{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:03:26Z","timestamp":1764785006796,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T00:00:00Z","timestamp":1672704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T00:00:00Z","timestamp":1672704000000},"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":["61872231"],"award-info":[{"award-number":["61872231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2021YFC2801000"],"award-info":[{"award-number":["2021YFC2801000"]}]},{"name":"Major Research plan of the National Social Science Foundation","award":["20&ZD130"],"award-info":[{"award-number":["20&ZD130"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11063-022-11139-3","type":"journal-article","created":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T14:04:06Z","timestamp":1672754646000},"page":"6289-6310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Scale-Aware Regional Collective Feature Enhancement Network for Scene Object Detection"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5761-5143","authenticated-orcid":false,"given":"Yiyao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-698X","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,3]]},"reference":[{"key":"11139_CR1","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu L et al (2020) Deep learning for generic object detection: a survey. Int J Comput Vis 128:261\u2013318","journal-title":"Int J Comput Vis"},{"key":"11139_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2016","unstructured":"Chen LC et al (2016) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40:834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11139_CR3","doi-asserted-by":"crossref","unstructured":"Li Y et al (2017) Fully convolutional instance-aware semantic segmentation. In: Computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.472"},{"key":"11139_CR4","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1049\/cvi2.12034","volume":"15","author":"C Yu","year":"2021","unstructured":"Yu C, Liu J, Li Y (2021) Multiscale fully convolutional network-based approach for multilingual character segmentation. IET Comput Vis 15:449\u2013461","journal-title":"IET Comput Vis"},{"key":"11139_CR5","doi-asserted-by":"crossref","unstructured":"Cao Z et al (2018) OpenPose: realtime multi-person 2D pose estimation using part affinity fields. In: IEEE transactions on pattern analysis and machine intelligence","DOI":"10.1109\/CVPR.2017.143"},{"key":"11139_CR6","doi-asserted-by":"crossref","unstructured":"Buizza C, Fischer T, Demiris Y (2020) Real-time multi-person pose tracking using data assimilation","DOI":"10.1109\/WACV45572.2020.9093442"},{"key":"11139_CR7","unstructured":"Newell A, Deng J, Huang Z (2016) Associative embedding: end-to-end learning for joint detection and grouping"},{"key":"11139_CR8","doi-asserted-by":"crossref","unstructured":"Hu H-N et al (2019) Joint monocular 3D vehicle detection and tracking, pp 5389\u20135398","DOI":"10.1109\/ICCV.2019.00549"},{"key":"11139_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J. and A. Zisserman, (2017) Quo Vadis, action recognition? A new model and the kinetics dataset, pp 4724\u20134733","DOI":"10.1109\/CVPR.2017.502"},{"key":"11139_CR10","doi-asserted-by":"crossref","unstructured":"Xu J et al (2018) Attention-aware compositional network for person re-identification, pp 2119\u20132128","DOI":"10.1109\/CVPR.2018.00226"},{"key":"11139_CR11","doi-asserted-by":"crossref","unstructured":"Wang D et al (2018) Deep object centric policies for autonomous driving","DOI":"10.1109\/ICRA.2019.8794224"},{"key":"11139_CR12","doi-asserted-by":"publisher","first-page":"90410","DOI":"10.1109\/ACCESS.2020.2993875","volume":"8","author":"S Shang","year":"2020","unstructured":"Shang S, Liu J, Yang Y (2020) Multi-layer transformer aggregation encoder for answer generation. IEEE Access 8:90410\u201390419","journal-title":"IEEE Access"},{"key":"11139_CR13","doi-asserted-by":"crossref","unstructured":"Bisong E (2019) Convolutional neural networks (CNN), pp 423\u2013441","DOI":"10.1007\/978-1-4842-4470-8_35"},{"key":"11139_CR14","doi-asserted-by":"crossref","unstructured":"Li B et al (2018) High performance visual tracking with siamese region proposal network, pp 8971\u20138980","DOI":"10.1109\/CVPR.2018.00935"},{"key":"11139_CR15","unstructured":"Kanazawa A, Sharma A, Jacobs D (2014) Locally scale-invariant convolutional neural networks. In: Computer science"},{"key":"11139_CR16","doi-asserted-by":"crossref","unstructured":"Fu L, Li X, Zi L (2020) Incremental learning for end-to-end automatic speech recognition","DOI":"10.1109\/ASRU51503.2021.9687910"},{"key":"11139_CR17","doi-asserted-by":"publisher","first-page":"79876","DOI":"10.1109\/ACCESS.2020.2990700","volume":"8","author":"S Chang","year":"2020","unstructured":"Chang S, Liu J (2020) Multi-lane capsule network for classifying images with complex background. IEEE Access 8:79876\u201379886","journal-title":"IEEE Access"},{"key":"11139_CR18","doi-asserted-by":"publisher","first-page":"8701","DOI":"10.1109\/TGRS.2020.2989856","volume":"58","author":"J Liu","year":"2020","unstructured":"Liu J et al (2020) An automatic and forward method to establish 3-D parametric scattering center models of complex targets for target recognition. IEEE Trans Geosci Remote Sens 58:8701\u20138716","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"11139_CR19","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Computer vision and pattern recognition. IEEE","DOI":"10.1109\/CVPR.2016.91"},{"key":"11139_CR20","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H et al (2019) Centernet: keypoint triplets for object detection","DOI":"10.1109\/ICCV.2019.00667"},{"key":"11139_CR21","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) CornerNet: detecting objects as paired keypoints. Int J Comput Vis","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"11139_CR22","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C et al (2015) SSD: single shot multibox detector","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11139_CR23","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2016) YOLO9000: better, faster, stronger","DOI":"10.1109\/CVPR.2017.690"},{"key":"11139_CR24","unstructured":"Ren S et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks"},{"key":"11139_CR25","doi-asserted-by":"crossref","unstructured":"Zheng Z et al (2019) Distance-IoU loss: faster and better learning for bounding box regression","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"11139_CR26","doi-asserted-by":"crossref","unstructured":"He Y et al (2019) Bounding box regression with uncertainty for accurate object detection. In: Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00300"},{"key":"11139_CR27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M et al (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88:303\u2013338","journal-title":"Int J Comput Vis"},{"key":"11139_CR28","first-page":"1","volume":"11","author":"PH Chen","year":"2010","unstructured":"Chen PH, Lin CJ, Sch\u00f6lkopf B (2010) A tutorial on-support vector machines. Appl Stoch Models Bus Ind 11:1\u2013136","journal-title":"Appl Stoch Models Bus Ind"},{"key":"11139_CR29","doi-asserted-by":"crossref","unstructured":"Chen X et al (2016) Monocular 3D object detection for autonomous driving. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.236"},{"key":"11139_CR30","doi-asserted-by":"crossref","unstructured":"Singh B, Davis LS (2017) An analysis of scale invariance in object detection-SNIP","DOI":"10.1109\/CVPR.2018.00377"},{"key":"11139_CR31","unstructured":"Zilly JG, Srivastava RK, Koutn\u00edk J, Schmidhuber J (2016) Recurrent highway networks"},{"key":"11139_CR32","doi-asserted-by":"crossref","unstructured":"He K et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11139_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy C et al (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"11139_CR34","unstructured":"Larsson G, Maire M, Shakhnarovich G (2016) FractalNet: ultra-deep neural networks without residuals"},{"key":"11139_CR35","unstructured":"Zhou X, Wang D, Krhenb\u00fchl P (2019) Objects as points"},{"key":"11139_CR36","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Laurens V, Weinberger KQ (2016) Densely connected convolutional networks. IEEE Computer Society","DOI":"10.1109\/CVPR.2017.243"},{"key":"11139_CR37","doi-asserted-by":"crossref","unstructured":"Szegedy C et al (2015) Rethinking the inception architecture for computer vision","DOI":"10.1109\/CVPR.2016.308"},{"key":"11139_CR38","doi-asserted-by":"crossref","unstructured":"Zoph B et al (2018) Learning transferable architectures for scalable image recognition, pp 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"},{"key":"11139_CR39","unstructured":"Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks"},{"key":"11139_CR40","unstructured":"Kaiming H et al (2017) Mask R-CNN. In: IEEE transactions on pattern analysis and machine intelligence"},{"key":"11139_CR41","unstructured":"Lin TY et al (2017) Focal loss for dense object detection. In: IEEE transactions on pattern analysis and machine intelligence, pp 2999\u20133007"},{"key":"11139_CR42","doi-asserted-by":"crossref","unstructured":"Lin TY, Dollar P, Girshick R, He K et al (2017) Feature pyramid networks for object detection. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.106"},{"key":"11139_CR43","doi-asserted-by":"crossref","unstructured":"Lin TY et al (2014) Microsoft COCO: common objects in context. In: European conference on computer vision","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11139_CR44","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11139_CR45","doi-asserted-by":"crossref","unstructured":"Girshick R et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2014.81"},{"key":"11139_CR46","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, Davis LS (2017) Soft-NMS\u2014improving object detection with one line of code","DOI":"10.1109\/ICCV.2017.593"},{"key":"11139_CR47","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A et al (2013) Playing atari with deep reinforcement learning. Computer science"},{"key":"11139_CR48","doi-asserted-by":"publisher","first-page":"224837","DOI":"10.1109\/ACCESS.2020.3044308","volume":"8","author":"P Gong","year":"2020","unstructured":"Gong P et al (2020) Towards knowledge enhanced language model for machine reading comprehension. IEEE Access 8:224837\u2013224851","journal-title":"IEEE Access"},{"key":"11139_CR49","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"11139_CR50","doi-asserted-by":"crossref","unstructured":"Li Y et al (2019) Scale-aware trident networks for object detection. In: IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"11139_CR51","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: ICLR"},{"key":"11139_CR52","doi-asserted-by":"crossref","unstructured":"He K et al (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/ICCV.2015.123"},{"key":"11139_CR53","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"11139_CR54","doi-asserted-by":"crossref","unstructured":"Shmelkov K, Schmid C, Alahari K (2017) Incremental learning of object detectors without catastrophic forgetting","DOI":"10.1109\/ICCV.2017.368"},{"key":"11139_CR55","doi-asserted-by":"crossref","unstructured":"Hang H, Chang H, Ma B, Wang N et al (2020) Dynamic R-CNN: towards high quality object detection via dynamic training","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"11139_CR56","doi-asserted-by":"crossref","unstructured":"Song G, Liu Y, Wang X (2020) Revisiting the sibling head in object detector. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"11139_CR57","doi-asserted-by":"crossref","unstructured":"Bodla N et al (2017) Soft-NMS\u2014improving object detection with one line of code","DOI":"10.1109\/ICCV.2017.593"},{"key":"11139_CR58","doi-asserted-by":"crossref","unstructured":"Jiang B et al (2018) Acquisition of localization confidence for accurate object detection. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01264-9_48"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11139-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-11139-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11139-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T16:19:38Z","timestamp":1696004378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-11139-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,3]]},"references-count":58,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["11139"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-11139-3","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2023,1,3]]},"assertion":[{"value":"22 December 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}