{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:48:40Z","timestamp":1761130120231,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62266043"],"award-info":[{"award-number":["62266043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China,China","doi-asserted-by":"crossref","award":["U1803261"],"award-info":[{"award-number":["U1803261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science and Technology Major Project, China","award":["95-Y50G34-9001-22\/23"],"award-info":[{"award-number":["95-Y50G34-9001-22\/23"]}]},{"name":"Autonomous Region Science and Technology Department International Cooperation Project, China","award":["2020E01023"],"award-info":[{"award-number":["2020E01023"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s11227-023-05744-9","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:01:58Z","timestamp":1699898518000},"page":"8038-8059","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ST-YOLOX: a lightweight and accurate object detection network based on Swin Transformer"],"prefix":"10.1007","volume":"80","author":[{"given":"Jingjing","family":"Han","sequence":"first","affiliation":[]},{"given":"Guangqi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hongyang","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Weijun","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Yurong","family":"Qian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"5744_CR1","doi-asserted-by":"publisher","first-page":"6696","DOI":"10.1007\/s11227-021-04140-5","volume":"78","author":"T Liu","year":"2022","unstructured":"Liu T, Wang S, Liu Y et al (2022) A lightweight neural network framework using linear grouped convolution for human activity recognition on mobile devices. J Supercomput 78:6696\u20136716","journal-title":"J Supercomput"},{"issue":"3","key":"5744_CR2","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1109\/TMC.2020.3019652","volume":"21","author":"K Ali","year":"2020","unstructured":"Ali K, Liu AX, Chai E et al (2020) Monitoring browsing behavior of customers in retail stores via rfid imaging. IEEE Trans Mob Comput 21(3):1034\u20131048","journal-title":"IEEE Trans Mob Comput"},{"key":"5744_CR3","doi-asserted-by":"crossref","unstructured":"Allegra D, Litrico M, Spatafora MAN, et\u00a0al (2021) Exploiting egocentric vision on shopping cart for out-of-stock detection in retail environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 1735\u20131740","DOI":"10.1109\/ICCVW54120.2021.00199"},{"issue":"1","key":"5744_CR4","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/s10489-022-03459-7","volume":"53","author":"H Wei","year":"2023","unstructured":"Wei H, Zhang Q, Qian Y et al (2023) Mtsdet: multi-scale traffic sign detection with attention and path aggregation. Appl Intell 53(1):238\u2013250","journal-title":"Appl Intell"},{"key":"5744_CR5","doi-asserted-by":"publisher","first-page":"10706","DOI":"10.1007\/s11227-023-05097-3","volume":"79","author":"TP Dang","year":"2023","unstructured":"Dang TP, Tran NT, To VH et al (2023) Improved yolov5 for real-time traffic signs recognition in bad weather conditions. J Supercomput 79:10706\u201310724","journal-title":"J Supercomput"},{"key":"5744_CR6","doi-asserted-by":"crossref","unstructured":"Fang W, Zhang K (2020) Real-time object detection of retail products for eye tracking. In: 2020 8th International Conference on Orange Technology (ICOT), IEEE, pp 1\u20134","DOI":"10.1109\/ICOT51877.2020.9468806"},{"key":"5744_CR7","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.1007\/s11227-020-03325-8","volume":"77","author":"MA Talib","year":"2021","unstructured":"Talib MA, Majzoub S, Nasir Q et al (2021) A systematic literature review on hardware implementation of artificial intelligence algorithms. J Supercomput 77:1897\u20131938","journal-title":"J Supercomput"},{"key":"5744_CR8","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et\u00a0al (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":"5744_CR9","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, et\u00a0al (2018a) Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"issue":"3","key":"5744_CR10","doi-asserted-by":"publisher","first-page":"3791","DOI":"10.1007\/s11227-021-04012-y","volume":"78","author":"Y Le","year":"2022","unstructured":"Le Y, Nanehkaran YA, Mwakapesa DS et al (2022) FP-DCNN: a parallel optimization algorithm for deep convolutional neural network. J Supercomput 78(3):3791\u20133813","journal-title":"J Supercomput"},{"issue":"15","key":"5744_CR11","doi-asserted-by":"publisher","first-page":"17718","DOI":"10.1007\/s10489-022-03217-9","volume":"52","author":"H Wei","year":"2022","unstructured":"Wei H, Zhang Q, Han J et al (2022) Sarnet: spatial attention residual network for pedestrian and vehicle detection in large scenes. Appl Intell 52(15):17718\u201317733","journal-title":"Appl Intell"},{"issue":"5786","key":"5744_CR12","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. science 313(5786):504\u2013507","journal-title":"science"},{"issue":"6","key":"5744_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"5744_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5744_CR15","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, et\u00a0al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"5744_CR16","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S et al (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5744_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"5744_CR18","unstructured":"Ren S, He K, Girshick R, et\u00a0al (2015) Faster R-CNN: Towards real-time object detection with region proposal networks. Adv Neural Inform Process Syst 28"},{"key":"5744_CR19","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, et\u00a0al (2017) Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"5744_CR20","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"5744_CR21","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, et\u00a0al (2018b) Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"5744_CR22","doi-asserted-by":"crossref","unstructured":"Zhang H, Chang H, Ma B, et\u00a0al (2020) Dynamic R-CNN: Towards high quality object detection via dynamic training. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV 16, Springer, pp 260\u2013275","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"5744_CR23","doi-asserted-by":"crossref","unstructured":"Li Z, Wang F, Wang N (2021) Lidar R-CNN: An efficient and universal 3d object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7546\u20137555","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"5744_CR24","doi-asserted-by":"crossref","unstructured":"Sun P, Zhang R, Jiang Y, et\u00a0al (2021) Sparse R-CNN: End-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14454\u201314463","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"5744_CR25","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, et\u00a0al (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":"5744_CR26","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":"5744_CR27","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"5744_CR28","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"5744_CR29","unstructured":"Chuyi L, Lulu L, Hongliang J, et al (2022) YOLOv6: a single-stage object detection framework for industrial applications. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"5744_CR30","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, et\u00a0al (2016) SSD: Single shot multibox detector. In: Computer vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"5744_CR31","unstructured":"Fu CY, Liu W, Ranga A, et\u00a0al (2017) DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659"},{"issue":"12","key":"5744_CR32","doi-asserted-by":"publisher","first-page":"4339","DOI":"10.3390\/s22124339","volume":"22","author":"M Maktab Dar Oghaz","year":"2022","unstructured":"Maktab Dar Oghaz M, Razaak M, Remagnino P (2022) Enhanced single shot small object detector for aerial imagery using super-resolution, feature fusion and deconvolution. Sensors 22(12):4339","journal-title":"Sensors"},{"key":"5744_CR33","unstructured":"Ge Z, Liu S, Wang F, et\u00a0al (2021) Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"5744_CR34","doi-asserted-by":"crossref","unstructured":"Chen Q, Wang Y, Yang T, et\u00a0al (2021) You only look one-level feature. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13039\u201313048","DOI":"10.1109\/CVPR46437.2021.01284"},{"issue":"19","key":"5744_CR35","doi-asserted-by":"publisher","first-page":"4161","DOI":"10.3390\/electronics12194161","volume":"12","author":"Y Qu","year":"2023","unstructured":"Qu Y, Wan B, Wang C et al (2023) Optimization algorithm for steel surface defect detection based on PP-YOLOE. Electronics 12(19):4161","journal-title":"Electronics"},{"key":"5744_CR36","first-page":"30","volume":"2017","author":"A Vaswani","year":"2022","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2022) Attention is all you need. Adv Neural Inform Process Syst 2017:30","journal-title":"Adv Neural Inform Process Syst"},{"key":"5744_CR37","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G et al (2020) End-to-end object detection with transformers. In: Proceedings of the European Conference on Computer Vision, Glasgow, UK  2020, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5744_CR38","doi-asserted-by":"crossref","unstructured":"Meng D, Chen X, Fan Z et al (2021) Conditional detr for fast training convergence. In: Proceedings of the IEEE International Conference on Computer Vision, Montreal, Canada, pp 3651\u20133660","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"5744_CR39","doi-asserted-by":"crossref","unstructured":"Gao P, Zheng M, Wang X et al (2022) Fast convergence of detr with spatially modulated coattention. In: Proceedings of the IEEE International Conference on Computer Vision, Montreal, Canada pp 3621\u20133630","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"5744_CR40","doi-asserted-by":"crossref","unstructured":"Wang Z, Jiacheng Z, Zhicheng Z, Fei S (2020) Efficient Yolo: A lightweight model for embedded deep learning object detection. In: 2020 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp 1-6. IEEE","DOI":"10.1109\/ICMEW46912.2020.9105997"},{"key":"5744_CR41","doi-asserted-by":"crossref","unstructured":"Tang Q, Jie L, Zhiping S, Yu H (2020) Lightdet: a lightweight and accurate object detection network. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 2243-2247. IEEE","DOI":"10.1109\/ICASSP40776.2020.9054101"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05744-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05744-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05744-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:55:18Z","timestamp":1711367718000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05744-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["5744"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05744-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"19 October 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2023","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 competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study does not involve humans or animals subjects.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}