{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:56:03Z","timestamp":1775120163190,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s11042-020-10191-2","type":"journal-article","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T20:03:45Z","timestamp":1609963425000},"page":"11539-11556","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Enhanced SSD with interactive multi-scale attention features for object detection"],"prefix":"10.1007","volume":"80","author":[{"given":"Shuren","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jia","family":"Qiu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,6]]},"reference":[{"key":"10191_CR1","doi-asserted-by":"publisher","unstructured":"Anderson P, He XD, Buehler C (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6077\u20136086. https:\/\/doi.org\/10.1109\/CVPR.2018.00636","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10191_CR2","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv:1409.0473"},{"key":"10191_CR3","doi-asserted-by":"publisher","unstructured":"Buzcu I, Alatan AA (2016) Fisher-selective search for object detection. In: IEEE International Conference on Image Processing, pp. 3633\u20133637, ICIP. https:\/\/doi.org\/10.1109\/ICIP.2016.7533037","DOI":"10.1109\/ICIP.2016.7533037"},{"key":"10191_CR4","doi-asserted-by":"publisher","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, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"10191_CR5","doi-asserted-by":"publisher","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol 1, pp 886\u2013893. https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"issue":"1","key":"10191_CR6","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2007","unstructured":"Everingham M, Eslami SMA (2007) The Pascal visual object classes challenge 2007 (VOC2007) development kit. Int J Comput Vis 111(1):98\u2013136. https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"Int J Comput Vis"},{"key":"10191_CR7","unstructured":"Fu C, Liu W, Ranga A (2017) DSSD: Deconvolutional Single Shot Detector arXiv:1701.06659"},{"key":"10191_CR8","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440\u20131448, ICCV. https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"10191_CR9","doi-asserted-by":"publisher","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"10191_CR10","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/s00371-019-01633-6","volume":"36","author":"Y Gui","year":"2020","unstructured":"Gui Y, Zeng G (2020) Joint learning of visual and spatial features for edit propagation from a single image. Vis Comput 36:469\u2013482. https:\/\/doi.org\/10.1007\/s00371-019-01633-6","journal-title":"Vis Comput"},{"key":"10191_CR11","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S (2014) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. Eur Conf Comput Vis, pp. 346\u2013361, ECCV. https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"10191_CR12","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. CVPR. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"10191_CR13","doi-asserted-by":"publisher","unstructured":"Hu H, Gu JY, Zhang Z, Dai J, Wei YC (2018) Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00378","DOI":"10.1109\/CVPR.2018.00378"},{"key":"10191_CR14","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely Connected Convolutional Networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261\u20132269, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"10191_CR15","doi-asserted-by":"publisher","unstructured":"Jia D, Wei D, Richard S, Lijia L, Kai L, Feifei L (2009) ImageNet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2009:248\u2013255, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"7553","key":"10191_CR16","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444. https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"10191_CR17","doi-asserted-by":"publisher","unstructured":"Li W, Xu H, Li H, Yang YJ, Sharma PK, Wang J, Singh S (2020) Complexity and algorithms for superposed data uploading problem in networks with smart devices. IEEE Internet Things J pp. 1\u20131. https:\/\/doi.org\/10.1109\/jiot.2019.2949352","DOI":"10.1109\/jiot.2019.2949352"},{"key":"10191_CR18","doi-asserted-by":"publisher","unstructured":"Lin TY, Dollar P, Girshick R (2017) Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 936\u2013944, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"10191_CR19","doi-asserted-by":"publisher","unstructured":"Lin T, Goyal P, Girshick R, He K, Dollar P (2018) Focal loss for dense object detection. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 42, no 2, pp 318\u2013327. https:\/\/doi.org\/10.1109\/TPAMI.2018.2858826","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"10191_CR20","doi-asserted-by":"publisher","unstructured":"Liu W, Anguelov D, Erhan D, Christian S, Scott R, Cheng-Yang F, Alexander C (2016) SSD: single shot MultiBox detector. In: European conference on computer vision. Pp. 21-37, ECCV. https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10191_CR21","unstructured":"Mnih V, Heess N, Graves A (2014) Recurrent models of visual attention. In: Advances in neural information processing systems, pp. 2204\u20132212, NIPS."},{"issue":"1","key":"10191_CR22","doi-asserted-by":"publisher","first-page":"24626","DOI":"10.1109\/ACCESS.2019.2894673","volume":"7","author":"J Qin","year":"2019","unstructured":"Qin J, Li H, Xiang X, Tan Y, Pan W, Xiong NN (2019) An encrypted image retrieval method based on Harris corner optimization and LSH in cloud computing. IEEE Access 7(1):24626\u201324633. https:\/\/doi.org\/10.1109\/ACCESS.2019.2894673","journal-title":"IEEE Access"},{"key":"10191_CR23","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: Better, Faster, Stronger. In: The IEEE Conference on Computer Vision and Pattern Recognition. pp. 6517\u20136525, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"10191_CR24","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: An Incremental Improvement"},{"key":"10191_CR25","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"10191_CR26","doi-asserted-by":"publisher","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 39, no 6, pp 1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","DOI":"10.1109\/TPAMI.2016.2577031"},{"issue":"8","key":"10191_CR27","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1088\/0031-9155\/45\/8\/315","volume":"45","author":"J Sempau","year":"2000","unstructured":"Sempau J, Wilderman SJ, Bielajew AF (2000) DPM, a fast, accurate Monte Carlo code optimized for photon and electron radiotherapy treatment planning dose calculations. Phys Med Biol 45(8):2263\u20132291. https:\/\/doi.org\/10.1088\/0031-9155\/45\/8\/315","journal-title":"Phys Med Biol"},{"key":"10191_CR28","unstructured":"Simonyan, K., Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556"},{"key":"10191_CR29","unstructured":"Stollenga M, Masci J, Gomez F, Schmidhuber J (2014) Deep networks with internal selective attention through feedback connections. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol 2, pp 3545\u20133553, NIPS"},{"key":"10191_CR30","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1007\/s11036-018-1049-4","volume":"24","author":"Q Tang","year":"2019","unstructured":"Tang Q, Xie MZ, Yang K, Yuansheng L, Dongdai Z, Yun S (2019) A decision function based smart charging and discharging strategy for electric vehicle in smart grid. Mob Netw Appl 24:1722\u20131731. https:\/\/doi.org\/10.1007\/s11036-018-1049-4","journal-title":"Mob Netw Appl"},{"key":"10191_CR31","doi-asserted-by":"publisher","unstructured":"Wang F, Jiang M, Qian C, et al. (2017) Residual attention network for image classification. IEEE Conf Comput Vis Pattern Recognit, pp. 6450\u20136458, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.683","DOI":"10.1109\/CVPR.2017.683"},{"key":"10191_CR32","doi-asserted-by":"publisher","unstructured":"Wang J, Gao Y, Yin X, Li F, Kim H (2018) An Enhanced PEGASIS Algorithm with Mobile Sink Support for Wireless Sensor Networks. Wirel Commun Mob Comput (9 pages). https:\/\/doi.org\/10.1155\/2018\/9472075","DOI":"10.1155\/2018\/9472075"},{"key":"10191_CR33","doi-asserted-by":"publisher","unstructured":"Xiao T, Xu Y, Yang K, Zhang J, Peng Y, Zhang Z (2015) The application of two-level attention models in deep convolutional neural network for fine-grained image classification. IEEE Conf Comput Vis Pattern Recognit, pp.842\u2013850, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2015.7298685","DOI":"10.1109\/CVPR.2015.7298685"},{"issue":"1","key":"10191_CR34","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3970\/cmc.2018.055.121","volume":"55","author":"D Zeng","year":"2018","unstructured":"Zeng D, Dai Y, Li F, Sherratt RS, Wang J (2018) Adversarial learning for distant supervised relation extraction. Comput Mater Contin 55(1):121\u2013136. https:\/\/doi.org\/10.3970\/cmc.2018.055.121","journal-title":"Comput Mater Contin"},{"key":"10191_CR35","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.jvcir.2017.07.006","volume":"48","author":"D Zhan","year":"2017","unstructured":"Zhan D, Yin T, Yang G, Xia M, Li L, Sun X (2017) Detecting image seam carving with low scaling ratio using multi-scale spatial and spectral entropies. J Vis Commun Image Represent 48:281\u2013291. https:\/\/doi.org\/10.1016\/j.jvcir.2017.07.006","journal-title":"J Vis Commun Image Represent"},{"key":"10191_CR36","doi-asserted-by":"publisher","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4203\u20134212, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00442","DOI":"10.1109\/CVPR.2018.00442"},{"key":"10191_CR37","doi-asserted-by":"publisher","unstructured":"Zhang Z, Qiao S, Xie C, Shen W, Wang B, Yuille AL (2018) Single-shot object detection with enriched semantics. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5813\u20135821, CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00609","DOI":"10.1109\/CVPR.2018.00609"},{"key":"10191_CR38","doi-asserted-by":"publisher","first-page":"15095","DOI":"10.1007\/s11042-018-6562-8","volume":"79","author":"J Zhang","year":"2020","unstructured":"Zhang J, Jin X, Sun J, Wang J, Arun KS (2020) Spatial and semantic convolutional features for robust visual object tracking. Multimed Tools Appl 79:15095\u201315115. https:\/\/doi.org\/10.1007\/s11042-018-6562-8","journal-title":"Multimed Tools Appl"},{"key":"10191_CR39","doi-asserted-by":"publisher","unstructured":"Zhaowei C, Quanfu F, Rogerio SF, Nuno V (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: European Conference on Computer Vision, pp. 354\u2013370, ECCV. https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22","DOI":"10.1007\/978-3-319-46493-0_22"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10191-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-10191-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10191-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T05:50:03Z","timestamp":1618552203000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-10191-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,6]]},"references-count":39,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["10191"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-10191-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,6]]},"assertion":[{"value":"21 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}