{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T02:29:25Z","timestamp":1770172165776,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2018,10,2]],"date-time":"2018-10-02T00:00:00Z","timestamp":1538438400000},"content-version":"tdm","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. 61671423 and No. 61271403"],"award-info":[{"award-number":["No. 61671423 and No. 61271403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1007\/s11042-018-6653-6","type":"journal-article","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T18:57:00Z","timestamp":1538420220000},"page":"11655-11674","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A detection method for low-pixel ratio object"],"prefix":"10.1007","volume":"78","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1995-216X","authenticated-orcid":false,"given":"Dong","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Jinwen","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Yuhao","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Mingyue","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Chengfeng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Zhipeng","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,2]]},"reference":[{"issue":"2","key":"6653_CR1","first-page":"212","volume":"74","author":"M Auli","year":"2013","unstructured":"Auli M, Galley M, Quirk C, et al (2013) Joint language and translation modeling with recurrent neural networks. Am J Psychoanal 74(2):212\u20133","journal-title":"Am J Psychoanal"},{"key":"6653_CR2","doi-asserted-by":"crossref","unstructured":"Bell S, Zitnick CL, Bala K, et al (2016) Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2874\u20132883","DOI":"10.1109\/CVPR.2016.314"},{"key":"6653_CR3","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-319-54193-8_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"Chenyi Chen","year":"2017","unstructured":"Chen C, Liu MY, Tuzel O, et al (2016) R-cnn for small object detection. In: Asian conference on computer vision. Springer, Cham, pp 214\u2013230"},{"issue":"3","key":"6653_CR4","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"6653_CR5","doi-asserted-by":"crossref","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, vol 1. IEEE, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"6653_CR6","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, et al (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition CVPR. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"6653_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Gool LV, Williams CKI, et al (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"issue":"5","key":"6653_CR8","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1109\/TIP.2017.2675341","volume":"26","author":"Y Gao","year":"2017","unstructured":"Gao Y, Ma J, Yuille AL (2017) Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples. IEEE Trans Image Process 26(5):2545\u20132560","journal-title":"IEEE Trans Image Process"},{"issue":"9","key":"6653_CR9","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TMM.2017.2729019","volume":"19","author":"L Gao","year":"2017","unstructured":"Gao L, Guo Z, Zhang H, et al (2017) Video captioning with attention-based lstm and semantic consistency. IEEE Trans Multimed 19(9):2045\u20132055","journal-title":"IEEE Trans Multimed"},{"key":"6653_CR10","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2015) Object detection via a multi-region and semantic segmentation-aware cnn model. In: Proceedings of the IEEE international conference on computer vision, pp 1134\u20131142","DOI":"10.1109\/ICCV.2015.135"},{"key":"6653_CR11","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2016) Locnet: improving localization accuracy for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 789\u2013798","DOI":"10.1109\/CVPR.2016.92"},{"key":"6653_CR12","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. Computer Science","DOI":"10.1109\/ICCV.2015.169"},{"issue":"1","key":"6653_CR13","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2016","unstructured":"Girshick R, Donahue J, Darrell T, et al (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38(1):142\u2013158","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6653_CR14","doi-asserted-by":"crossref","unstructured":"Gkioxari G, Girshick R, Malik J (2015) Contextual action recognition with r* cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1080\u20131088","DOI":"10.1109\/ICCV.2015.129"},{"key":"6653_CR15","doi-asserted-by":"crossref","unstructured":"Guo Z, Gao L, Song J, et al (2016) Attention-based LSTM with semantic consistency for videos captioning. In: Proceedings of the 2016 ACM on multimedia conference. ACM, pp 357\u2013361","DOI":"10.1145\/2964284.2967242"},{"key":"6653_CR16","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollr P, et al (2017) Mask r-cnn. In: 2017 IEEE international conference on computer vision (ICCV). IEEE, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"6653_CR17","first-page":"346","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Kaiming He","year":"2014","unstructured":"He K, Zhang X, Ren S, et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. In: European conference on computer vision. Springer, Cham, pp 346\u2013361"},{"key":"6653_CR18","unstructured":"Ho TK (1995) Random decision forests. In: Proceedings of the third international conference on document analysis and recognition, vol 1. IEEE, pp 278\u2013282"},{"key":"6653_CR19","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.patcog.2017.12.012","volume":"77","author":"Y Li","year":"2018","unstructured":"Li Y, Zhang Y (2018) Robust infrared small target detection using local steering kernel reconstruction. Pattern Recogn 77:113\u2013125","journal-title":"Pattern Recogn"},{"key":"6653_CR20","doi-asserted-by":"crossref","unstructured":"Li J, Liang X, Wei Y, et al (2017) Perceptual generative adversarial networks for small object detection. In: IEEE CVPR","DOI":"10.1109\/CVPR.2017.211"},{"issue":"2","key":"6653_CR21","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1109\/TGRS.2017.2756911","volume":"56","author":"Y Li","year":"2018","unstructured":"Li Y, Zhang Y, Huang X, et al (2018) Large-scale remote sensing image retrieval by deep hashing neural networks. IEEE Trans Geosci Remote Sens 56 (2):950\u2013965","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"6653_CR22","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Tsung-Yi Lin","year":"2014","unstructured":"Lin TY, Maire M, Belongie S, et al (2014) Microsoft coco: common objects in context., 8693, 740-755. (2014, September). Microsoft coco: Common objects in context. In: European conference on computer vision. Springer, Cham, pp 740\u2013755"},{"key":"6653_CR23","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision, vol 2. IEEE, pp 1150\u20131157","DOI":"10.1109\/ICCV.1999.790410"},{"issue":"2","key":"6653_CR24","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"6653_CR25","doi-asserted-by":"crossref","unstructured":"Minaeian S, Liu J, Son YJ (2018) Effective and efficient detection of moving targets from a UAV\u2019s Camera. IEEE transactions on intelligent transportation systems","DOI":"10.1109\/TITS.2017.2782790"},{"key":"6653_CR26","doi-asserted-by":"crossref","unstructured":"Najibi M, Rastegari M, Davis LS (2016) G-cnn: an iterative grid based object detector. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2369\u20132377","DOI":"10.1109\/CVPR.2016.260"},{"key":"6653_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen LD, Lin D, Lin Z, et al (2018) Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation. In: 2018 IEEE international symposium on circuits and systems (ISCAS). IEEE, pp 1\u20135","DOI":"10.1109\/ISCAS.2018.8351550"},{"issue":"7","key":"6653_CR28","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2000","unstructured":"Ojala T, Pietikainen M, Maenpaa T (2000) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971\u2013987","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6653_CR29","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, et al (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":"6653_CR30","unstructured":"Ren S, He K, Girshick R, et al (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"6653_CR31","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"6653_CR32","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"},{"issue":"3","key":"6653_CR33","doi-asserted-by":"publisher","first-page":"904","DOI":"10.3390\/s18030904","volume":"18","author":"T Tian","year":"2018","unstructured":"Tian T, Li C, Xu J, et al (2018) Urban area detection in very high resolution remote sensing images using deep convolutional neural networks. Sensors 18(3):904","journal-title":"Sensors"},{"issue":"2","key":"6653_CR34","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Sande KE, Gevers T, et al (2013) Selective search for object recognition. Int J Comput Vis 104(2):154\u2013171","journal-title":"Int J Comput Vis"},{"issue":"4","key":"6653_CR35","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1109\/LSP.2016.2611485","volume":"24","author":"X Wang","year":"2017","unstructured":"Wang X, Gao L, Song J, et al (2017) Beyond frame-level cnn: saliency-aware 3-d cnn with lstm for video action recognition. IEEE Signal Process Lett 24(4):510\u2013514","journal-title":"IEEE Signal Process Lett"},{"key":"6653_CR36","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.neucom.2017.08.063","volume":"275","author":"X Wang","year":"2018","unstructured":"Wang X, Gao L, Song J, et al (2018) Deep appearance and motion learning for egocentric activity recognition. Neurocomputing 275:438\u2013447","journal-title":"Neurocomputing"},{"issue":"3","key":"6653_CR37","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1109\/TMM.2017.2749159","volume":"20","author":"X Wang","year":"2018","unstructured":"Wang X, Gao L, Wang P, et al (2018) Two-stream 3-d convnet fusion for action recognition in videos with arbitrary size and length. IEEE Trans Multimed 20 (3):634\u2013644","journal-title":"IEEE Trans Multimed"},{"key":"6653_CR38","doi-asserted-by":"crossref","unstructured":"Xu D, Ricci E, Yan Y, et al (2015) Learning deep representations of appearance and motion for anomalous event detection. BMVC","DOI":"10.5244\/C.29.8"},{"key":"6653_CR39","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-91635-4_1","volume-title":"Advanced Computing Strategies for Engineering","author":"Nobuyoshi Yabuki","year":"2018","unstructured":"Yabuki N, Nishimura N, Fukuda T (2018) Automatic object detection from digital images by deep learning with transfer learning. In: Workshop of the European group for intelligent computing in engineering. Springer, Cham, pp 3\u201315"},{"key":"6653_CR40","doi-asserted-by":"crossref","unstructured":"Yang Z, Yu W, Liang P, et al (2018) Deep transfer learning for military object recognition under small training set condition. Neural Comput Applic, 1\u201310","DOI":"10.1007\/s00521-018-3468-3"},{"key":"6653_CR41","unstructured":"Zhu Y, Urtasun R, Salakhutdinov R, et al (2015) segdeepm: exploiting segmentation and context in deep neural networks for object detection. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 4703\u20134711"},{"key":"6653_CR42","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"C. Lawrence Zitnick","year":"2014","unstructured":"Zitnick CL, Dollr P (2014) Edge boxes: locating object proposals from edges. In: European conference on computer vision. Springer, Cham, pp 391\u2013405"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6653-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6653-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6653-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T21:59:06Z","timestamp":1761083946000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6653-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,2]]},"references-count":42,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["6653"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6653-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,2]]},"assertion":[{"value":"9 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}