{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:40:07Z","timestamp":1748738407010,"version":"3.41.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319276731"},{"type":"electronic","value":"9783319276748"}],"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":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-27674-8_11","type":"book-chapter","created":{"date-parts":[[2015,12,31]],"date-time":"2015-12-31T14:47:31Z","timestamp":1451573251000},"page":"116-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning Hough Transform with Latent Structures for Joint Object Detection and Pose Estimation"],"prefix":"10.1007","author":[{"given":"Hanxi","family":"Li","sequence":"first","affiliation":[]},{"given":"Xuming","family":"He","sequence":"additional","affiliation":[]},{"given":"Nick","family":"Barnes","sequence":"additional","affiliation":[]},{"given":"Mingwen","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,1,1]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Wan, L., Eigen, D., Fergus, R.: End-to-end integration of a convolution network, deformable parts model and non-maximum suppression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 851\u2013859 (2015)","DOI":"10.1109\/CVPR.2015.7298686"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Zia, M.Z., Stark, M., Schindler, K.: Explicit occlusion modeling for 3d object class representations. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.427"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Maji, S., Malik, J.: Object detection using a max-margin hough transform. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206693"},{"key":"11_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-642-15555-0_15","volume-title":"Computer Vision \u2013 ECCV 2010","author":"P Yarlagadda","year":"2010","unstructured":"Yarlagadda, P., Monroy, A., Ommer, B.: Voting by grouping dependent parts. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 197\u2013210. Springer, Heidelberg (2010)"},{"key":"11_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-642-33712-3_23","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Razavi","year":"2012","unstructured":"Razavi, N., Gall, J., Kohli, P., Van Gool, L.: Latent hough transform for object detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 312\u2013325. Springer, Heidelberg (2012)"},{"issue":"11","key":"11_CR7","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.1109\/TPAMI.2011.70","volume":"33","author":"J Gall","year":"2011","unstructured":"Gall, J., Yao, A., Razavi, N., Van Gool, L., Lempitsky, V.: Hough forests for object detection, tracking, and action recognition. TPAMI 33(11), 2188\u20132202 (2011)","journal-title":"TPAMI"},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","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(1), 259\u2013289 (2008)","journal-title":"IJCV"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Arie-Nachimson, M., Basri, R.: Constructing implicit 3d shape models for pose estimation. In: CVPR (2009)","DOI":"10.1109\/ICCV.2009.5459310"},{"key":"11_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/978-3-642-15549-9_45","volume-title":"Computer Vision \u2013 ECCV 2010","author":"N Razavi","year":"2010","unstructured":"Razavi, N., Gall, J., Van Gool, L.: Backprojection revisited: scalable multi-view object detection and similarity metrics for detections. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 620\u2013633. Springer, Heidelberg (2010)"},{"key":"11_CR11","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: Cnn features off-the-shelf: an astounding baseline for recognition. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 512\u2013519. IEEE (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"11_CR14","unstructured":"Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS (2002)"},{"key":"11_CR15","unstructured":"Hejrati, M., Ramanan, D.: Analyzing 3d objects in cluttered images. In: NIPS (2012)"},{"issue":"2","key":"11_CR16","first-page":"111","volume":"13","author":"D Ballard","year":"1981","unstructured":"Ballard, D.: Generalizing the hough transform to detect arbitrary shapes. PR 13(2), 111\u2013122 (1981)","journal-title":"PR"},{"key":"11_CR17","unstructured":"Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Workshop on Statistical Learning in Computer Vision, ECCV (2004)"},{"issue":"1\u20133","key":"11_CR18","doi-asserted-by":"publisher","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(1\u20133), 259\u2013289 (2008)","journal-title":"IJCV"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Ommer, B., Malik, J.: Multi-scale object detection by clustering lines. In: CVPR (2009)","DOI":"10.1109\/ICCV.2009.5459200"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Payet, N., Todorovic, S.: From contours to 3d object detection and pose estimation. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126342"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Glasner, D., Galun, M., Alpert, S., Basri, R., Shakhnarovich, G.: Viewpoint-aware object detection and pose estimation. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126379"},{"issue":"2","key":"11_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3d human pose annotations. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587. IEEE (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1653\u20131660. IEEE (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"11_CR26","unstructured":"Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes challenge 2007 (voc 2007) results (2007) 11 (2008)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Ozuysal, M., Lepetit, V., Fua, P.: Pose estimation for category specific multiview object localization. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206633"},{"key":"11_CR28","unstructured":"Berg, A.C., Malik, J.: Geometric blur for template matching. In: CVPR (2001)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, T.: Implicit shape kernel for discriminative learning of the hough transform detector. In: BMVC (2010)","DOI":"10.5244\/C.24.105"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27674-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:08Z","timestamp":1748736008000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27674-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319276731","9783319276748"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27674-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"1 January 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}