{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T18:42:33Z","timestamp":1761676953336,"version":"3.37.3"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:00:00Z","timestamp":1609718400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:00:00Z","timestamp":1609718400000},"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":["61876093"],"award-info":[{"award-number":["61876093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20181393"],"award-info":[{"award-number":["BK20181393"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201908320072"],"award-info":[{"award-number":["201908320072"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mobile Netw Appl"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11036-020-01723-z","type":"journal-article","created":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:03:13Z","timestamp":1609718593000},"page":"77-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["RSANet: Towards Real-Time Object Detection with Residual Semantic-Guided Attention Feature Pyramid Network"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7894-7929","authenticated-orcid":false,"given":"Quan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenghua","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihua","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,4]]},"reference":[{"key":"1723_CR1","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"1723_CR2","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"1723_CR3","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1723_CR4","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":"1723_CR5","doi-asserted-by":"crossref","unstructured":"Nakayama Y, Lu H, Li Y, Kamiya T (2020) WideSegNeXt: semantic image segmentation using wide residual network and NeXt dilated unit. IEEE Sensors Journal","DOI":"10.1109\/JSEN.2020.3008908"},{"key":"1723_CR6","doi-asserted-by":"crossref","unstructured":"Lu W, Zhang X, Lu H, Li F (2020) Deep hierarchical encoding model for sentence semantic matching. Journal of Visual Communication and Image Representation, 102794","DOI":"10.1016\/j.jvcir.2020.102794"},{"key":"1723_CR7","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":"1723_CR8","doi-asserted-by":"crossref","unstructured":"Van de Sande KE, Uijlings JR, Gevers T, Smeulders AW (2011) Segmentation as selective search for object recognition. In: 2011 International conference on computer vision. IEEE, pp 1879\u2013 1886","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"1723_CR9","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"},{"key":"1723_CR10","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":"1723_CR11","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":"1723_CR12","unstructured":"Howard A, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861"},{"key":"1723_CR13","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1723_CR14","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"},{"key":"1723_CR15","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (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":"1723_CR16","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1723_CR17","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":"1723_CR18","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":"1723_CR19","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767"},{"key":"1723_CR20","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":"1723_CR21","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: deconvolutional single shot detector. arXiv:1701.06659"},{"key":"1723_CR22","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li S (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":"1723_CR23","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, Le QV, Adam H (2019) Searching for mobilenetv3. In: Proceedings of the IEEE international conference on computer vision, pp 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1723_CR24","unstructured":"Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv:1602.07360"},{"key":"1723_CR25","unstructured":"Wang RJ, Li X, Ling CX (2018) Pelee: a real-time object detection system on mobile devices. In: Advances in neural information processing systems, pp 1963\u20131972"},{"key":"1723_CR26","doi-asserted-by":"crossref","unstructured":"Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2017.683"},{"key":"1723_CR27","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":"1723_CR28","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":"1723_CR29","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv:1312.44001312.4400"},{"key":"1723_CR30","doi-asserted-by":"crossref","unstructured":"Wong A, Famuori M, Shafiee MJ, Li F, Chwyl B, Chung J (2019) YOLO nano: a highly compact you only look once convolutional neural network for object detection. arXiv:1910.01271","DOI":"10.1109\/EMC2-NIPS53020.2019.00013"},{"key":"1723_CR31","doi-asserted-by":"crossref","unstructured":"Cong D, Zhou Q, Cheng J, Wu X, Zhang S, Ou W, Lu H (2019) CAN: contextual aggregating network for semantic segmentation. In: ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 1892\u20131896","DOI":"10.1109\/ICASSP.2019.8683673"},{"key":"1723_CR32","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2007) The PASCAL visual object classes challenge 2007 (VOC2007) results"},{"key":"1723_CR33","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Common objects in context. In: European conference on computer vision. Springer, Cham, pp 740\u2013755"},{"key":"1723_CR34","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Deven M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp 265\u2013283"},{"key":"1723_CR35","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":"1723_CR36","doi-asserted-by":"crossref","unstructured":"Mehta R, Ozturk C (2018) Object detection at 200 frames per second. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-11021-5_41"},{"key":"1723_CR37","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2017) Light-head r-cnn: in defense of two-stage object detector. arXiv:1711.07264"},{"key":"1723_CR38","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhou Q, Liu J, Xiong J, Gao G, Wu X, Latecki LJ (2019) Lednet: a lightweight encoder-decoder network for real-time semantic segmentation. In: 2019 IEEE International conference on image processing (ICIP). IEEE, pp 1860\u20131864","DOI":"10.1109\/ICIP.2019.8803154"},{"key":"1723_CR39","doi-asserted-by":"crossref","unstructured":"Liu J, Zhou Q, Qiang Y, Kang B, Wu X, Zheng B (IEEE) FDDWNet: a lightweight convolutional neural network for real-time semantic segmentation. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2373\u20132377","DOI":"10.1109\/ICASSP40776.2020.9053838"},{"key":"1723_CR40","unstructured":"Li S, Zhou Q, Liu J, Wang J, Fan Y, Wu X, Latecki LJ (2020) IEEE 27th Int. conf. on image processing (ICIP) virtual"},{"key":"1723_CR41","unstructured":"Wang Z, Zheng L, Liu Y, Wang S (2019) Towards real-time multi-object tracking. arXiv:1909.12605"},{"key":"1723_CR42","unstructured":"Zhan Y, Wang C, Wang X, Zeng W, Liu W (2020) A simple baseline for multi-object tracking. arXiv:2004.01888"},{"key":"1723_CR43","doi-asserted-by":"crossref","unstructured":"Lu Z, Rathod V, Votel R, Huang J (2020) RetinaTrack: online single stage joint detection and tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14668\u201314678","DOI":"10.1109\/CVPR42600.2020.01468"},{"key":"1723_CR44","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: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1723_CR45","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"1723_CR46","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"issue":"9","key":"1723_CR47","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":"1723_CR48","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.031671502.03167"},{"key":"1723_CR49","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"1723_CR50","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":"1723_CR51","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":"1723_CR52","doi-asserted-by":"crossref","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2019) M2det: a single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 9259\u20139266","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"1723_CR53","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"}],"container-title":["Mobile Networks and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-020-01723-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11036-020-01723-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-020-01723-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T09:07:20Z","timestamp":1670663240000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11036-020-01723-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,4]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["1723"],"URL":"https:\/\/doi.org\/10.1007\/s11036-020-01723-z","relation":{},"ISSN":["1383-469X","1572-8153"],"issn-type":[{"type":"print","value":"1383-469X"},{"type":"electronic","value":"1572-8153"}],"subject":[],"published":{"date-parts":[[2021,1,4]]},"assertion":[{"value":"30 November 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}