{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T04:03:34Z","timestamp":1743480214681,"version":"3.40.3"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T00:00:00Z","timestamp":1740700800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T00:00:00Z","timestamp":1740700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82272130"],"award-info":[{"award-number":["82272130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China Key Program","award":["U22A20103"],"award-info":[{"award-number":["U22A20103"]}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["2023Z019072001"],"award-info":[{"award-number":["2023Z019072001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012130","name":"Chinese Aeronautical Establishment","doi-asserted-by":"publisher","award":["2024Z074072001"],"award-info":[{"award-number":["2024Z074072001"]}],"id":[{"id":"10.13039\/501100012130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s40747-025-01817-9","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T02:27:47Z","timestamp":1740709667000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KeyBoxGAN: enhancing 2D object detection through annotated and editable image synthesis"],"prefix":"10.1007","volume":"11","author":[{"given":"Yashuo","family":"Bai","sequence":"first","affiliation":[]},{"given":"Yong","family":"Song","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Xu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ya","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Yizhao","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Jinxiang","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,28]]},"reference":[{"issue":"Jun. 7","key":"1817_CR1","first-page":"1","volume":"293","author":"H Nie","year":"2024","unstructured":"Nie H, Lu S (2024) Persistverify: federated model ownership verification with spatial attention and boundary sampling. Knowl-Based Syst 293(Jun. 7):1\u20131114","journal-title":"Knowl-Based Syst"},{"key":"1817_CR2","doi-asserted-by":"crossref","unstructured":"Nie H, Lu S, Wang M, Xiao J, Lu Z, Yi Z (2024) Verichroma: ownership verification forfederated models viargb filters. In: European Conference on Parallel Processing","DOI":"10.1007\/978-3-031-69766-1_23"},{"key":"1817_CR3","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"1817_CR4","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inform Process Syst 28"},{"key":"1817_CR5","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"11","key":"1817_CR6","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: The kitti dataset. Int J Robot Res 32(11):1231\u20131237","journal-title":"Int J Robot Res"},{"key":"1817_CR7","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"1817_CR8","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.neucom.2022.06.104","volume":"503","author":"X Zhao","year":"2022","unstructured":"Zhao X, Wang G, He Z, Jiang H (2022) A survey of moving object detection methods: a practical perspective. Neurocomputing 503:28\u201348","journal-title":"Neurocomputing"},{"issue":"6","key":"1817_CR9","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1109\/TITS.2020.2993926","volume":"22","author":"L Chen","year":"2021","unstructured":"Chen L, Lin S, Lu X, Cao D, Wu H, Guo C, Liu C, Wang F-Y (2021) Deep neural network based vehicle and pedestrian detection for autonomous driving: a survey. IEEE Trans Intell Trans Syst 22(6):3234\u20133246","journal-title":"IEEE Trans Intell Trans Syst"},{"key":"1817_CR10","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Yeh I-H, Liao H-YM (2024) Yolov9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"1817_CR11","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Ieee","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"1817_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int J Comput Vis"},{"key":"1817_CR13","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1817_CR14","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"issue":"1","key":"1817_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):1\u201348","journal-title":"J Big Data"},{"key":"1817_CR16","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. Advances in neural information processing systems 27"},{"key":"1817_CR17","doi-asserted-by":"crossref","unstructured":"Durgadevi M, et\u00a0al. (2021) Generative adversarial network (gan): a general review on different variants of gan and applications. In: 2021 6th International Conference on Communication and Electronics Systems (ICCES), pp. 1\u20138. IEEE","DOI":"10.1109\/ICCES51350.2021.9489160"},{"issue":"11","key":"1817_CR18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132323","journal-title":"Proc IEEE"},{"key":"1817_CR19","unstructured":"Krizhevsky A, Hinton G, et al. (2009) Learning multiple layers of features from tiny images"},{"key":"1817_CR20","unstructured":"Yu F, Seff A, Zhang Y, Song S, Funkhouser T, Xiao J (2015) Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365"},{"key":"1817_CR21","doi-asserted-by":"crossref","unstructured":"Liu Z, Luo P, Wang X, Tang X (2015) Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730\u20133738","DOI":"10.1109\/ICCV.2015.425"},{"key":"1817_CR22","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410","DOI":"10.1109\/CVPR.2019.00453"},{"key":"1817_CR23","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J, Aila T (2020) Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"1817_CR24","doi-asserted-by":"crossref","unstructured":"Park T, Liu M-Y, Wang T-C, Zhu J-Y (2019) Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346","DOI":"10.1109\/CVPR.2019.00244"},{"key":"1817_CR25","unstructured":"Brock A, Donahue J, Simonyan K (2018) Large scale gan training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096"},{"key":"1817_CR26","unstructured":"Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X (2016) Improved techniques for training gans. Advances in neural information processing systems 29"},{"key":"1817_CR27","unstructured":"Dosovitskiy A, Ros G, Codevilla F, Lopez A, Koltun V (2017) Carla: An open urban driving simulator. In: Proceedings of the 1st Annual Conference on Robot Learning. Proceedings of Machine Learning Research, vol. 78, pp. 1\u201316. PMLR"},{"key":"1817_CR28","doi-asserted-by":"crossref","unstructured":"Mahalanobis PC (2018) On the generalized distance in statistics. Sankhy\u0101: The Indian Journal of Statistics, Series A (2008-) 80:1\u20137","DOI":"10.1007\/s13171-019-00164-5"},{"key":"1817_CR29","doi-asserted-by":"crossref","unstructured":"Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, pp. 13001\u201313008","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"1817_CR30","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"1817_CR31","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Mane D, Vasudevan V, Le QV (2019) Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 113\u2013123","DOI":"10.1109\/CVPR.2019.00020"},{"key":"1817_CR32","unstructured":"Hendrycks D, Mu N, Cubuk ED, Zoph B, Gilmer J, Lakshminarayanan B (2019) Augmix: a simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781"},{"key":"1817_CR33","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inform Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inform Process Syst"},{"key":"1817_CR34","unstructured":"Nichol AQ, Dhariwal P (2021) Improved denoising diffusion probabilistic models. In: International conference on machine learning, pp. 8162\u20138171. PMLR"},{"key":"1817_CR35","unstructured":"Song J, Meng C, Ermon S (2020) Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502"},{"key":"1817_CR36","unstructured":"Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434"},{"key":"1817_CR37","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Pfister T, Tuzel O, Susskind J, Wang W, Webb R (2017) Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2107\u20132116","DOI":"10.1109\/CVPR.2017.241"},{"issue":"10","key":"1817_CR38","doi-asserted-by":"publisher","first-page":"3037","DOI":"10.1109\/TCSVT.2018.2873599","volume":"29","author":"Z Zheng","year":"2018","unstructured":"Zheng Z, Zheng L, Yang Y (2018) Pedestrian alignment network for large-scale person re-identification. IEEE Trans Circ Syst Video Technol 29(10):3037\u20133045","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"1817_CR39","doi-asserted-by":"publisher","first-page":"41","DOI":"10.5194\/isprs-archives-XLII-2-W4-41-2017","volume":"42","author":"V Kniaz","year":"2017","unstructured":"Kniaz V, Gorbatsevich V, Mizginov V (2017) Thermalnet: a deep convolutional network for synthetic thermal image generation. Int Arch Photogrammetry Remote Sens Spatial Informa Sci 42:41\u201345","journal-title":"Int Arch Photogrammetry Remote Sens Spatial Informa Sci"},{"issue":"11","key":"1817_CR40","first-page":"3305","volume":"38","author":"W Chen","year":"2018","unstructured":"Chen W, Guan Z, Chen Y (2018) Data augmentation method based on conditional generative adversarial net model. J Comput Appl 38(11):3305","journal-title":"J Comput Appl"},{"key":"1817_CR41","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1016\/j.neucom.2021.11.080","volume":"488","author":"Y Wei","year":"2022","unstructured":"Wei Y, Xu S, Kang B, Hoque S (2022) Generating training images with different angles by gan for improving grocery product image recognition. Neurocomputing 488:694\u2013705","journal-title":"Neurocomputing"},{"key":"1817_CR42","doi-asserted-by":"crossref","unstructured":"Zhu K, Wang Y, Yang H, Huang D, Chen L (2020) Intensity enhancement via gan for multimodal facial expression recognition. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 1346\u20131350. IEEE","DOI":"10.1109\/ICIP40778.2020.9190705"},{"key":"1817_CR43","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"1817_CR44","doi-asserted-by":"crossref","unstructured":"Choi Y, Choi M, Kim M, Ha J-W, Kim S, Choo J (2018) Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789\u20138797","DOI":"10.1109\/CVPR.2018.00916"},{"key":"1817_CR45","doi-asserted-by":"crossref","unstructured":"Choi Y, Uh Y, Yoo J, Ha J-W (2020) Stargan v2: Diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8188\u20138197","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"1817_CR46","first-page":"12104","volume":"33","author":"T Karras","year":"2020","unstructured":"Karras T, Aittala M, Hellsten J, Laine S, Lehtinen J, Aila T (2020) Training generative adversarial networks with limited data. Adv Neural Inform Process Syst 33:12104\u201312114","journal-title":"Adv Neural Inform Process Syst"},{"key":"1817_CR47","unstructured":"Jahanian A, Chai L, Isola P (2019) On the \u201csteerability\u201d of generative adversarial networks. arXiv preprint arXiv:1907.07171"},{"key":"1817_CR48","doi-asserted-by":"crossref","unstructured":"Zhu J, Shen Y, Zhao D, Zhou B (2020) In-domain gan inversion for real image editing. In: European Conference on Computer Vision, pp. 592\u2013608. Springer","DOI":"10.1007\/978-3-030-58520-4_35"},{"issue":"4","key":"1817_CR49","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","volume":"44","author":"Y Shen","year":"2020","unstructured":"Shen Y, Yang C, Tang X, Zhou B (2020) Interfacegan: interpreting the disentangled face representation learned by gans. IEEE Trans Pattern Anal Mach Intell 44(4):2004\u20132018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1817_CR50","first-page":"16331","volume":"34","author":"H Ling","year":"2021","unstructured":"Ling H, Kreis K, Li D, Kim SW, Torralba A, Fidler S (2021) Editgan: high-precision semantic image editing. Adv Neural Inform Process Syst 34:16331\u201316345","journal-title":"Adv Neural Inform Process Syst"},{"key":"1817_CR51","doi-asserted-by":"crossref","unstructured":"Pan X, Tewari A, Leimk\u00fchler T, Liu L, Meka A, Theobalt C (2023) Drag your gan: Interactive point-based manipulation on the generative image manifold. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311","DOI":"10.1145\/3588432.3591500"},{"key":"1817_CR52","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1817_CR53","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et\u00a0al. (2021) Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR"},{"key":"1817_CR54","unstructured":"Ramesh A, Dhariwal P, Nichol A, Chu C, Chen M (2022) Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1(2):3"},{"key":"1817_CR55","unstructured":"Midjourney.com. https:\/\/www.midjourney.com\/. Accessed: 2022"},{"key":"1817_CR56","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91\u2013110","journal-title":"Int J Comput Vis"},{"issue":"9","key":"1817_CR57","doi-asserted-by":"publisher","first-page":"13586","DOI":"10.1111\/exsy.13586","volume":"41","author":"E Hassan","year":"2024","unstructured":"Hassan E, Hossain MS, Elmuogy S, Ghoneim A, AlMutib K, Saber A (2024) Ultimate pose estimation: a comparative study. Expert Syst 41(9):13586","journal-title":"Expert Syst"},{"key":"1817_CR58","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14, pp. 483\u2013499. Springer","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1817_CR59","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"1817_CR60","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inform Process Syst 30"},{"key":"1817_CR61","doi-asserted-by":"crossref","unstructured":"Yang S, Quan Z, Nie M, Yang W (2021) Transpose: Keypoint localization via transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11802\u201311812","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"1817_CR62","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1817_CR63","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1817_CR64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3230846","volume":"60","author":"X He","year":"2022","unstructured":"He X, Zhou Y, Zhao J, Zhang D, Yao R, Xue Y (2022) Swin transformer embedding unet for remote sensing image semantic segmentation. IEEE Trans Geosci Remote Sens 60:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1817_CR65","doi-asserted-by":"crossref","unstructured":"Li X, Wang H, Liu X, Lu H (2022) Swinnet: Swin transformer drives edge-aware rgb-d and rgb-t salient object detection. IEEE Transactions on Image Processing","DOI":"10.3390\/s23218802"},{"key":"1817_CR66","doi-asserted-by":"crossref","unstructured":"Wu Y, Lim J, Yang M-H (2013) Online object tracking: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411\u20132418","DOI":"10.1109\/CVPR.2013.312"},{"key":"1817_CR67","doi-asserted-by":"crossref","unstructured":"Fan H, Lin L, Yang F, Chu P, Deng G, Yu S, Bai H, Xu Y, Liao C, Ling H (2019) Lasot: A high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383","DOI":"10.1109\/CVPR.2019.00552"},{"key":"1817_CR68","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inform Process Syst 30"},{"key":"1817_CR69","unstructured":"Wang Z, Simoncelli EP, Bovik AC (2003) Multiscale structural similarity for image quality assessment. In: The thrity-seventh asilomar conference on signals, systems & computers, 2003, 2: 1398\u20131402. IEEE"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01817-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01817-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01817-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T09:34:11Z","timestamp":1743413651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01817-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,28]]},"references-count":69,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1817"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01817-9","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2025,2,28]]},"assertion":[{"value":"17 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author declares no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The current research has been done on publicly available datasets. All data that support the findings of this paper are included in this manuscript.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data availability"}},{"value":"Not applicable.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"Not applicable.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"186"}}