{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T10:38:28Z","timestamp":1756895908458,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,3,15]],"date-time":"2017-03-15T00:00:00Z","timestamp":1489536000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"CAMETRON"},{"name":"KU Leuven FWO scholarship"},{"name":"KU Leuven DBOF PhD scholarship"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1007\/s11263-017-1006-x","type":"journal-article","created":{"date-parts":[[2017,3,15]],"date-time":"2017-03-15T10:29:41Z","timestamp":1489573781000},"page":"115-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers"],"prefix":"10.1007","volume":"124","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-9269","authenticated-orcid":false,"given":"Amir","family":"Ghodrati","sequence":"first","affiliation":[]},{"given":"Ali","family":"Diba","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Pedersoli","sequence":"additional","affiliation":[]},{"given":"Tinne","family":"Tuytelaars","sequence":"additional","affiliation":[]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,3,15]]},"reference":[{"key":"1006_CR1","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselaers, T., & Ferrari, V. (2010). What is an object? In CVPR","DOI":"10.1109\/CVPR.2010.5540226"},{"issue":"5","key":"1006_CR2","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbelaez","year":"2011","unstructured":"Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour detection and hierarchical image segmentation. PAMI, 33(5), 898\u2013916.","journal-title":"PAMI"},{"key":"1006_CR3","doi-asserted-by":"crossref","unstructured":"Arbelaez, P., Pont-Tuset, J., Barron, J., Marques, F., & Malik, J. (2014). Multiscale combinatorial grouping. In CVPR","DOI":"10.1109\/CVPR.2014.49"},{"key":"1006_CR4","doi-asserted-by":"crossref","unstructured":"Bergh, M., Roig, G., Boix, X., Manen, S., & Gool, L. (2013). Online video seeds for temporal window objectness. In ICCV","DOI":"10.1109\/ICCV.2013.54"},{"key":"1006_CR5","doi-asserted-by":"crossref","unstructured":"Bilen, H., Pedersoli, M., & Tuytelaars, T. (2015). Weakly supervised object detection with convex clustering. In CVPR","DOI":"10.1109\/CVPR.2015.7298711"},{"key":"1006_CR6","doi-asserted-by":"crossref","unstructured":"Brox, T., & Malik, J. (2010). Object segmentation by long term analysis of point trajectories. In ECCV","DOI":"10.1007\/978-3-642-15555-0_21"},{"issue":"7","key":"1006_CR7","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1109\/TPAMI.2011.231","volume":"34","author":"J Carreira","year":"2012","unstructured":"Carreira, J., & Sminchisescu, C. (2012). Cpmc: Automatic object segmentation using constrained parametric min-cuts. PAMI, 34(7), 1312\u20131328.","journal-title":"PAMI"},{"key":"1006_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, M. M., Zhang, Z., Lin, W. Y., & Torr, P. (2014). Bing: Binarized normed gradients for objectness estimation at 300fps. In CVPR","DOI":"10.1109\/CVPR.2014.414"},{"key":"1006_CR9","doi-asserted-by":"crossref","unstructured":"Cinbis, R. G., Verbeek, J., & Schmid, C. (2013). Segmentation driven object detection with fisher vectors. In ICCV","DOI":"10.1109\/ICCV.2013.369"},{"key":"1006_CR10","doi-asserted-by":"crossref","unstructured":"Deselaers, T., Alexe, B., & Ferrari, V. (2010). Localizing objects while learning their appearance. In ECCV","DOI":"10.1007\/978-3-642-15561-1_33"},{"key":"1006_CR11","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., & Zitnick, C. L. (2013). Structured forests for fast edge detection. In ICCV","DOI":"10.1109\/ICCV.2013.231"},{"key":"1006_CR12","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., & Anguelov, D. (2014). Scalable object detection using deep neural networks. In CVPR","DOI":"10.1109\/CVPR.2014.276"},{"issue":"2","key":"1006_CR13","doi-asserted-by":"crossref","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. (2010). The pascal visual object classes (voc) challenge. IJCV, 88(2), 303\u2013338.","journal-title":"IJCV"},{"key":"1006_CR14","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., & Lin, C. J. (2008). Liblinear: A library for large linear classification. The Journal of Machine Learning Research, 9, 1871\u20131874.","journal-title":"The Journal of Machine Learning Research"},{"key":"1006_CR15","doi-asserted-by":"crossref","unstructured":"Ghodrati, A., Diba, A., Pedersoli, M., Tuytelaars, T., & Van\u00a0Gool, L. (2015). Deepproposal: Hunting objects by cascading deep convolutional layers. In ICCV","DOI":"10.1109\/ICCV.2015.296"},{"key":"1006_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. In ICCV","DOI":"10.1109\/ICCV.2015.169"},{"key":"1006_CR17","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR","DOI":"10.1109\/CVPR.2014.81"},{"key":"1006_CR18","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., & Malik, J. (2015). Finding action tubes. In CVPR","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"1006_CR19","unstructured":"Hariharan, B., Arbelez, P., Girshick, R., & Malik, J. (2014). Hypercolumns for object segmentation and fine-grained localization. arXiv preprint arXiv:1411:5752"},{"issue":"9","key":"1006_CR20","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., & Sun, J. (2015). Spatial pyramid pooling in deep convolutional networks for visual recognition. PAMI, 37(9), 1904\u20131916.","journal-title":"PAMI"},{"issue":"4","key":"1006_CR21","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. (2015). What makes for effective detection proposals? PAMI, 38(4), 814\u2013830.","journal-title":"PAMI"},{"key":"1006_CR22","doi-asserted-by":"crossref","unstructured":"Jain, M., Gemert, J., J.\u00e9gou, H., Bouthemy, P., & Snoek, C. (2014). Action localization with tubelets from motion. In CVPR","DOI":"10.1109\/CVPR.2014.100"},{"key":"1006_CR23","doi-asserted-by":"crossref","unstructured":"Kr\u00e4henb\u00fchl, P., & Koltun, V. (2014). Geodesic object proposals. In ECCV","DOI":"10.1007\/978-3-319-10602-1_47"},{"key":"1006_CR24","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In NIPS"},{"key":"1006_CR25","unstructured":"Lan, T., Wang, Y., & Mori, G. (2011). Discriminative figure-centric models for joint action localization and recognition. In ICCV"},{"key":"1006_CR26","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR"},{"key":"1006_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick C. L. (2014a). Microsoft coco: Common objects in context. In ECCV","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1006_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick C. L. (2014b). Microsoft coco: Common objects in context. In ECCV","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1006_CR29","doi-asserted-by":"crossref","unstructured":"Manen, S., Guillaumin, M., & Gool, L. V. (2013). Prime object proposals with randomized prim\u2019s algorithm. In ICCV","DOI":"10.1109\/ICCV.2013.315"},{"key":"1006_CR30","doi-asserted-by":"crossref","unstructured":"Oneata, D., Revaud, J., Verbeek, J., & Schmid, C. (2014). Spatio-temporal object detection proposals. In ECCV","DOI":"10.1007\/978-3-319-10578-9_48"},{"key":"1006_CR31","unstructured":"Pinheiro, P. O., Collobert, R., & Dollar, P. (2015). Learning to segment object candidates. In NIPS"},{"key":"1006_CR32","doi-asserted-by":"crossref","unstructured":"Pinheiro, P. O., Lin, T. Y., Collobert, R., & Doll\u00e1r, P. (2016). Learning to refine object segments. In ECCV","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"1006_CR33","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS"},{"key":"1006_CR34","doi-asserted-by":"crossref","unstructured":"Rodriguez, M. D., Ahmed, J., & Shah, M. (2008). Action mach a spatio-temporal maximum average correlation height filter for action recognition. In CVPR","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"1006_CR35","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229"},{"key":"1006_CR36","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In ICLR"},{"key":"1006_CR37","unstructured":"Song, H. O., Girshick, R., Jegelka, S., Mairal, J., Harchaoui, Z., & Darrell, T. (2014). On learning to localize objects with minimal supervision. In ICML"},{"key":"1006_CR38","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402"},{"issue":"2","key":"1006_CR39","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1109\/TPAMI.2013.137","volume":"36","author":"D Tran","year":"2014","unstructured":"Tran, D., Yuan, J., & Forsyth, D. (2014). Video event detection: From subvolume localization to spatiotemporal path search. PAMI, 36(2), 404\u2013416.","journal-title":"PAMI"},{"key":"1006_CR40","doi-asserted-by":"crossref","unstructured":"van Gemert, J. C., Jain, M., Gati, E., & Snoek, C. G. (2015). Apt: Action localization proposals from dense trajectories. In BMVC","DOI":"10.5244\/C.29.177"},{"key":"1006_CR41","doi-asserted-by":"crossref","unstructured":"Van\u00a0de Sande, K. E., Uijlings, J. R., Gevers, T., & Smeulders, A. W. (2011). Segmentation as selective search for object recognition. In ICCV","DOI":"10.1109\/ICCV.2011.6126456"},{"issue":"2","key":"1006_CR42","first-page":"137","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., & Jones, M. J. (2004). Robust real-time face detection. IJCV, 57(2), 137\u2013154.","journal-title":"Robust real-time face detection. IJCV"},{"key":"1006_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Yang, M., Zhu, S., & Lin, Y. (2013). Regionlets for generic object detection. In ICCV","DOI":"10.1109\/ICCV.2013.10"},{"key":"1006_CR44","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., & Schmid, C. (2015). Learning to track for spatio-temporal action localization. In ICCV","DOI":"10.1109\/ICCV.2015.362"},{"key":"1006_CR45","unstructured":"Xinggang, W., Yan, W., Xiang, B., & Zhijiang, Z. (2015). Deepcontour:, A. deep convolutional feature learned by positive-sharing loss for contour detection. In CVPR"},{"key":"1006_CR46","doi-asserted-by":"crossref","unstructured":"Yu, G., & Yuan, J. (2015). Fast action proposals for human action detection and search. In CVPR","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"1006_CR47","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In ECCV","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"1006_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Liu, Z., & Yin, B. (2014). Cracking bing and beyond. In BMVC","DOI":"10.5244\/C.28.23"},{"key":"1006_CR49","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., & Oliva, A. (2014). Learning deep features for scene recognition using places database. In NIPS"},{"key":"1006_CR50","doi-asserted-by":"crossref","unstructured":"Zitnick, C. L., & Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In ECCV","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-017-1006-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1006-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1006-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,19]],"date-time":"2019-09-19T15:34:42Z","timestamp":1568907282000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-017-1006-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,15]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,9]]}},"alternative-id":["1006"],"URL":"https:\/\/doi.org\/10.1007\/s11263-017-1006-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2017,3,15]]}}}