{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:30:44Z","timestamp":1780057844204,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shaanxi Province Key Research and Development Program Project","award":["2021GY- 034"],"award-info":[{"award-number":["2021GY- 034"]}]},{"name":"Youth Talent Promotion Project of Shaanxi University Science and Technology Association","award":["Grant 20200103"],"award-info":[{"award-number":["Grant 20200103"]}]},{"name":"EquipmentAdvance Research Field Fund Project","award":["80913010601"],"award-info":[{"award-number":["80913010601"]}]},{"name":"Chongqing Excellent Scientist Project","award":["No. cstc2021ycjh-bgzxm0339"],"award-info":[{"award-number":["No. cstc2021ycjh-bgzxm0339"]}]},{"name":"Special Project on Technological Innovation and Application Development","award":["No.cstc2020jscx-dxwtB0032"],"award-info":[{"award-number":["No.cstc2020jscx-dxwtB0032"]}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2021QNRC001"],"award-info":[{"award-number":["2021QNRC001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902293, 62036007, 62176195, and U21A20514"],"award-info":[{"award-number":["61902293, 62036007, 62176195, and U21A20514"]}],"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":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547817","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"1730-1738","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":201,"title":["RKformer: Runge-Kutta Transformer with Random-Connection Attention for Infrared Small Target Detection"],"prefix":"10.1145","author":[{"given":"Mingjin","family":"Zhang","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haichen","family":"Bai","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyue","family":"Wang","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2009.12.023"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2013.2242477"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299163"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2017.2700023"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00099"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044958"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2538295"},{"key":"e_1_3_2_2_9_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 1999, Vol. 3809 . International Society for Optics and Photonics , 74--83. 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 1999, Vol. 3809. International Society for Optics and Photonics, 74--83."},{"key":"e_1_3_2_2_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly etal 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020). 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_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.034"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2281420"},{"key":"e_1_3_2_2_13_1","volume-title":"Generative adversarial nets. Advances in Neural Information Processing Systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow , Jean Pouget-Abadie , Mehdi Mirza , Bing Xu , David Warde-Farley , Sherjil Ozair , Aaron Courville , and Yoshua Bengio . 2014. Generative adversarial nets. Advances in Neural Information Processing Systems 27 ( 2014 ). Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in Neural Information Processing Systems 27 (2014)."},{"key":"e_1_3_2_2_14_1","volume-title":"Partial Differential Equations is All You Need for Generating Neural Architectures--A Theory for Physical Artificial Intelligence Systems. arXiv preprint arXiv:2103.08313","author":"Guo Ping","year":"2021","unstructured":"Ping Guo , Kaizhu Huang , and Zenglin Xu. 2021. Partial Differential Equations is All You Need for Generating Neural Architectures--A Theory for Physical Artificial Intelligence Systems. arXiv preprint arXiv:2103.08313 ( 2021 ). Ping Guo, Kaizhu Huang, and Zenglin Xu. 2021. Partial Differential Equations is All You Need for Generating Neural Architectures--A Theory for Physical Artificial Intelligence Systems. arXiv preprint arXiv:2103.08313 (2021)."},{"key":"e_1_3_2_2_15_1","volume-title":"Infrared small target detection based on the weighted strengthened local contrast measure","author":"Han Jinhui","year":"2020","unstructured":"Jinhui Han , Saed Moradi , Iman Faramarzi , Honghui Zhang , Qian Zhao , Xiaojian Zhang , and Nan Li. 2020. Infrared small target detection based on the weighted strengthened local contrast measure . IEEE Geoscience and Remote Sensing Letters ( 2020 ). Jinhui Han, Saed Moradi, Iman Faramarzi, Honghui Zhang, Qian Zhao, Xiaojian Zhang, and Nan Li. 2020. Infrared small target detection based on the weighted strengthened local contrast measure. IEEE Geoscience and Remote Sensing Letters (2020)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00183"},{"key":"e_1_3_2_2_18_1","volume-title":"Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180","author":"Ho Jonathan","year":"2019","unstructured":"Jonathan Ho , Nal Kalchbrenner , Dirk Weissenborn , and Tim Salimans . 2019. Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 ( 2019 ). Jonathan Ho, Nal Kalchbrenner, Dirk Weissenborn, and Tim Salimans. 2019. Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 (2019)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_21_1","volume-title":"Echo state network. scholarpedia 2, 9","author":"Jaeger Herbert","year":"2007","unstructured":"Herbert Jaeger . 2007. Echo state network. scholarpedia 2, 9 ( 2007 ), 2330. Herbert Jaeger. 2007. Echo state network. scholarpedia 2, 9 (2007), 2330."},{"key":"e_1_3_2_2_22_1","volume-title":"Toward Real-world Single Image Deraining: A New Benchmark and Beyond. arXiv preprint arXiv:2206.05514","author":"Li Wei","year":"2022","unstructured":"Wei Li , Qiming Zhang , Jing Zhang , Zhen Huang , Xinmei Tian , and Dacheng Tao . 2022. Toward Real-world Single Image Deraining: A New Benchmark and Beyond. arXiv preprint arXiv:2206.05514 ( 2022 ). Wei Li, Qiming Zhang, Jing Zhang, Zhen Huang, Xinmei Tian, and Dacheng Tao. 2022. Toward Real-world Single Image Deraining: A New Benchmark and Beyond. arXiv preprint arXiv:2206.05514 (2022)."},{"key":"e_1_3_2_2_23_1","volume-title":"A Comprehensive Survey on Data-Efficient GANs in Image Generation. arXiv preprint arXiv:2204.08329","author":"Li Ziqiang","year":"2022","unstructured":"Ziqiang Li , XintianWu, Beihao Xia , Jing Zhang , ChaoyueWang, and Bin Li. 2022. A Comprehensive Survey on Data-Efficient GANs in Image Generation. arXiv preprint arXiv:2204.08329 ( 2022 ). Ziqiang Li, XintianWu, Beihao Xia, Jing Zhang, ChaoyueWang, and Bin Li. 2022. A Comprehensive Survey on Data-Efficient GANs in Image Generation. arXiv preprint arXiv:2204.08329 (2022)."},{"key":"e_1_3_2_2_24_1","volume-title":"Current Trends in Computer Science and Mechanical Automation","author":"Liu Ming","unstructured":"Ming Liu , Hao-yuan Du, Yue-jin Zhao, Li-quan Dong, and Mei Hui . 2018. Image small target detection based on deep learning with snr controlled sample generation . In Current Trends in Computer Science and Mechanical Automation Vol. 1 . De Gruyter Open Poland , 211--220. Ming Liu, Hao-yuan Du, Yue-jin Zhao, Li-quan Dong, and Mei Hui. 2018. Image small target detection based on deep learning with snr controlled sample generation. In Current Trends in Computer Science and Mechanical Automation Vol. 1. De Gruyter Open Poland, 211--220."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Lingyi Lu and Xin Xu. 2021. Visible-Infrared Cross-Modal Person Reidentification based on Positive Feedback. In ACM Multimedia Asia. 1--6. Lingyi Lu and Xin Xu. 2021. Visible-Infrared Cross-Modal Person Reidentification based on Positive Feedback. In ACM Multimedia Asia. 1--6.","DOI":"10.1145\/3469877.3497693"},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the International Conference on Machine Learning. 3276--3285","author":"Lu Yiping","year":"2018","unstructured":"Yiping Lu , Aoxiao Zhong , Quanzheng Li , and Bin Dong . 2018 . Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations . In Proceedings of the International Conference on Machine Learning. 3276--3285 . Yiping Lu, Aoxiao Zhong, Quanzheng Li, and Bin Dong. 2018. Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations. In Proceedings of the International Conference on Machine Learning. 3276--3285."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2020.3024391"},{"key":"e_1_3_2_2_29_1","volume-title":"Deep learning in medical image analysis and multimodal learning for clinical decision support","author":"Sudre Carole H","unstructured":"Carole H Sudre , Wenqi Li , Tom Vercauteren , Sebastien Ourselin , and M Jorge Cardoso . 2017. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations . In Deep learning in medical image analysis and multimodal learning for clinical decision support . Springer , 240--248. Carole H Sudre,Wenqi Li, Tom Vercauteren, Sebastien Ourselin, and M Jorge Cardoso. 2017. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, 240--248."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3022069"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSSC.2010.5730289"},{"key":"e_1_3_2_2_32_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8509--8518","author":"Zhou Luping","year":"2019","unstructured":"HuanWang, Luping Zhou , and LeiWang. 2019 . Miss detection vs. false alarm: Adversarial learning for small object segmentation in infrared images . In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8509--8518 . HuanWang, Luping Zhou, and LeiWang. 2019. Miss detection vs. false alarm: Adversarial learning for small object segmentation in infrared images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8509--8518."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475317"},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Learning Representations.","author":"Wang Wen","year":"2021","unstructured":"Wen Wang , Yang Cao , Jing Zhang , and Dacheng Tao . 2021 . FP-DETR: Detection Transformer Advanced by Fully Pre-training . In International Conference on Learning Representations. Wen Wang, Yang Cao, Jing Zhang, and Dacheng Tao. 2021. FP-DETR: Detection Transformer Advanced by Fully Pre-training. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413933"},{"key":"e_1_3_2_2_37_1","volume-title":"Vitae: Vision transformer advanced by exploring intrinsic inductive bias. Advances in Neural Information Processing Systems 34","author":"Xu Yufei","year":"2021","unstructured":"Yufei Xu , Qiming Zhang , Jing Zhang , and Dacheng Tao . 2021 . Vitae: Vision transformer advanced by exploring intrinsic inductive bias. Advances in Neural Information Processing Systems 34 (2021). Yufei Xu, Qiming Zhang, Jing Zhang, and Dacheng Tao. 2021. Vitae: Vision transformer advanced by exploring intrinsic inductive bias. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.742"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs10111821"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs11040382"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00095"},{"key":"e_1_3_2_2_43_1","volume-title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond. arXiv preprint arXiv:2202.10108","author":"Zhang Qiming","year":"2022","unstructured":"Qiming Zhang , Yufei Xu , Jing Zhang , and Dacheng Tao . 2022. ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond. arXiv preprint arXiv:2202.10108 ( 2022 ). Qiming Zhang, Yufei Xu, Jing Zhang, and Dacheng Tao. 2022. ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond. arXiv preprint arXiv:2202.10108 (2022)."},{"key":"e_1_3_2_2_44_1","volume-title":"VSA: Learning Varied-Size Window Attention in Vision Transformers. arXiv preprint arXiv:2204.08446","author":"Zhang Qiming","year":"2022","unstructured":"Qiming Zhang , Yufei Xu , Jing Zhang , and Dacheng Tao . 2022 . VSA: Learning Varied-Size Window Attention in Vision Transformers. arXiv preprint arXiv:2204.08446 (2022). Qiming Zhang, Yufei Xu, Jing Zhang, and Dacheng Tao. 2022. VSA: Learning Varied-Size Window Attention in Vision Transformers. arXiv preprint arXiv:2204.08446 (2022)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNNSP.2003.1279357"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3012981"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_2_2_48_1","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations.","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. In International Conference on Learning Representations. Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations."}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547817","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:34Z","timestamp":1750186954000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":48,"alternative-id":["10.1145\/3503161.3547817","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547817","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}