{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:06:32Z","timestamp":1757617592573,"version":"3.44.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Natural Science Foundation of China under Grant","award":["62363025"],"award-info":[{"award-number":["62363025"]}]},{"name":"Education Industry Support Plan Project of Gansu Provincial Department","award":["2023CYZC-26"],"award-info":[{"award-number":["2023CYZC-26"]}]},{"name":"Key R&D plan of Science and Technology Plan of Gansu Province - Social Development Field Project","award":["23YFFA0064"],"award-info":[{"award-number":["23YFFA0064"]}]},{"DOI":"10.13039\/501100009590","name":"Gansu Education Department","doi-asserted-by":"publisher","award":["2023CXZX-468"],"award-info":[{"award-number":["2023CXZX-468"]}],"id":[{"id":"10.13039\/501100009590","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s10489-024-05850-y","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:56:39Z","timestamp":1742954199000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision-based attention deep q-network with prior-based knowledge"],"prefix":"10.1007","volume":"55","author":[{"given":"Jialin","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4627-6112","authenticated-orcid":false,"given":"Ce","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kailun","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shutian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangfei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyun","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"5850_CR1","doi-asserted-by":"crossref","unstructured":"Kim K, Ha J, Kim Y (2022) Self-predictive dynamics for generalization of vision-based reinforcement learning. In: Proceedings of the Thirty-First international joint conference on artificial intelligence, pp 3150\u20133156","DOI":"10.24963\/ijcai.2022\/437"},{"key":"5850_CR2","doi-asserted-by":"crossref","unstructured":"de Morais GAP, Marcos LB, Bueno JNAD, de Resende NF, Terra MH, Grassi V Jr (2020) Vision-based robust control framework based on deep reinforcement learning applied to autonomous ground vehicles. Control Eng Pract 104:104630","DOI":"10.1016\/j.conengprac.2020.104630"},{"issue":"3\u20134","key":"5850_CR3","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8(3\u20134):279\u2013292","journal-title":"Mach Learn"},{"issue":"7540","key":"5850_CR4","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"5850_CR5","doi-asserted-by":"crossref","unstructured":"Yuan J, Zhu A, Xu Q, Wattanachote K, Gong Y (2023) Ctif-net: A cnn-transformer iterative fusion network for salient object detection. IEEE Trans Circuits Syst Video Technol","DOI":"10.1109\/TCSVT.2023.3321190"},{"key":"5850_CR6","doi-asserted-by":"crossref","unstructured":"Yan R, Yan L, Geng G, Cao Y, Zhou P, Meng Y (2024) Asnet: Adaptive semantic network based on transformer-cnn for salient object detection in optical remote sensing images. IEEE Trans Geosci Remote Sens","DOI":"10.1109\/TGRS.2024.3362836"},{"key":"5850_CR7","first-page":"1","volume":"61","author":"L Gao","year":"2023","unstructured":"Gao L, Liu B, Fu P, Xu M (2023) Adaptive spatial tokenization transformer for salient object detection in optical remote sensing images. IEEE Trans Geosci Remote Sens 61:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"5","key":"5850_CR8","first-page":"2712","volume":"44","author":"WJ Shi","year":"2022","unstructured":"Shi WJ, Huang G, Song SJ (2022) Self-supervised discovering of interpretable features for reinforcement learning. IEEE Trans Pattern Anal Mach Intell 44(5):2712\u20132724","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5850_CR9","doi-asserted-by":"crossref","unstructured":"Huang W, Zhang C, Wu J, He X, Zhang J, Lv C (2023) Sampling efficient deep reinforcement learning through preference-guided stochastic exploration. IEEE Trans Neural Netw Learn Syst 1\u201312","DOI":"10.1109\/TNNLS.2023.3317628"},{"issue":"3","key":"5850_CR10","first-page":"3421","volume":"45","author":"JH Zhu","year":"2023","unstructured":"Zhu JH, Xia YC, Wu LJ (2023) Masked contrastive representation learning for reinforcement learning. IEEE Trans Pattern Anal Mach Intell 45(3):3421\u20133433","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5850_CR11","doi-asserted-by":"crossref","unstructured":"Shang J, Kahatapitiya K, Li X (2022) Starformer: Transformer with state-action-reward representations for visual reinforcement learning. In: European conference on computer vision, pp 462\u2013479","DOI":"10.1007\/978-3-031-19842-7_27"},{"key":"5850_CR12","doi-asserted-by":"crossref","unstructured":"Tang J, Mihailovic A, Aghvami H (2022) Constructing a drl decision making scheme for multi-path routing in all-ip access network. In: IEEE Global communications conference, IEEE, pp 3623\u20133628","DOI":"10.1109\/GLOBECOM48099.2022.10000597"},{"key":"5850_CR13","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.neunet.2023.01.025","volume":"161","author":"JW Xing","year":"2023","unstructured":"Xing JW, Nagata T, Zou XY (2023) Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization. Neural Netw 161:228\u2013241","journal-title":"Neural Netw"},{"key":"5850_CR14","doi-asserted-by":"crossref","unstructured":"Pham NT, Dang DNM, Nguyen ND, Nguyen TT, Nguyen H, Manavalan B, Lim CP, Nguyen SD (2023) Hybrid data augmentation and deep attention-based dilated convolutional-recurrent neural networks for speech emotion recognition. Expert Syst Appl 230:120608","DOI":"10.1016\/j.eswa.2023.120608"},{"key":"5850_CR15","doi-asserted-by":"crossref","unstructured":"Fathnejat H, Ahmadi-Nedushan B, Hosseininejad S, Noori M, Altabey WA (2023) A data-driven structural damage identification approach using deep convolutional-attention-recurrent neural architecture under temperature variations. Eng Struct 276:115311","DOI":"10.1016\/j.engstruct.2022.115311"},{"issue":"3","key":"5850_CR16","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/LRA.2023.3243526","volume":"8","author":"AY Yasutomi","year":"2023","unstructured":"Yasutomi AY, Ichiwara H, Ito H, Mori H, Ogata T (2023) Visual spatial attention and proprioceptive data-driven reinforcement learning for robust peg-in-hole task under variable conditions. IEEE Robot Automat Lett 8(3):1834\u20131841","journal-title":"IEEE Robot Automat Lett"},{"issue":"9","key":"5850_CR17","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1038\/s43588-023-00503-5","volume":"3","author":"Y Zheng","year":"2023","unstructured":"Zheng Y, Lin Y, Zhao L, Wu T, Jin D, Li Y (2023) Spatial planning of urban communities via deep reinforcement learning. Nat Comput Sci 3(9):748\u2013762","journal-title":"Nat Comput Sci"},{"issue":"5","key":"5850_CR18","doi-asserted-by":"publisher","first-page":"3441","DOI":"10.1007\/s00371-023-03044-0","volume":"40","author":"Y Liu","year":"2024","unstructured":"Liu Y, Yang D, Zhang F, Xie Q, Zhang C (2024) Deep recurrent residual channel attention network for single image super-resolution. Visual Comput 40(5):3441\u20133456","journal-title":"Visual Comput"},{"key":"5850_CR19","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.neunet.2023.03.017","volume":"163","author":"H Sun","year":"2023","unstructured":"Sun H, Li B, Dan Z, Hu W, Du B, Yang W, Wan J (2023) Multi-level feature interaction and efficient non-local information enhanced channel attention for image dehazing. Neural Netw 163:10\u201327","journal-title":"Neural Netw"},{"key":"5850_CR20","doi-asserted-by":"crossref","unstructured":"Hou Y-E, Yang K, Dang L, Liu Y (2023) Contextual spatial-channel attention network for remote sensing scene classification. IEEE Geosci Remote Sens Lett","DOI":"10.1109\/LGRS.2023.3304645"},{"key":"5850_CR21","doi-asserted-by":"crossref","unstructured":"Pan X, Ye T, Xia Z, Song S, Huang G (2023) Slide-transformer: Hierarchical vision transformer with local self-attention. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 2082\u20132091","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"5850_CR22","doi-asserted-by":"publisher","first-page":"1178450","DOI":"10.3389\/fcomp.2023.1178450","volume":"5","author":"P Mehrani","year":"2023","unstructured":"Mehrani P, Tsotsos JK (2023) Self-attention in vision transformers performs perceptual grouping, not attention. Front Comput Sci 5:1178450","journal-title":"Front Comput Sci"},{"key":"5850_CR23","doi-asserted-by":"crossref","unstructured":"Bilal A, Liu X, Shafiq M, Ahmed Z, Long H (2024) Nimeq-sacnet: A novel self-attention precision medicine model for vision-threatening diabetic retinopathy using image data. Comput Biol Med 171:108099","DOI":"10.1016\/j.compbiomed.2024.108099"},{"key":"5850_CR24","unstructured":"Sorokin I, Seleznev A, Pavlov M (2015) Deep attention recurrent q-network. arXiv preprint arXiv:1512.01693, 1\u20137"},{"key":"5850_CR25","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang X, Chang Y (2022) Towards explainable reinforcement learning using scoring mechanism augmented agents. In: Knowledge science, engineering and management, proceedings, Part II, pp 547\u2013558","DOI":"10.1007\/978-3-031-10986-7_44"},{"key":"5850_CR26","doi-asserted-by":"crossref","unstructured":"Ma X, Zhang S, Wang Y, Li R, Chen X, Yu D (2023) Ascam-former: Blind image quality assessment based on adaptive spatial & channel attention merging transformer and image to patch weights sharing. Expert Syst Appl 215:119268","DOI":"10.1016\/j.eswa.2022.119268"},{"key":"5850_CR27","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/j.isatra.2022.06.035","volume":"133","author":"S Zhang","year":"2023","unstructured":"Zhang S, Liu Z, Chen Y, Jin Y, Bai G (2023) Selective kernel convolution deep residual network based on channel-spatial attention mechanism and feature fusion for mechanical fault diagnosis. ISA Trans 133:369\u2013383","journal-title":"ISA Trans"},{"key":"5850_CR28","doi-asserted-by":"crossref","unstructured":"Wang Y, Shi K, Lu C, Liu Y, Zhang M, Qu H (2023) Spatial-temporal self-attention for asynchronous spiking neural networks. In: Thirty-Second international joint conference on artificial intelligence, vol. 8, pp 3085\u20133093","DOI":"10.24963\/ijcai.2023\/344"},{"key":"5850_CR29","doi-asserted-by":"crossref","unstructured":"Zhao Y, Luo C, Tang C, Chen D, Codella N, Zha Z-J (2023) Streaming video model. In: IEEE\/CVF Conference on computer vision and pattern recognition, pp 14602\u201314612","DOI":"10.1109\/CVPR52729.2023.01403"},{"key":"5850_CR30","doi-asserted-by":"crossref","unstructured":"Feng W, Xu N, Zhang T, Zhang Y, Wu F (2024) Enhancing cross-task transferability of adversarial examples via spatial and channel attention. IEEE Trans Multimed","DOI":"10.1109\/TMM.2024.3349925"},{"key":"5850_CR31","doi-asserted-by":"crossref","unstructured":"Hassanin M, Anwar S, Radwan I, Khan FS, Mian A (2024) Visual attention methods in deep learning: An in-depth survey. Inf Fusion 108:102417","DOI":"10.1016\/j.inffus.2024.102417"},{"issue":"1","key":"5850_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TG.2019.2896986","volume":"12","author":"N Justesen","year":"2020","unstructured":"Justesen N, Bontrager P, Togelius J, Risi S (2020) Deep learning for video game playing. IEEE Trans Games 12(1):1\u201320","journal-title":"IEEE Trans Games"},{"key":"5850_CR33","unstructured":"Hasselt Hv, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Thirtieth AAAI conference on artificial intelligence, pp 2094\u20132100"},{"key":"5850_CR34","doi-asserted-by":"crossref","unstructured":"Hessel M, Modayil J, Hasselt H, Schaul T, Ostrovski G, Dabney W, Horgan D, Piot B, Azar M, Silver D (2018) Rainbow: Combining improvements in deep reinforcement learning. In: Thirty-Second AAAI Conference on artificial intelligence and thirtieth innovative applications of artificial intelligence conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, pp 11796\u201311804","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"5850_CR35","unstructured":"Yarats D, Kostrikov I, Fergus R (2021) Image augmentation is all you need: Regularizing deep reinforcement learning from pixels. In: International conference on learning representations, pp 1\u201322"},{"key":"5850_CR36","unstructured":"Schwarzer M, Anand A, Goel R, Hjelm RD, Courville A, Bachman P (2021) Data-efficient reinforcement learning with self-predictive representations. In: International conference on learning representations, pp 1\u201318"},{"key":"5850_CR37","doi-asserted-by":"crossref","unstructured":"Hou X, Zhang L (2007) Saliency detection: A spectral residual approach. In: IEEE Conference on computer vision and pattern recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383267"},{"key":"5850_CR38","unstructured":"Li Y, Sycara K, Iyer R (2017) Object-sensitive deep reinforcement learning. In: Benzm\u00fcller C, Lisetti C, Theobald M (eds.) GCAI 2017. 3rd Global conference on artificial intelligence, vol. 50, pp 20\u201335. EasyChair, Miami, USA. 18-22"},{"key":"5850_CR39","volume-title":"Advances in Neural Information Processing Systems","author":"V Goel","year":"2018","unstructured":"Goel V, Weng J, Poupart P (2018) Unsupervised video object segmentation for deep reinforcement learning. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in Neural Information Processing Systems, vol 31. Curran Associates Inc, Montr\u00e9al, Canada"},{"key":"5850_CR40","unstructured":"Vaswani A, Shazeer N, Parmar N (2017) Attention is all you need. In: International conference on neural information processing systems, pp 6000\u20136010"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05850-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05850-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05850-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:43:15Z","timestamp":1757148195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05850-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["5850"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05850-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"7 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 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":"The authors have no relevant financial or nonfinancial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"565"}}