90_1","volume-title":"Chen Change Loy, and Bo Dai","author":"Zhou Chong","year":"2023","unstructured":"Chong Zhou, Xiangtai Li, Chen Change Loy, and Bo Dai. 2023. EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM. arXiv preprint arXiv:2312.06660 (2023)."},{"key":"e_1_3_2_1_91_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"e_1_3_2_1_93_1","volume-title":"Segment everything everywhere all at once. Advances in Neural Information Processing Systems","author":"Zou Xueyan","year":"2024","unstructured":"Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, and Yong Jae Lee. 2024. Segment everything everywhere all at once. Advances in Neural Information Processing Systems (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":93,"alternative-id":["10.1145\/3664647.3680609","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680609","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}