{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T10:20:02Z","timestamp":1785320402705,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464923","type":"print"},{"value":"9783319464930","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46493-0_22","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T14:59:53Z","timestamp":1474037993000},"page":"354-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":936,"title":["A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection"],"prefix":"10.1007","author":[{"given":"Zhaowei","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanfu","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rogerio S.","family":"Feris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuno","family":"Vasconcelos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"issue":"2","key":"22_CR1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"PA Viola","year":"2004","unstructured":"Viola, P.A., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"issue":"8","key":"22_CR2","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r, P., Appel, R., Belongie, S.J., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532\u20131545 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587(2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: ICCV, pp. 1440\u20131448(2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"22_CR5","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A., Ma, H., Fidler, S., Urtasun, R.: 3D object proposals for accurate object class detection. In: NIPS (2015)"},{"key":"22_CR6","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, Heidelberg (2014). doi: 10.1007\/978-3-319-10578-9_23"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: ICCV, pp. 1134\u20131142(2015)","DOI":"10.1109\/ICCV.2015.135"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"van de Sande, K.E.A., Uijlings, J.R.R., Gevers, T., Smeulders, A.W.M.: Segmentation as selective search for object recognition. In: ICCV, pp. 1879\u20131886(2011)","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"22_CR9","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: CVPR, pp. 3354\u20133361(2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV, pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"issue":"4","key":"22_CR13","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Doll\u00e1r","year":"2012","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: An evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743\u2013761 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Bourdev, L.D., Brandt, J.: Robust object detection via soft cascade. In: CVPR, pp. 236\u2013243 (2005)","DOI":"10.1109\/CVPR.2005.310"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Cai, Z., Saberian, M.J., Vasconcelos, N.: Learning complexity-aware cascades for deep pedestrian detection. In: ICCV, pp. 3361\u20133369 (2015)","DOI":"10.1109\/ICCV.2015.384"},{"issue":"5","key":"22_CR16","doi-asserted-by":"publisher","first-page":"2511","DOI":"10.1109\/TITS.2015.2409889","volume":"16","author":"E Ohn-Bar","year":"2015","unstructured":"Ohn-Bar, E., Trivedi, M.M.: Learning to detect vehicles by clustering appearance patterns. IEEE Trans. Intell. Transp. Syst. 16(5), 2511\u20132521 (2015)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"1","key":"22_CR17","first-page":"2569","volume":"15","author":"MJ Saberian","year":"2014","unstructured":"Saberian, M.J., Vasconcelos, N.: Boosting algorithms for detector cascade learning. J. Mach. Learn. Res. 15(1), 2569\u20132605 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106\u20131114(2012)"},{"issue":"9","key":"22_CR19","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.A., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., Yang, M., Zhu, S., Lin, Y.: Regionlets for generic object detection. In: ICCV, pp. 17\u201324 (2013)","DOI":"10.1109\/ICCV.2013.10"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"22_CR23","unstructured":"Lee, C., Xie, S., Gallagher, P.W., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: AISTATS (2015)"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Benenson, R., Mathias, M., Timofte, R., Gool, L.J.V.: Pedestrian detection at 100 frames per second. In: CVPR, pp. 2903\u20132910 (2012)","DOI":"10.1109\/CVPR.2012.6248017"},{"key":"22_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Bell, S., Zitnick, C.L., Bala, K., Girshick, R.B.: Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.314"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Urtasun, R., Salakhutdinov, R., Fidler, S.: segDeepM: Exploiting segmentation and context in deep neural networks for object detection. In: CVPR, pp. 4703\u20134711 (2015)","DOI":"10.1109\/CVPR.2015.7299102"},{"issue":"2","key":"22_CR28","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, L.J.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"22_CR29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R.B., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. In: MM, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"issue":"4","key":"22_CR31","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1109\/TPAMI.2015.2465908","volume":"38","author":"J Hosang","year":"2015","unstructured":"Hosang, J., Benenson, R., Doll\u00e1r, P., Schiele, B.: What makes for effective detection proposals? PAMI 38(4), 814\u2013830 (2015)","journal-title":"PAMI"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Cheng, M., Zhang, Z., Lin, W., Torr, P.H.S.: BING: binarized normed gradients for objectness estimation at 300fps. In: CVPR, pp. 3286\u20133293 (2014)","DOI":"10.1109\/CVPR.2014.414"},{"key":"22_CR33","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: 10.1007\/978-3-319-10602-1_26"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P.A., Pont-Tuset, J., Barron, J.T., Marqu\u00e9s, F., Malik, J.: Multiscale combinatorial grouping. In: CVPR, pp. 328\u2013335 (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"22_CR35","unstructured":"Geiger, A., Wojek, C., Urtasun, R.: Joint 3D estimation of objects and scene layout. In: NIPS, pp. 1467\u20131475 (2011)"},{"issue":"11","key":"22_CR36","doi-asserted-by":"publisher","first-page":"2232","DOI":"10.1109\/TPAMI.2015.2408347","volume":"37","author":"B Pepik","year":"2015","unstructured":"Pepik, B., Stark, M., Gehler, P.V., Schiele, B.: Multi-view and 3D deformable part models. IEEE Trans. Pattern Anal. Mach. Intell. 37(11), 2232\u20132245 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Choi, W., Lin, Y., Savarese, S.: Data-driven 3D voxel patterns for object category recognition. In: CVPR, pp. 1903\u20131911 (2015)","DOI":"10.1109\/CVPR.2015.7298800"},{"key":"22_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1007\/978-3-319-10599-4_42","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Li","year":"2014","unstructured":"Li, B., Wu, T., Zhu, S.-C.: Integrating context and occlusion for car detection by hierarchical and-or model. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 652\u2013667. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10599-4_42"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Tian, Y., Luo, P., Wang, X., Tang, X.: Deep learning strong parts for pedestrian detection. In: ICCV, pp. 1904\u20131912 (2015)","DOI":"10.1109\/ICCV.2015.221"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Schiele, B.: Filtered channel features for pedestrian detection. In: CVPR, pp. 1751\u20131760 (2015)","DOI":"10.1109\/CVPR.2015.7298784"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Paisitkriangkrai, S., Shen, C., van den Hengel, A.: Pedestrian detection with spatially pooled features and structured ensemble learning. CoRR abs\/1409.5209 (2014)","DOI":"10.1007\/978-3-319-10593-2_36"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Yang, F., Choi, W., Lin, Y.: Exploit all the layers: Fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers. In: CVPR. (2016)","DOI":"10.1109\/CVPR.2016.234"},{"key":"22_CR43","unstructured":"Nam, W., Doll\u00e1r, P., Han, J.H.: Local decorrelation for improved pedestrian detection. In: NIPS, pp. 424\u2013432 (2014)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46493-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:21:11Z","timestamp":1749583271000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46493-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464923","9783319464930"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}