{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T07:08:37Z","timestamp":1790492917253,"version":"4.1.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012663","type":"print"},{"value":"9783030012670","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01267-0_28","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T13:02:36Z","timestamp":1538830956000},"page":"473-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":191,"title":["Revisiting RCNN: On Awakening the Classification Power of Faster RCNN"],"prefix":"10.1007","author":[{"given":"Bowen","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghui","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjun","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Brandt, J.: Robust object detection via soft cascade. In: IEEE CVPR, vol. 2, pp. 236\u2013243 (2005)","DOI":"10.1109\/CVPR.2005.310"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: IEEE CVPR, June 2018","DOI":"10.1109\/CVPR.2018.00644"},{"key":"28_CR3","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379\u2013387 (2016)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: IEEE ICCV, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"28_CR6","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.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"issue":"9","key":"28_CR7","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 TPAMI 32(9), 1627\u20131645 (2010)","journal-title":"IEEE TPAMI"},{"issue":"1","key":"28_CR8","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119\u2013139 (1997)","journal-title":"J. Comput. Syst. Sci."},{"key":"28_CR9","unstructured":"Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"28_CR12","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"28_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Li, H., Lin, Z., Shen, X., Brandt, J., Hua, G.: A convolutional neural network cascade for face detection. In: IEEE CVPR, pp. 5325\u20135334 (2015)","DOI":"10.1109\/CVPR.2015.7299170"},{"issue":"7","key":"28_CR17","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1109\/TMM.2017.2772796","volume":"20","author":"Jianan Li","year":"2018","unstructured":"Li, J., et al.: Multistage object detection with group recursive learning. IEEE Trans. Multimed. 20(7), 1645\u20131655 (2018)","journal-title":"IEEE Transactions on Multimedia"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.211"},{"issue":"5","key":"28_CR19","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"Jianan Li","year":"2017","unstructured":"Li, J., et al.: Attentive contexts for object detection. IEEE Trans. Multimed. 19(5), 944\u2013954 (2017)","journal-title":"IEEE Transactions on Multimedia"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Liang, X., Liu, S., Wei, Y., Liu, L., Lin, L., Yan, S.: Towards computational baby learning: a weakly-supervised approach for object detection. In: IEEE ICCV, pp. 999\u20131007 (2015)","DOI":"10.1109\/ICCV.2015.120"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: IEEE CVPR, vol. 1, p. 4 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: IEEE ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"28_CR23","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, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"28_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE CVPR, pp. 6517\u20136525 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"28_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"28_CR28","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"issue":"2","key":"28_CR29","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. IJCV 104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"issue":"2","key":"28_CR30","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time face detection. IJCV 57(2), 137\u2013154 (2004)","journal-title":"IJCV"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Wei, Y., et al.: TS2C: tight box mining with surrounding segmentation context for weakly supervised object detection. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_27"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE CVPR, pp. 5987\u20135995 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Xu, H., Lv, X., Wang, X., Ren, Z., Chellappa, R.: Deep regionlets for object detection. arXiv preprint arXiv:1712.02408 (2017)","DOI":"10.1007\/978-3-030-01252-6_49"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01267-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:48:14Z","timestamp":1775242094000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01267-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012663","9783030012670"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01267-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}