{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T02:50:20Z","timestamp":1774493420806,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T00:00:00Z","timestamp":1615334400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T00:00:00Z","timestamp":1615334400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61802055"],"award-info":[{"award-number":["61802055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61773068"],"award-info":[{"award-number":["61773068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["N2024005-1"],"award-info":[{"award-number":["N2024005-1"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s00521-021-05867-1","type":"journal-article","created":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T17:04:42Z","timestamp":1615395882000},"page":"11627-11639","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Global context aware RCNN for object detection"],"prefix":"10.1007","volume":"33","author":[{"given":"Wenchao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4549-744X","authenticated-orcid":false,"given":"Chong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mai","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Tie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,10]]},"reference":[{"key":"5867_CR1","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. In: European conference on computer vision, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"5867_CR2","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (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":"5867_CR3","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"5867_CR4","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"5867_CR5","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5867_CR6","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"5867_CR7","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: CVPR09","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5867_CR8","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.neucom.2020.08.074","volume":"421","author":"H Zhang","year":"2021","unstructured":"Zhang H, Sun M, Li Q, Liu L, Liu M, Ji Y (2021) An empirical study of multi-scale object detection in high resolution UAV images. Neurocomputing 421:173\u2013182","journal-title":"Neurocomputing"},{"issue":"12","key":"5867_CR9","doi-asserted-by":"publisher","first-page":"7722","DOI":"10.1109\/TII.2019.2954956","volume":"16","author":"H Zhang","year":"2019","unstructured":"Zhang H, Li D, Ji Y, Zhou H, Wu W, Liu K (2019) Toward new retail: a benchmark dataset for smart unmanned vending machines. IEEE Trans Ind Inform 16(12):7722\u20137731","journal-title":"IEEE Trans Ind Inform"},{"key":"5867_CR10","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:180402767"},{"key":"5867_CR11","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":"5867_CR12","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"5867_CR13","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhuo J, Krahenbuhl P (2019) Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 850\u2013859","DOI":"10.1109\/CVPR.2019.00094"},{"key":"5867_CR14","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv preprint arXiv:190407850"},{"key":"5867_CR15","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, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"5867_CR16","doi-asserted-by":"crossref","unstructured":"Wu Y, Chen Y, Yuan L, Liu Z, Wang L, Li H, Fu Y (2020) Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10186\u201310195","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"5867_CR17","doi-asserted-by":"crossref","unstructured":"Wang J, Chen K, Yang S, Loy CC, Lin D (2019) Region proposal by guided anchoring. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2965\u20132974","DOI":"10.1109\/CVPR.2019.00308"},{"key":"5867_CR18","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":"5867_CR19","doi-asserted-by":"crossref","unstructured":"Chen K, Pang J, Wang J, Xiong Y, Li X, Sun S, Feng W, Liu Z, Shi J, Ouyang W, et\u00a0al. (2019) Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4974\u20134983","DOI":"10.1109\/CVPR.2019.00511"},{"key":"5867_CR20","unstructured":"Qiao S, Chen LC, Yuille A (2020) Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. arXiv preprint arXiv:200602334"},{"key":"5867_CR21","doi-asserted-by":"crossref","unstructured":"Bello I, Zoph B, Vaswani A, Shlens J, Le QV (2019) Attention augmented convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 3286\u20133295","DOI":"10.1109\/ICCV.2019.00338"},{"key":"5867_CR22","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"5867_CR23","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, So\u00a0Kweon I (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"5867_CR24","doi-asserted-by":"crossref","unstructured":"Hu H, Gu J, Zhang Z, Dai J, Wei Y (2018) Relation networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3588\u20133597","DOI":"10.1109\/CVPR.2018.00378"},{"key":"5867_CR25","doi-asserted-by":"crossref","unstructured":"Tang X, Du DK, He Z, Liu J (2018) Pyramidbox: a context-assisted single shot face detector. In: Proceedings of the European conference on computer vision (ECCV), pp 797\u2013813","DOI":"10.1007\/978-3-030-01240-3_49"},{"key":"5867_CR26","doi-asserted-by":"crossref","unstructured":"Wu J, Kuang Z, Wang L, Zhang W, Wu G (2020) Context-aware RCNN: a baseline for action detection in videos. arXiv preprint arXiv:200709861","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"5867_CR27","doi-asserted-by":"crossref","unstructured":"Lin X, Ma L, Liu W, Chang SF (2020) Context-gated convolution. In: Proceedings of the European conference on computer vision. Springer, Cham, pp 701\u2013718","DOI":"10.1007\/978-3-030-58523-5_41"},{"key":"5867_CR28","doi-asserted-by":"crossref","unstructured":"Si J, Zhang H, Li CG, Kuen J, Kong X, Kot AC, Wang G (2018) Dual attention matching network for context-aware feature sequence based person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5363\u20135372","DOI":"10.1109\/CVPR.2018.00562"},{"key":"5867_CR29","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: ICML"},{"key":"5867_CR30","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"5867_CR31","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"5867_CR32","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et\u00a0al. (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp 8024\u20138035"},{"key":"5867_CR33","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 249\u2013256"},{"key":"5867_CR34","doi-asserted-by":"crossref","unstructured":"Xu H, Lv X, Wang X, Ren Z, Bodla N, Chellappa R (2018) Deep regionlets for object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 798\u2013814","DOI":"10.1007\/978-3-030-01252-6_49"},{"key":"5867_CR35","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. In: 2017 IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5867_CR36","doi-asserted-by":"crossref","unstructured":"Jiang B, Luo R, Mao J, Xiao T, Jiang Y (2018) Acquisition of localization confidence for accurate object detection. In: Proceedings of the European conference on computer vision (ECCV), pp 784\u2013799","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"5867_CR37","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, Davis LS (2017) Soft-NMS\u2014improving object detection with one line of code. In: Proceedings of the IEEE international conference on computer vision, pp 5561\u20135569","DOI":"10.1109\/ICCV.2017.593"},{"key":"5867_CR38","doi-asserted-by":"crossref","unstructured":"Tan Z, Nie X, Qian Q, Li N, Li H (2019) Learning to rank proposals for object detection. In: Proceedings of the IEEE international conference on computer vision, pp 8273\u20138281","DOI":"10.1109\/ICCV.2019.00836"},{"key":"5867_CR39","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith L, Petersson L (2018) Improving object localization with fitness NMS and bounded IoU loss. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6877\u20136885","DOI":"10.1109\/CVPR.2018.00719"},{"key":"5867_CR40","unstructured":"Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X, Sun S, Feng W, Liu Z, Xu J, Zhang Z, Cheng D, Zhu C, Cheng T, Zhao Q, Li B, Lu X, Zhu R, Wu Y, Dai J, Wang J, Shi J, Ouyang W, Loy CC, Lin D (2019) MMDetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:190607155"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05867-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05867-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05867-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T20:06:05Z","timestamp":1629749165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05867-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,10]]},"references-count":40,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["5867"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05867-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,10]]},"assertion":[{"value":"1 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}