{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T02:07:42Z","timestamp":1777169262270,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319458854","type":"print"},{"value":"9783319458861","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-45886-1_16","type":"book-chapter","created":{"date-parts":[[2016,8,26]],"date-time":"2016-08-26T08:41:50Z","timestamp":1472200910000},"page":"192-204","source":"Crossref","is-referenced-by-count":54,"title":["A Convnet for Non-maximum Suppression"],"prefix":"10.1007","author":[{"given":"Jan","family":"Hosang","sequence":"first","affiliation":[]},{"given":"Rodrigo","family":"Benenson","sequence":"additional","affiliation":[]},{"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,27]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1109\/TPAMI.2012.79","volume":"34","author":"O Barinova","year":"2012","unstructured":"Barinova, O., Lempitsky, V., Kholi, P.: On detection of multiple object instances using Hough transforms. PAMI 34, 1773\u20131784 (2012)","journal-title":"PAMI"},{"key":"16_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1007\/978-3-642-15567-3_13","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L Bourdev","year":"2010","unstructured":"Bourdev, L., Maji, S., Brox, T., Malik, J.: Detecting people using mutually consistent poselet activations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 168\u2013181. Springer, Heidelberg (2010)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Chen, G., Ding, Y., Xiao, J., Han, T.X.: Detection evolution with multi-order contextual co-occurrence. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.235"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Convolutional feature masking for joint object and stuff segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"16_CR6","doi-asserted-by":"crossref","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. PAMI 34, 743\u2013761 (2012)","journal-title":"PAMI"},{"key":"16_CR7","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. IJCV 111, 98\u2013136 (2015)","journal-title":"IJCV"},{"key":"16_CR8","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"P Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. PAMI 32, 1627\u20131645 (2010)","journal-title":"PAMI"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Ferryman, J., Ellis, A.: Pets 2010: dataset and challenge. In: AVSS (2010)","DOI":"10.1109\/AVSS.2010.90"},{"key":"16_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 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"16_CR14","doi-asserted-by":"crossref","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, 814\u2013830 (2015)","journal-title":"PAMI"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. In: ACM International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"16_CR16","unstructured":"Kingma, D., Ba, J.: ADAM: a method for stochastic optimization. In: ICLR (2015)"},{"key":"16_CR17","first-page":"1149","volume":"116","author":"P Kontschieder","year":"2012","unstructured":"Kontschieder, P., Rota Bul\u00f2, S., Donoser, M., Pelillo, M., Bischof, H.: Evolutionary Hough games for coherent object detection. CVIU 116, 1149\u20131158 (2012)","journal-title":"CVIU"},{"key":"16_CR18","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s11263-007-0095-3","volume":"77","author":"B Leibe","year":"2008","unstructured":"Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV 77, 259\u2013289 (2008)","journal-title":"IJCV"},{"key":"16_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Heidelberg (2014)"},{"key":"16_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1007\/978-3-319-10593-2_47","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Mathias","year":"2014","unstructured":"Mathias, M., Benenson, R., Pedersoli, M., Van Gool, L.: Face detection without bells and whistles. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part IV. LNCS, vol. 8692, pp. 720\u2013735. Springer, Heidelberg (2014)"},{"key":"16_CR21","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/TPAMI.2013.103","volume":"36","author":"A Milan","year":"2014","unstructured":"Milan, A., Roth, S., Schindler, K.: Continuous energy minimization for multitarget tracking. PAMI 36, 58\u201372 (2014)","journal-title":"PAMI"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Ouyang, W., Wang, X.: Single-pedestrian detection aided by multi-pedestrian detection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.411"},{"key":"16_CR23","unstructured":"Parikh, D., Zitnick, C.: Human-debugging of machines. In: NIPS WCSSWC (2011)"},{"key":"16_CR24","unstructured":"Pinheiro, P.O., Collobert, R., Dollar, P.: Learning to segment object candidates. In: NIPS (2015)"},{"key":"16_CR25","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":"16_CR26","doi-asserted-by":"crossref","unstructured":"Rodriguez, M., Laptev, I., Sivic, J., Audibert, J.Y.: Density-aware person detection and tracking in crowds. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126526"},{"key":"16_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1007\/978-3-319-16865-4_19","volume-title":"Computer Vision \u2013 ACCV 2014","author":"R Rothe","year":"2015","unstructured":"Rothe, R., Guillaumin, M., Van Gool, L.: Non-maximum Suppression for Object Detection by Passing Messages Between Windows. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9003, pp. 290\u2013306. Springer, Heidelberg (2015)"},{"key":"16_CR28","doi-asserted-by":"crossref","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., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Sadeghi, M.A., Farhadi, A.: Recognition using visual phrases. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"16_CR30","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)"},{"key":"16_CR31","unstructured":"Shu, G., Dehghan, A., Oreifej, O., Hand, E., Shah, M.: Part-based multiple-person tracking with partial occlusion handling. In: CVPR (2012)"},{"key":"16_CR32","unstructured":"Stewart, R., Andriluka, M.: End-to-end people detection in crowded scenes (2015). arXiv:1506.04878"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Subburaman, V.B., Descamps, A., Carincotte, C.: Counting people in the crowd using a generic head detector. In: AVSS (2012)","DOI":"10.1109\/AVSS.2012.87"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Schiele, B.: Detection and tracking of occluded people. In: BMVC (2012)","DOI":"10.5244\/C.26.9"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Tang, S., Andres, B., Andriluka, M., Schiele, B.: Subgraph decomposition for multi-target tracking. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299138"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., Schiele, B.: Learning people detectors for tracking in crowded scenes. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.134"},{"key":"16_CR37","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2009.186","volume":"32","author":"Z Tu","year":"2010","unstructured":"Tu, Z., Bai, X.: Auto-context and its application to high-level vision tasks and 3D brain image segmentation. PAMI 32, 1744\u20131757 (2010)","journal-title":"PAMI"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Vezhnevets, A., Ferrari, V.: Object localization in imagenet by looking out of the window. In: BMVC (2015)","DOI":"10.5244\/C.29.27"},{"key":"16_CR39","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.: Robust real-time face detection. IJCV 57, 137\u2013154 (2004)","journal-title":"IJCV"},{"key":"16_CR40","unstructured":"Wan, L., Eigen, D., Fergus, R.: End-to-end integration of a convolutional network, deformable parts model and non-maximum suppression. In: CVPR (2015)"},{"key":"16_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1007\/978-3-642-37331-2_23","volume-title":"Computer Vision \u2013 ACCV 2012","author":"P Wohlhart","year":"2013","unstructured":"Wohlhart, P., Donoser, M., Roth, P.M., Bischof, H.: Detecting partially occluded objects with an implicit shape model random field. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 302\u2013315. Springer, Heidelberg (2013)"},{"key":"16_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/978-3-540-69321-5_8","volume-title":"Pattern Recognition","author":"C Wojek","year":"2008","unstructured":"Wojek, C., Dork\u00f3, G., Schulz, A., Schiele, B.: Sliding-windows for rapid object class localization: a parallel technique. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 71\u201381. Springer, Heidelberg (2008)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Yan, J., Yu, Y., Zhu, X., Lei, Z., Li, S.Z.: Object detection by labeling superpixels. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299146"},{"key":"16_CR44","unstructured":"Yao, J., Fidler, S., Urtasun, R.: Describing the scene as a whole: joint object detection, scene classification and semantic segmentation. In: CVPR (2012)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-45886-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,12]],"date-time":"2019-09-12T20:17:37Z","timestamp":1568319457000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-45886-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319458854","9783319458861"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-45886-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}