{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T02:49:53Z","timestamp":1781318993177,"version":"3.54.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T00:00:00Z","timestamp":1655942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T00:00:00Z","timestamp":1655942400000},"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":["61572214"],"award-info":[{"award-number":["61572214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003397","name":"Huazhong University of Science and Technology","doi-asserted-by":"publisher","award":["2020kfyXGYJ114"],"award-info":[{"award-number":["2020kfyXGYJ114"]}],"id":[{"id":"10.13039\/501100003397","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s11042-022-13164-9","type":"journal-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T21:03:08Z","timestamp":1656018188000},"page":"2349-2367","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Dynamic multi-scale loss optimization for object detection"],"prefix":"10.1007","volume":"82","author":[{"given":"Yihao","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juntao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1247-2211","authenticated-orcid":false,"given":"Qi","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,23]]},"reference":[{"key":"13164_CR1","doi-asserted-by":"crossref","unstructured":"Cai Q, Pan Y, Wang Y, Liu J, Yao T, Mei T (2020) Learning a unified sample weighting network for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 14161\u201314170","DOI":"10.1109\/CVPR42600.2020.01418"},{"key":"13164_CR2","doi-asserted-by":"crossref","unstructured":"Caicedo J C, Lazebnik S (2015) Active object localization with deep reinforcement learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 2488\u20132496","DOI":"10.1109\/ICCV.2015.286"},{"key":"13164_CR3","unstructured":"Cao J, Chen Q, Guo J, Shi R (2020) Attention-guided context feature pyramid network for object detection. arXiv:2005.11475"},{"key":"13164_CR4","doi-asserted-by":"crossref","unstructured":"Cao Y, Chen K, Loy C C, Lin D (2020) Prime sample attention in object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 11580\u201311588","DOI":"10.1109\/CVPR42600.2020.01160"},{"key":"13164_CR5","unstructured":"Chen K, Wang J, Pang J, et al. (2019) MMDetection: open mmlab detection toolbox and benchmark. arXiv:1906.07155"},{"key":"13164_CR6","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 6568\u20136577","DOI":"10.1109\/ICCV.2019.00667"},{"issue":"2","key":"13164_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Gool L V, Williams C K I, Winn J M, Zisserman A (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"13164_CR8","doi-asserted-by":"crossref","unstructured":"Guo C, Fan B, Zhang Q, Xiang S, Pan C (2020) Augfpn: improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12595\u201312604","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"13164_CR9","doi-asserted-by":"crossref","unstructured":"Guo M, Haque A, Huang D, Yeung S, Fei-fei L (2018) Dynamic task prioritization for multitask learning. In: Proceedings of the European conference on computer vision (ECCV), pp 282\u2013299","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"13164_CR10","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P., Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"13164_CR11","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"13164_CR12","doi-asserted-by":"crossref","unstructured":"He Y, Zhu C, Wang J, Savvides M, Zhang X (2019) Bounding box regression with uncertainty for accurate object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 2888\u20132897","DOI":"10.1109\/CVPR.2019.00300"},{"key":"13164_CR13","unstructured":"Jie Z, Liang X, Feng J, Jin X, Lu W F, Yan S (2016) Tree-structured reinforcement learning for sequential object localization. In: Advances in neural information processing systems, pp 127\u2013 135"},{"key":"13164_CR14","unstructured":"Joya C, Dong L, Tong X, Shiwei W, Yifei C, Enhong C (2019) Is heuristic sampling necessary in training deep object detectors?. arXiv:1909.04868"},{"key":"13164_CR15","unstructured":"Kendall A, Gal Y, Cipolla R (2018) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7482\u20137491"},{"key":"13164_CR16","doi-asserted-by":"crossref","unstructured":"Kim S, Park S, Na B, Yoon S (2020) Spiking-yolo: spiking neural network for energy-efficient object detection. Proc AAAI Conf Artif Intell:11270\u201311277","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"13164_CR17","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong T, Sun F, Liu H, Jiang Y, Li L, Shi J (2020) Foveabox: beyound anchor-based object detection. IEEE Trans Image Process (TIP) 29:7389\u20137398","journal-title":"IEEE Trans Image Process (TIP)"},{"key":"13164_CR18","doi-asserted-by":"crossref","unstructured":"Kong X, Xin B, Wang Y, Hua G (2017) Collaborative deep reinforcement learning for joint object search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7072\u20137081","DOI":"10.1109\/CVPR.2017.748"},{"key":"13164_CR19","doi-asserted-by":"crossref","unstructured":"Li B, Liu Y, Wang X (2019) Gradient harmonized single-stage detector. In: Proceedings of the AAAI conference on artificial intelligence, pp 8577\u20138584","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"13164_CR20","doi-asserted-by":"crossref","unstructured":"Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"13164_CR21","doi-asserted-by":"crossref","unstructured":"Lin T Y, Doll\u00e1r P., Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"13164_CR22","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 (ICCV), pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"13164_CR23","doi-asserted-by":"crossref","unstructured":"Lin T Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick C L (2014) Microsoft coco: common objects in context. In: Proceedings of the European conference on computer vision (ECCV), pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"7","key":"13164_CR24","first-page":"2544","volume":"31","author":"S Liu","year":"2019","unstructured":"Liu S, Huang D, Wang Y (2019) Pay attention to them: deep reinforcement learning-based cascade object detection. IEEE Trans Neural Netw Learn Syst 31(7):2544\u20132556","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"13164_CR25","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"13164_CR26","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y, Berg A C (2016) Ssd: single shot multibox detector. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"13164_CR27","doi-asserted-by":"crossref","unstructured":"Luo Y, Cao X, Zhang J, Guo J, Shen H, Wang T, Feng Q (2021) CE-FPN: enhancing channel information for object detection. arXiv:2103.10643","DOI":"10.1007\/s11042-022-11940-1"},{"key":"13164_CR28","doi-asserted-by":"crossref","unstructured":"Mathe S, Pirinen A, Sminchisescu C (2016) Reinforcement learning for visual object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 2894\u20132902","DOI":"10.1109\/CVPR.2016.316"},{"key":"13164_CR29","doi-asserted-by":"crossref","unstructured":"Oksuz K, Cam B C, Kalkan S, Akbas E (2021) Imbalance problems in object detection: A Review IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)","DOI":"10.1109\/TPAMI.2020.2981890"},{"key":"13164_CR30","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra r-cnn: towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"key":"13164_CR31","doi-asserted-by":"crossref","unstructured":"Pirinen A, Sminchisescu C (2018) Deep reinforcement learning of region proposal networks for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6945\u20136954","DOI":"10.1109\/CVPR.2018.00726"},{"issue":"6","key":"13164_CR32","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 39(6):1137\u20131149","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"13164_CR33","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R B (2016) Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 761\u2013769","DOI":"10.1109\/CVPR.2016.89"},{"key":"13164_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192","volume-title":"Reinforcement learning - an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning - an introduction. MIT Press, Cambridge. https:\/\/www.worldcat.org\/oclc\/37293240"},{"key":"13164_CR35","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: Fully convolutional one-stage object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 9626\u20139635","DOI":"10.1109\/ICCV.2019.00972"},{"key":"13164_CR36","doi-asserted-by":"crossref","unstructured":"Wei Y, Pan X, Qin H, Ouyang W, Yan J (2018) Quantization mimic: Towards very tiny cnn for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 267\u2013283","DOI":"10.1007\/978-3-030-01237-3_17"},{"issue":"1","key":"13164_CR37","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/TNNLS.2019.2899936","volume":"31","author":"S Yang","year":"2019","unstructured":"Yang S, Deng B, Wang J, Li H, Lu M, Che Y, Wei X, Loparo K A (2019) Scalable digital neuromorphic architecture for large-scale biophysically meaningful neural network with multi-compartment neurons. IEEE Trans Neural Netw Learn Syst 31(1):148\u2013162","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"13164_CR38","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3389\/fnins.2021.601109","volume":"15","author":"S Yang","year":"2021","unstructured":"Yang S., Gao T., Wang J., Deng B., Lansdell B., Linares-Barranco B. (2021) Efficient spike-driven learning with dendritic event-based processing. Front Neurosci 15:97","journal-title":"Front Neurosci"},{"key":"13164_CR39","doi-asserted-by":"crossref","unstructured":"Yang S., Wang J., Deng B., Azghadi M. R., Linares-Barranco B. (2021) Neuromorphic context-dependent learning framework with fault-tolerant spike routing. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2021.3084250"},{"key":"13164_CR40","doi-asserted-by":"crossref","unstructured":"Yang S, Wang J, Zhang N, Deng B, Pang Y, Azghadi M R (2021) Cerebellumorphic: large-scale neuromorphic model and architecture for supervised motor learning. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2021.3057070"},{"key":"13164_CR41","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang T S (2016) Unitbox: an advanced object detection network. In: Proceedings of the ACM Conference on Multimedia, pp 516\u2013520","DOI":"10.1145\/2964284.2967274"},{"key":"13164_CR42","doi-asserted-by":"crossref","unstructured":"Yu X, Liu T, Wang X, Tao D (2017) On compressing deep models by low rank and sparse decomposition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7370\u20137379","DOI":"10.1109\/CVPR.2017.15"},{"issue":"15","key":"13164_CR43","doi-asserted-by":"publisher","first-page":"21145","DOI":"10.1007\/s11042-019-7446-2","volume":"78","author":"C Yuan","year":"2019","unstructured":"Yuan C, Guo J, Feng P, Zhao Z, Luo Y, Xu C, Wang T, Duan K (2019) Learning deep embedding with mini-cluster loss for person re-identification. Multimed Tools Appl 78(15):21145\u201321166","journal-title":"Multimed Tools Appl"},{"key":"13164_CR44","doi-asserted-by":"crossref","unstructured":"Zhang H, Chang H, Ma B, Wang N, Chen X (2020) Dynamic r-CNN: towards high quality object detection via dynamic training. In: Proceedings of the European conference on computer vision (ECCV), pp 260\u2013275","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"13164_CR45","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y, Lei Z, Li S Z (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9756\u20139765","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"13164_CR46","doi-asserted-by":"crossref","unstructured":"Zhang T, Zhong Q, Pu S, Xie D (2021) Modulating localization and classification for harmonized object detection IEEE International conference on multimedia and expo (ICME)","DOI":"10.1109\/ICME51207.2021.9428181"},{"key":"13164_CR47","doi-asserted-by":"crossref","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 840\u2013849","DOI":"10.1109\/CVPR.2019.00093"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13164-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-13164-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13164-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T05:26:59Z","timestamp":1672723619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-13164-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,23]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["13164"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-13164-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,23]]},"assertion":[{"value":"10 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors have participated sufficiently in the work to take public responsibility for the content, including participation in the concept, design, analysis, writing, or revision of the manuscript. The authors declare that they have no conflict of interest. And each author certifies that this manuscript has not been and will not be submitted to or published in any other publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}