{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T18:31:03Z","timestamp":1778005863024,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,3,14]],"date-time":"2020-03-14T00:00:00Z","timestamp":1584144000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,14]],"date-time":"2020-03-14T00:00:00Z","timestamp":1584144000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61671095"],"award-info":[{"award-number":["No. 61671095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s11063-020-10228-5","type":"journal-article","created":{"date-parts":[[2020,3,14]],"date-time":"2020-03-14T16:03:21Z","timestamp":1584201801000},"page":"2789-2806","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["A Balanced Feature Fusion SSD for Object Detection"],"prefix":"10.1007","volume":"51","author":[{"given":"Hui","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lufa","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,14]]},"reference":[{"key":"10228_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, Cham, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10228_CR2","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"10228_CR3","unstructured":"Chen C, Liu MY, Tuzel O, Xiao J (2016) R-CNN for small object detection. In: Asian conference on computer vision. Springer, Cham, pp 214\u2013230"},{"key":"10228_CR4","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659"},{"key":"10228_CR5","unstructured":"Dai J, Li Y, He K, Sun J (2016) RFCN: object detection via region based fully convolutional networks. In: Neural Information Processing Systems, pp 379\u2013387"},{"key":"10228_CR6","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, Cham, pp 818\u2013833"},{"key":"10228_CR7","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":"10228_CR8","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 conference on computer vision and pattern recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"issue":"12","key":"10228_CR9","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659\u20135670","journal-title":"IEEE Trans Image Process"},{"key":"10228_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2932058","author":"J Yu","year":"2019","unstructured":"Yu J, Tan M, Zhang H, Tao D, Rui Y (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2019.2932058","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"10228_CR11","doi-asserted-by":"publisher","first-page":"2420","DOI":"10.1109\/TIP.2018.2804218","volume":"27","author":"J Zhang","year":"2018","unstructured":"Zhang J, Yu J, Tao D (2018) Local deep-feature alignment for unsupervised dimension reduction. IEEE Trans Image Process 27(5):2420\u20132432","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"10228_CR12","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TNNLS.2019.2908982","volume":"31","author":"J Yu","year":"2019","unstructured":"Yu J, Zhu C, Zhang J, Huang Q, Tao D (2019) Spatial pyramid-enhanced NetVLAD with weighted triplet loss for place recognition. IEEE Trans Neural Netw Learn Syst 31(2):661\u2013674","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10228_CR13","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 conference on computer vision and pattern recognition, pp 7482\u20137491"},{"key":"10228_CR14","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 conference on computer vision and pattern recognition, pp 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"issue":"7","key":"10228_CR15","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"C Hong","year":"2018","unstructured":"Hong C, Yu J, Zhang J, Jin X, Lee KH (2018) Multi-modal face pose estimation with multi-task manifold deep learning. IEEE Trans Ind Inform 15(7):3952\u20133961","journal-title":"IEEE Trans Ind Inform"},{"issue":"5","key":"10228_CR16","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1109\/TIFS.2016.2636090","volume":"12","author":"J Yu","year":"2016","unstructured":"Yu J, Zhang B, Kuang Z, Lin D, Fan J (2016) iPrivacy: image privacy protection by identifying sensitive objects via deep multi-task learning. IEEE Trans Inf Forensics Secur 12(5):1005\u20131016","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"4","key":"10228_CR17","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TCYB.2014.2336697","volume":"45","author":"J Yu","year":"2014","unstructured":"Yu J, Tao D, Wang M, Rui Y (2014) Learning to rank using user clicks and visual features for image retrieval. IEEE Trans Cybern 45(4):767\u2013779","journal-title":"IEEE Trans Cybern"},{"key":"10228_CR18","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":"10228_CR19","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"},{"issue":"6","key":"10228_CR20","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10228_CR21","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":"10228_CR22","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp 1097\u20131105"},{"issue":"2","key":"10228_CR23","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vis 104(2):154\u2013171","journal-title":"Int J Comput Vis"},{"issue":"9","key":"10228_CR24","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 Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10228_CR25","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":"10228_CR26","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, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"10228_CR27","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":"10228_CR28","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RS, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: European conference on computer vision. Springer, Cham, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"10228_CR29","doi-asserted-by":"crossref","unstructured":"Jeong J, Park H, Kwak N (2017) Enhancement of SSD by concatenating feature maps for object detection. arXiv preprint arXiv:1705.09587","DOI":"10.5244\/C.31.76"},{"key":"10228_CR30","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 conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10228_CR31","doi-asserted-by":"crossref","unstructured":"Shen Z, Liu Z, Li J, Jiang YG, Chen Y, Xue X (2017) Dsod: learning deeply supervised object detectors from scratch. In: Proceedings of the IEEE international conference on computer vision, pp 1919\u20131927","DOI":"10.1109\/ICCV.2017.212"},{"key":"10228_CR32","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten 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":"10228_CR33","doi-asserted-by":"crossref","unstructured":"Choi J, Lee K, Jeong J et al (2019) Two-layer residual feature fusion for object detection. In: International conference on pattern recognition applications and methods, pp 352\u2013359","DOI":"10.5220\/0007306803520359"},{"key":"10228_CR34","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 761\u2013769","DOI":"10.1109\/CVPR.2016.89"},{"key":"10228_CR35","doi-asserted-by":"crossref","unstructured":"Lin TY, 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":"10228_CR36","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang T (2016) Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM international conference on multimedia. ACM, pp 516\u2013520","DOI":"10.1145\/2964284.2967274"},{"key":"10228_CR37","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"},{"issue":"2","key":"10228_CR38","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-020-10228-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-020-10228-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-020-10228-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T00:34:03Z","timestamp":1615682043000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-020-10228-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,14]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["10228"],"URL":"https:\/\/doi.org\/10.1007\/s11063-020-10228-5","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,14]]},"assertion":[{"value":"14 March 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}