{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T10:07:30Z","timestamp":1774519650081,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"DOI":"10.1007\/s11063-025-11769-3","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T04:11:09Z","timestamp":1751429469000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["EA-DETR: Edge-Aware Detection Transformer for Water Surface Floating Object Identification"],"prefix":"10.1007","volume":"57","author":[{"given":"Jiayi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,2]]},"reference":[{"key":"11769_CR1","unstructured":"Zheng G, Songtao L, Feng W, et al (2021) Yolox: Exceeding yolo series in 2021. Preprint at arXiv:2107.08430"},{"issue":"6","key":"11769_CR2","first-page":"1137","volume":"39","author":"R Shaoqing","year":"2016","unstructured":"Shaoqing R, Kaiming H, Ross G et al (2016) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence 39(6):1137\u20131149","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"11769_CR3","doi-asserted-by":"crossref","unstructured":"Nicolas C, Francisco M, Gabriel S, et al End-to-end object detection with transformers, in European conference on computer vision (Springer, UK, 2020), pp. 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"3","key":"11769_CR4","doi-asserted-by":"publisher","DOI":"10.1049\/csy2.12120","volume":"6","author":"S Huaxiang","year":"2024","unstructured":"Huaxiang S, Yuxuan Y, Zhiwei O et al (2024) Efficient knowledge distillation for hybrid models: A vision transformer-convolutional neural network to convolutional neural network approach for classifying remote sensing images. IET Cyber-Systems and Robotics 6(3):e12120","journal-title":"IET Cyber-Systems and Robotics"},{"issue":"4","key":"11769_CR5","first-page":"56","volume":"10","author":"S Huaxiang","year":"2024","unstructured":"Huaxiang S, Yong Z, Wanbo L et al (2024) Variance consistency learning: enhancing cross-modal knowledge distillation for remote sensing image classification. Annals of Emerging Technologies in Computing (AETiC) 10(4):56\u201376","journal-title":"Annals of Emerging Technologies in Computing (AETiC)"},{"issue":"186","key":"11769_CR6","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1111\/phor.12489","volume":"39","author":"S Huaxiang","year":"2024","unstructured":"Huaxiang S, Yuxuan Y, Zhiwei O et al (2024) Quantitative regularization in robust vision transformer for remote sensing image classification. The Photogrammetric Record 39(186):340\u2013372","journal-title":"The Photogrammetric Record"},{"issue":"1","key":"11769_CR7","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1108\/IJICC-08-2024-0383","volume":"18","author":"S Huaxiang","year":"2025","unstructured":"Huaxiang S, Hanjun X, Wenhui W et al (2025) Qaga-net: enhanced vision transformer-based object detection for remote sensing images. International Journal of Intelligent Computing and Cybernetics 18(1):133\u2013152","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"issue":"1","key":"11769_CR8","doi-asserted-by":"publisher","first-page":"5507","DOI":"10.1038\/s41598-025-89735-1","volume":"15","author":"S Huaxiang","year":"2025","unstructured":"Huaxiang S, Hanglu X, Yingying D et al (2025) Pure data correction enhancing remote sensing image classification with a lightweight ensemble model. Scientific Reports 15(1):5507","journal-title":"Scientific Reports"},{"issue":"189","key":"11769_CR9","doi-asserted-by":"publisher","DOI":"10.1111\/phor.70004","volume":"40","author":"S Huaxiang","year":"2025","unstructured":"Huaxiang S, Junping X, Yunyang W et al (2025) Optimized data distribution learning for enhancing vision transformer-based object detection in remote sensing images. The Photogrammetric Record 40(189):e70004","journal-title":"The Photogrammetric Record"},{"key":"11769_CR10","doi-asserted-by":"crossref","unstructured":"Yian Z, Wenyu L, Shangliang X, et al Detrs beat yolos on real-time object detection, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (IEEE, China, 2024), pp. 16965\u201316974","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"11769_CR11","unstructured":"Hao Z, Feng L, Shilong L et al (2022) Dino: Detr with improved denoising anchor boxes for end-to-end object detection. Preprint at arXiv:2203.03605"},{"key":"11769_CR12","unstructured":"Josh B, Eric K, Eric T et al (2020) Toward transformer-based object detection. Preprint at arXiv:2012.09958"},{"key":"11769_CR13","first-page":"6000","volume":"30","author":"V Ashish","year":"2017","unstructured":"Ashish V, Noam S, Niki P et al (2017) Attention is all you need. Advances in Neural Information Processing Systems 30:6000\u20136010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"11769_CR14","unstructured":"Dongchen H, Ziyi W, Zhuofan X et al (2024) Demystify mamba in vision: A linear attention perspective. Preprint at arXiv:2405.16605"},{"key":"11769_CR15","doi-asserted-by":"crossref","unstructured":"Zhaohui Z, Ping W, Wei L et al Distance-IoU loss: Faster and better learning for bounding box regression, in Proceedings of the AAAI conference on artificial intelligence (AAAI, USA, 2020), pp. 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"11769_CR16","unstructured":"Yuwei C, Jiannan Z, Mengxin J, et al Flow: A dataset and benchmark for floating waste detection in inland waters, in Proceedings of the IEEE\/CVF international conference on computer vision (ICCV, Online, 2021), pp. 10953\u201310962"},{"key":"11769_CR17","doi-asserted-by":"publisher","unstructured":"Fulton MS, Hong J, Sattar J (2020) Trash-icra19: A bounding box labeled dataset of underwater trash. Figshare https:\/\/doi.org\/10.13020\/x0qn-y082","DOI":"10.13020\/x0qn-y082"},{"key":"11769_CR18","doi-asserted-by":"crossref","unstructured":"L.S. Richard, F.D. Steven, M.A. H., Modeling floating objects at river structures. Journal of Hydraulic Engineering 135(5), 403\u2013414 (2009)","DOI":"10.1061\/(ASCE)0733-9429(2009)135:5(403)"},{"key":"11769_CR19","unstructured":"Bohan Z, Jing L, Zizheng P et al (2023) A survey on efficient training of transformers. Preprint at arXiv:2302.01107"},{"key":"11769_CR20","unstructured":"Nikita K, \u0141ukasz K, Anselm L (2020) Reformer: The efficient transformer. Preprint at arXiv:2001.04451"},{"key":"11769_CR21","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"R Aurko","year":"2021","unstructured":"Aurko R, Mohammad S, Ashish V et al (2021) Efficient content-based sparse attention with routing transformers. Transactions of the Association for Computational Linguistics 9:53\u201368","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"11769_CR22","unstructured":"Yi T, Dara B, Liu Y et al Sparse sinkhorn attention, in International Conference on Machine Learning (PMLR, Korea, 2020), pp. 9438\u20139447"},{"key":"11769_CR23","unstructured":"Sinong W, Belinda ZL, Madian K et al (2020) Linformer: Self-attention with linear complexity. Preprint at arXiv:2006.04768"},{"key":"11769_CR24","unstructured":"Krzysztof C, Valerii L, David D et al (2020) Masked language modeling for proteins via linearly scalable long-context transformers. Preprint at arXiv:2006.03555"},{"key":"11769_CR25","unstructured":"Rewon C, Scott G, Alec R et al (2019) Generating long sequences with sparse transformers. Preprint at arXiv:1904.10509"},{"key":"11769_CR26","doi-asserted-by":"crossref","unstructured":"Zilong H, Xinggang W, Yunchao W et al Ccnet: Criss-cross attention for semantic segmentation, in Proceedings of the IEEE\/CVF international conference on computer vision (ICCV, Korea, 2019), pp. 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"11769_CR27","unstructured":"Jonathan H, Nal K, Dirk W et al (2019) Axial attention in multidimensional transformers. Preprint at arXiv:1912.12180"},{"key":"11769_CR28","unstructured":"Joshua A, Santiago O, Chris A et al (2020) Encoding long and structured data in transformers. Preprint at arXiv:2004.08483"},{"key":"11769_CR29","first-page":"17283","volume":"33","author":"M Zaheer","year":"2020","unstructured":"Zaheer M, Guruganesh G, Dubey KA et al (2020) Big bird: Transformers for longer sequences. Advances in neural information processing systems 33:17283\u201317297","journal-title":"Advances in neural information processing systems"},{"key":"11769_CR30","unstructured":"Jiezhong Q, Hao M, Omer L et al (2019) Blockwise self-attention for long document understanding. Preprint at arXiv:1911.02972"},{"key":"11769_CR31","unstructured":"Niki P, Ashish V, Jakob U et al Image transformer, in International conference on machine learning (PMLR, France, 2018), pp. 4055\u20134064"},{"key":"11769_CR32","unstructured":"Peter JL, Mohammad S, Etienne P et al (2018) Generating wikipedia by summarizing long sequences. Preprint at arXiv:1801.10198"},{"key":"11769_CR33","doi-asserted-by":"crossref","unstructured":"Huiyu W, Yukun Z, Bradley G et al Axial-deeplab: Stand-alone axial-attention for panoptic segmentation, in European conference on computer vision (Springer, Online, 2020), pp. 108\u2013126","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"11769_CR34","unstructured":"Zhiqi L, Wenhai W, Enze X et al Panoptic segformer: Delving deeper into panoptic segmentation with transformers, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR, USA, 2022), pp. 1280\u20131289"},{"key":"11769_CR35","unstructured":"Felix W, Angela F, Alexei B et al (2019) Pay less attention with lightweight and dynamic convolutions. Preprint at arXiv:1901.10430"},{"key":"11769_CR36","unstructured":"Albert G, Tri D (2023) Mamba: Linear-time sequence modeling with selective state spaces. Preprint at arXiv:2312.00752"},{"key":"11769_CR37","unstructured":"Jie H, Li S, Samuel A et al Squeeze-and-excitation networks, in Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR, USA, 2018), pp. 7132\u20137141"},{"issue":"4","key":"11769_CR38","first-page":"537","volume":"8","author":"D Ziou","year":"1998","unstructured":"Ziou D, Tabbone S (1998) Edge detection techniques-an overview. Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications 8(4):537\u2013559","journal-title":"Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications"},{"key":"11769_CR39","doi-asserted-by":"crossref","unstructured":"A. R., The max roberts operator is a hueckel-type edge detector. IEEE Transactions on Pattern Analysis and Machine Intelligence (1), 101\u2013103 (1981)","DOI":"10.1109\/TPAMI.1981.4767056"},{"key":"11769_CR40","doi-asserted-by":"crossref","unstructured":"Lei Y, Xiaoyu W, Dewei Z et al An improved Prewitt algorithm for edge detection based on noised image, in 2011 4th International congress on image and signal processing (IEEE, China, 2011), pp. 1197\u20131200","DOI":"10.1109\/CISP.2011.6100495"},{"issue":"2","key":"11769_CR41","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/4.996","volume":"23","author":"N Kanopoulos","year":"1988","unstructured":"Kanopoulos N, Vasanthavada N, Baker RL (1988) Design of an image edge detection filter using the sobel operator. IEEE Journal of solid-state circuits 23(2):358\u2013367","journal-title":"IEEE Journal of solid-state circuits"},{"issue":"5","key":"11769_CR42","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1109\/TPAMI.2007.1027","volume":"29","author":"X Wang","year":"2007","unstructured":"Wang X (2007) Laplacian operator-based edge detectors. IEEE transactions on pattern analysis and machine intelligence 29(5):886\u2013890","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"11769_CR43","doi-asserted-by":"crossref","unstructured":"Caixia D, Guibin W, XinRui Y Image edge detection algorithm based on improved canny operator, in 2013 International Conference on Wavelet Analysis and Pattern Recognition (IEEE, China, 2013), pp. 168\u2013172","DOI":"10.1109\/ICWAPR.2013.6599311"},{"issue":"3","key":"11769_CR44","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1080\/20964471.2019.1657720","volume":"3","author":"S Jia","year":"2019","unstructured":"Jia S, Shaohua G, Yunqiang Z et al (2019) A survey of remote sensing image classification based on cnns. Big earth data 3(3):232\u2013254","journal-title":"Big earth data"},{"key":"11769_CR45","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3389\/fnins.2019.00095","volume":"13","author":"S Abhronil","year":"2019","unstructured":"Abhronil S, Yuting Y, Robert W et al (2019) Going deeper in spiking neural networks: Vgg and residual architectures. Frontiers in neuroscience 13:95","journal-title":"Frontiers in neuroscience"},{"key":"11769_CR46","doi-asserted-by":"crossref","unstructured":"Sanghyun W, Jongchan P, JoonYoung L et al Cbam: Convolutional block attention module, in Proceedings of the European conference on computer vision (ECCV, Germany, 2018), pp. 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11769_CR47","unstructured":"Yulun Z, Kunpeng L, Kai L et al Image super-resolution using very deep residual channel attention networks, in Proceedings of the European conference on computer vision (ECCV, Germany, 2018), pp. 286\u2013301"},{"key":"11769_CR48","doi-asserted-by":"crossref","unstructured":"Hamid R, Nathan T, JunYoung G et al Generalized intersection over union: A metric and a loss for bounding box regression, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR, USA, 2019), pp. 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"11769_CR49","doi-asserted-by":"crossref","unstructured":"Zhaohui Z, Ping W, Wei L et al Distance-IoU loss: Faster and better learning for bounding box regression, in Proceedings of the AAAI conference on artificial intelligence (AAAI, USA, 2020), pp. 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"11769_CR50","doi-asserted-by":"crossref","unstructured":"Usha R, Vamsidhar Y (2020) Binary cross entropy with deep learning technique for image classification. Int. J. Adv. Trends Comput. Sci. Eng 9(10)","DOI":"10.30534\/ijatcse\/2020\/175942020"},{"key":"11769_CR51","doi-asserted-by":"crossref","unstructured":"Carole HS, Wenqi L, Tom V et al Generalised dice overlap as a deep learning loss function for highly unbalanced segmentationsn, in DLMIA (MICCAI, Canada, 2017), pp. 240\u2013248","DOI":"10.1007\/978-3-319-67558-9_28"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11769-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-025-11769-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11769-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T00:28:30Z","timestamp":1757204910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-025-11769-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["11769"],"URL":"https:\/\/doi.org\/10.1007\/s11063-025-11769-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5606468\/v1","asserted-by":"object"}]},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,2]]},"assertion":[{"value":"10 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The code used in this study is not publicly available. However, it can be made available upon reasonable request to the corresponding author.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"62"}}