{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T14:26:01Z","timestamp":1773239161494,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62266046"],"award-info":[{"award-number":["62266046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["YDZJ202201ZYTS603"],"award-info":[{"award-number":["YDZJ202201ZYTS603"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Jilin Provincial Department of Education","award":["JJKH20230281KJ"],"award-info":[{"award-number":["JJKH20230281KJ"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s10489-024-06200-8","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T15:15:52Z","timestamp":1734966952000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards more accurate object detection via encoding reinforcement and multi-channel enhancement"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6773-7777","authenticated-orcid":false,"given":"Weina","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuangyong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huxidan","family":"Jumahong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"6200_CR1","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang T, Zhang X (2023) Motrv2: Bootstrapping end-to-end multi-object tracking by pretrained object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22056\u201322065","DOI":"10.1109\/CVPR52729.2023.02112"},{"issue":"Suppl 1","key":"6200_CR2","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1007\/s10462-023-10558-5","volume":"56","author":"C Fu","year":"2023","unstructured":"Fu C, Lu K, Zheng G, Ye J, Cao Z, Li B, Lu G (2023) Siamese object tracking for unmanned aerial vehicle: A review and comprehensive analysis. Artif Intell Rev 56(Suppl 1):1417\u20131477","journal-title":"Artif Intell Rev"},{"issue":"7","key":"6200_CR3","doi-asserted-by":"publisher","first-page":"130","DOI":"10.3390\/jimaging9070130","volume":"9","author":"H Ullah","year":"2023","unstructured":"Ullah H, Munir A (2023) Human activity recognition using cascaded dual attention cnn and bi-directional gru framework. J Imag 9(7):130","journal-title":"J Imag"},{"issue":"2","key":"6200_CR4","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","volume":"45","author":"Y-F Song","year":"2022","unstructured":"Song Y-F, Zhang Z, Shan C, Wang L (2022) Constructing stronger and faster baselines for skeleton-based action recognition. IEEE Trans Patt Anal Mach Intell 45(2):1474\u20131488","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6200_CR5","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (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"},{"key":"6200_CR6","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"6200_CR7","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":"6200_CR8","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Han J, Ding G (2022) Scaling up your kernels to 31x31: Revisiting large kernel design in cnns. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11963\u201311975","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"6200_CR9","unstructured":"Liu S, Chen T, Chen X, Chen X, Xiao Q, Wu B, K\u00e4rkk\u00e4inen T, Pechenizkiy M, Mocanu D, Wang Z (2022) More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity. arXiv preprint arXiv:2207.03620"},{"key":"6200_CR10","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28"},{"issue":"9","key":"6200_CR11","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, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Patt Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6200_CR12","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"6200_CR13","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"6200_CR14","doi-asserted-by":"crossref","unstructured":"Bakkouri I, Bakkouri S (2024) 2mgas-net: multi-level multi-scale gated attentional squeezed network for polyp segmentation. Signal, Image and Video Processing 1\u201310","DOI":"10.1007\/s11760-024-03240-y"},{"key":"6200_CR15","doi-asserted-by":"crossref","unstructured":"Bakkouri I, Afdel K (2020) Dermonet: A computer-aided diagnosis system for dermoscopic disease recognition. In: Image and Signal Processing: 9th International Conference, ICISP 2020, Marrakesh, Morocco, June 4\u20136, 2020, Proceedings 9, pp 170\u2013177. Springer","DOI":"10.1007\/978-3-030-51935-3_18"},{"key":"6200_CR16","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25"},{"key":"6200_CR17","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6200_CR18","unstructured":"Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. Adv Neural Inf Process Syst 29"},{"key":"6200_CR19","doi-asserted-by":"crossref","unstructured":"Chen Q, Wang Y, Yang T, Zhang X, Cheng J, Sun J (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"},{"key":"6200_CR20","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv preprint arXiv:1605.07146","DOI":"10.5244\/C.30.87"},{"key":"6200_CR21","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6200_CR22","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) 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, pp 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"6200_CR23","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-iou loss: Faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"6200_CR24","unstructured":"Gevorgyan Z (2022) Siou loss: More powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740"},{"key":"6200_CR25","unstructured":"Tong Z, Chen Y, Xu Z, Yu R (2023) Wise-iou: Bounding box regression loss with dynamic focusing mechanism. arXiv preprint arXiv:2301.10051"},{"key":"6200_CR26","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami SA, Van Gool L, Williams CK, Winn J, Zisserman A (2015) The pascal visual object classes challenge: A retrospective. Int J Comp Vision 111:98\u2013136","journal-title":"Int J Comp Vision"},{"key":"6200_CR27","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"},{"key":"6200_CR28","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (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, pp 21\u201337. Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6200_CR29","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng H-T, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings\u00a0of the European Conference on Computer Vision (ECCV), pp 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"6200_CR30","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"6200_CR31","doi-asserted-by":"publisher","first-page":"104397","DOI":"10.1016\/j.engappai.2021.104397","volume":"104","author":"C Termritthikun","year":"2021","unstructured":"Termritthikun C, Jamtsho Y, Ieamsaard J, Muneesawang P, Lee I (2021) Eeea-net: An early exit evolutionary neural architecture search. Eng Appl Artif Intell 104:104397","journal-title":"Eng Appl Artif Intell"},{"key":"6200_CR32","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, Zhao Q (2021) Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 2778\u20132788","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"6200_CR33","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W et al (2022) Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976"},{"key":"6200_CR34","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2023) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"6200_CR35","doi-asserted-by":"publisher","first-page":"107578","DOI":"10.1016\/j.patcog.2020.107578","volume":"109","author":"X Ye","year":"2021","unstructured":"Ye X, Chen S, Xu R (2021) Dpnet: Detail-preserving network for high quality monocular depth estimation. Patt Recogn 109:107578","journal-title":"Patt Recogn"},{"issue":"1","key":"6200_CR36","doi-asserted-by":"publisher","first-page":"9535","DOI":"10.1038\/s41598-023-36724-x","volume":"13","author":"W Wang","year":"2023","unstructured":"Wang W, Li S, Shao J, Jumahong H (2023) Lkc-net: large kernel convolution object detection network. Sci Rep 13(1):9535","journal-title":"Sci Rep"},{"key":"6200_CR37","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6200_CR38","unstructured":"Yu G, Chang Q, Lv W, Xu C, Cui C, Ji W, Dang Q, Deng K, Wang G, Du Y et al (2021) Pp-picodet: A better real-time object detector on mobile devices. arXiv preprint arXiv:2111.00902"},{"key":"6200_CR39","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"6200_CR40","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"6200_CR41","unstructured":"Huang X, Wang X, Lv W, Bai X, Long X, Deng K, Dang Q, Han S, Liu Q, Hu X et al (2021) Pp-yolov2: A practical object detector. arXiv preprint arXiv:2104.10419"},{"key":"6200_CR42","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2021) Scaled-yolov4: Scaling cross stage partial network. In: Proceedings of the IEEE\/cvf Conference on Computer Vision and Pattern Recognition, pp 13029\u201313038","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"6200_CR43","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"6200_CR44","unstructured":"Xu X, Jiang Y, Chen W, Huang Y, Zhang Y, Sun X (2022) Damo-yolo: A report on real-time object detection design. arXiv preprint arXiv:2211.15444"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06200-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-06200-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06200-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T16:04:03Z","timestamp":1738253043000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-06200-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["6200"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-06200-8","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,23]]},"assertion":[{"value":"13 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2024","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 declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"212"}}