{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T09:01:06Z","timestamp":1725872466054},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319488950"},{"type":"electronic","value":"9783319488967"}],"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\/978-3-319-48896-7_21","type":"book-chapter","created":{"date-parts":[[2016,11,26]],"date-time":"2016-11-26T09:18:05Z","timestamp":1480151885000},"page":"210-220","source":"Crossref","is-referenced-by-count":1,"title":["Category Aggregation Among Region Proposals for Object Detection"],"prefix":"10.1007","author":[{"given":"Linghui","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianshe","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,27]]},"reference":[{"key":"21_CR1","unstructured":"Sermanet, P., Eigen, D., Zhang, X., et al.: Overfeat integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2241\u20132248. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"21_CR3","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)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"21_CR5","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"21_CR7","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":"21_CR8","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: 2010 IEEE Conference on IEEE Computer Vision and Pattern Recognition (CVPR), pp. 73\u201380 (2010)","DOI":"10.1109\/CVPR.2010.5540226"},{"issue":"2","key":"21_CR9","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., et al.: Selective search for object recognition. Int. J. Comput. Vision 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, M.M., Zhang, Z., Lin, W.Y., et al.: BING: binarized normed gradients for objectness estimation at 300fps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3286\u20133293 (2014)","DOI":"10.1109\/CVPR.2014.414"},{"key":"21_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: 10.1007\/978-3-319-10602-1_26"},{"key":"21_CR12","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., et al.: Scalable object detection using deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132154 (2014)","DOI":"10.1109\/CVPR.2014.276"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Arbelez, P., Pont-Tuset, J., Barron, J., et al.: Multiscale combinatorial grouping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 328\u2013335 (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Qi, G.J., Hua, X.S., Rui, Y., et al.: Correlative multi-label video annotation. In: Proceedings of the 15th International Conference on Multimedia, pp. 17\u201326. ACM (2007)","DOI":"10.1145\/1291233.1291245"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, W., Chang, S.F., Loui, A.C.: Active context-based concept fusion with partial user labels. In: 2006 IEEE International Conference on Image Processing, pp. 2917\u20132920. IEEE (2006)","DOI":"10.1109\/ICIP.2006.313129"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: 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 (2015)","DOI":"10.1109\/ICCV.2015.135"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Ouyang, W., Wang, X., Zeng, X., et al.: DeepID-net: deformable deep convolutional neural networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403\u20132412 (2015)","DOI":"10.1109\/CVPR.2015.7298854"},{"issue":"9","key":"21_CR19","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Weng, M.F., Chuang, Y.Y.: Multi-cue fusion for semantic video indexing. In: Proceedings of the 16th ACM International Conference on Multimedia, pp. 71\u201380. ACM (2008)","DOI":"10.1145\/1459359.1459370"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Choi, M.J., Lim, J.J., Torralba, A., et al.: Exploiting hierarchical context on a large database of object categories. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 129\u2013136. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540221"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., et al.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1717\u20131724 (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zheng, L., Wang, S., Liu, Z., et al.: Packing, padding: coupled multi-index for accurate image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1939\u20131946 (2014)","DOI":"10.1109\/CVPR.2014.250"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing - PCM 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-48896-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,15]],"date-time":"2019-09-15T20:26:48Z","timestamp":1568579208000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-48896-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319488950","9783319488967"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48896-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}