{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T14:26:26Z","timestamp":1784989586824,"version":"3.55.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319541921","type":"print"},{"value":"9783319541938","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-54193-8_14","type":"book-chapter","created":{"date-parts":[[2017,3,10]],"date-time":"2017-03-10T04:24:07Z","timestamp":1489119847000},"page":"214-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":285,"title":["R-CNN for Small Object Detection"],"prefix":"10.1007","author":[{"given":"Chenyi","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oncel","family":"Tuzel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxiong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,3,11]]},"reference":[{"key":"14_CR1","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, C.K., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Torralba, A., Efros, A., et al.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521\u20131528 (2011)","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1109\/TPAMI.2010.182","volume":"33","author":"A Kembhavi","year":"2011","unstructured":"Kembhavi, A., Harwood, D., Davis, L.S.: Vehicle detection using partial least squares. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1250\u20131265 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Morariu, V., Ahmed, E., Santhanam, V., Harwood, D., Davis, L.S., et al.: Composite discriminant factor analysis. In: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 564\u2013571 (2014)","DOI":"10.1109\/WACV.2014.6836052"},{"key":"14_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-33712-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D Hoiem","year":"2012","unstructured":"Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 340\u2013353. Springer, Heidelberg (2012). doi:\n                      10.1007\/978-3-642-33712-3_25"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10602-1_48"},{"key":"14_CR9","first-page":"1","volume":"119","author":"J Xiao","year":"2014","unstructured":"Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: Sun database: exploring a large collection of scene categories. Int. J. Comput. Vis. 119, 1\u201320 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10602-1_26"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Kuo, W., Hariharan, B., Malik, J.: DeepBox: learning objectness with convolutional networks. arXiv preprint \n                      arXiv:1505.02146\n                      \n                     (2015)","DOI":"10.1109\/ICCV.2015.285"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2155\u20132162 (2014)","DOI":"10.1109\/CVPR.2014.276"},{"key":"14_CR14","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A., Hebert, M., et al.: An empirical study of context in object detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1271\u20131278 (2009)","DOI":"10.1109\/CVPRW.2009.5206532"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M., et al.: Context-based vision system for place and object recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 273\u2013280 (2003)","DOI":"10.1109\/ICCV.2003.1238354"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R*CNN. arXiv preprint \n                      arXiv:1505.01197\n                      \n                     (2015)","DOI":"10.1109\/ICCV.2015.129"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. arXiv preprint \n                      arXiv:1505.01749\n                      \n                     (2015)","DOI":"10.1109\/ICCV.2015.135"},{"key":"14_CR19","unstructured":"Zhu, Y., Urtasun, R., Salakhutdinov, R., Fidler, S.: segDeepM: exploiting segmentation and context in deep neural networks for object detection. arXiv preprint \n                      arXiv:1502.04275\n                      \n                     (2015)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N.G., Lee, S.W., Fidler, S., Urtasun, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sohn, K., Villegas, R., Pan, G., Lee, H.: Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction. arXiv preprint \n                      arXiv:1504.03293\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2015.7298621"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Yoo, D., Park, S., Lee, J.Y., Paek, A., Kweon, I.S.: AttentionNet: aggregating weak directions for accurate object detection. arXiv preprint \n                      arXiv:1506.07704\n                      \n                     (2015)","DOI":"10.1109\/ICCV.2015.305"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. arXiv preprint \n                      arXiv:1506.02640\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.91"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.: SSD: single shot multibox detector. arXiv preprint \n                      arXiv:1512.02325\n                      \n                     (2015)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"14_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/978-3-319-24947-6_43","volume-title":"Pattern Recognition","author":"B Pepik","year":"2015","unstructured":"Pepik, B., Benenson, R., Ritschel, T., Schiele, B.: What is holding back convnets for detection? In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 517\u2013528. Springer, Heidelberg (2015). doi:\n                      10.1007\/978-3-319-24947-6_43"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Liu, M.Y., Mallya, A., Tuzel, O., Chen, X.: Unsupervised network pretraining via encoding human design. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1\u20139. IEEE (2016)","DOI":"10.1109\/WACV.2016.7477698"},{"key":"14_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \n                      arXiv:1409.1556\n                      \n                     (2014)"},{"key":"14_CR28","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR29","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-54193-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T01:46:21Z","timestamp":1558316781000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-54193-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319541921","9783319541938"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-54193-8_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"11 March 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.accv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}