{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:29:58Z","timestamp":1743085798775,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110086"},{"type":"electronic","value":"9783030110093"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11009-3_43","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T06:24:44Z","timestamp":1548311084000},"page":"698-715","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images"],"prefix":"10.1007","author":[{"given":"Siddharth","family":"Mahendran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haider","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren\u00e9","family":"Vidal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Malik, J.: Viewpoints and keypoints. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1510\u20131519, June 2015","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2686\u20132694, December 2015","DOI":"10.1109\/ICCV.2015.308"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Ko\u0161eck\u00e1, J.: 3D bounding box estimation using deep learning and geometry. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632\u20135640, July 2017","DOI":"10.1109\/CVPR.2017.597"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Chan, A., Derpanis, K.G., Daniilidis, K.: 6-DoF object pose from semantic keypoints. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2011\u20132018, May 2017","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"43_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-3-319-46466-4_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Wu","year":"2016","unstructured":"Wu, J., et al.: Single image 3D interpreter network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 365\u2013382. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_22"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3D pose regression using convolutional neural networks. In: IEEE International Conference on Computer Vision Workshop on Recovering 6D Object Pose (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Kokkinos, I.: UberNet: training a \u2018universal\u2019 convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.579"},{"key":"43_CR8","unstructured":"Elhoseiny, M., El-Gaaly, T., Bakry, A., Elgammal, A.: A comparative analysis and study of multiview CNN models for joint object categorization and pose estimation. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning. ICML 2016, vol. 18, pp. 888\u2013897. JMLR.org (2016)"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: IEEE Winter Conference on Applications of Computer Vision, pp. 75\u201382, March 2014","DOI":"10.1109\/WACV.2014.6836101"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778, June 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR11","unstructured":"Hara, K., Vemulapalli, R., Chellappa, R.: Designing deep convolutional neural networks for continuous object orientation estimation. CoRR abs\/1702.01499 (2017)"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"L\u00f3pez-Sastre, R.J., Tuytelaars, T., Savarese, S.: Deformable part models revisited: a performance evaluation for object category pose estimation. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1052\u20131059, November 2011","DOI":"10.1109\/ICCVW.2011.6130367"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Hejrati, M., Ramanan, D.: Analysis by synthesis: 3D object recognition by object reconstruction. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2449\u20132456, June 2014","DOI":"10.1109\/CVPR.2014.314"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Aubry, M., Maturana, D., Efros, A.A., Russell, B.C., Sivic, J.: Seeing 3D chairs: exemplar part-based 2D\u20133D alignment using a large dataset of CAD models. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3762\u20133769, June 2014","DOI":"10.1109\/CVPR.2014.487"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Pepik, B., Stark, M., Gehler, P., Schiele, B.: Teaching 3D geometry to deformable part models. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3362\u20133369, June 2012","DOI":"10.1109\/CVPR.2012.6248075"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Savarese, S., Fei-Fei, L.: 3D generic object categorization, localization and pose estimation. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138, October 2007","DOI":"10.1109\/ICCV.2007.4408987"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"Bakry, A., El-Gaaly, T., Elhoseiny, M., Elgammal, A.: Joint object recognition and pose estimation using a nonlinear view-invariant latent generative model. In: IEEE Winter Applications of Computer Vision Conference (2016)","DOI":"10.1109\/WACV.2016.7477655"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Xiang, Y., Savarese, S.: A coarse-to-fine model for 3D pose estimation and sub-category recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298639"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Juranek, R., Herout, A., Dubska, M., Zemcik, P.: Real-time pose estimation piggybacked on object detection. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.274"},{"key":"43_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-319-48896-7_17","volume-title":"Advances in Multimedia Information Processing - PCM 2016","author":"Y Wang","year":"2016","unstructured":"Wang, Y., Li, S., Jia, M., Liang, W.: Viewpoint estimation for objects with convolutional neural network trained on synthetic images. In: Chen, E., Gong, Y., Tie, Y. (eds.) PCM 2016. LNCS, vol. 9917, pp. 169\u2013179. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48896-7_17"},{"key":"43_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: British Machine Vision Conference (2014)","DOI":"10.5244\/C.28.6"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Li, W., Luo, Y., Wang, P., Qin, Z., Zhou, H., Qiao, H.: Recent advances on application of deep learning for recovering object pose. In: International Conference on Robotics and Biomimetics (2016)","DOI":"10.1109\/ROBIO.2016.7866501"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Braun, M., Rao, Q., Wang, Y., Flohr, F.: Pose-RCNN: joint object detection and pose estimation using 3D object proposals. In: International Conference on Intelligent Transportation Systems (2016)","DOI":"10.1109\/ITSC.2016.7795763"},{"key":"43_CR25","unstructured":"Massa, F., Aubry, M., Marlet, R.: Convolutional neural networks for joint object detection and pose estimation: a comparative study. CoRR abs\/1412.7190 (2014)"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Massa, F., Marlet, R., Aubry, M.: Crafting a multi-task CNN for viewpoint estimation. In: British Machine Vision Conference (2016)","DOI":"10.5244\/C.30.91"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"O\u00f1oro-Rubio, D., L\u00f3pez-Sastre, R.J., Redondo-Cabrera, C., Gil-Jim\u00e9nez, P.: The challenge of simultaneous object detection and pose estimation: a comparative study. coRR abs\/1801.08110 (2018)","DOI":"10.1016\/j.imavis.2018.09.013"},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Afifi, A.J., Hellwich, O., Soomro, T.A.: Simultaneous object classification and viewpoint estimation using deep multi-task convolutional neural network. In: The 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (2018)","DOI":"10.5220\/0006544001770184"},{"key":"43_CR29","doi-asserted-by":"crossref","unstructured":"Li, C., Bai, J., Hager, G.D.: A unified framework for multi-view multi-class object pose estimation. coRR abs\/1801.08103 (2018)","DOI":"10.1007\/978-3-030-01270-0_16"},{"key":"43_CR30","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)"},{"key":"43_CR31","unstructured":"Chollet, F.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"43_CR32","unstructured":"TensorFlow: large-scale machine learning on heterogeneous systems (2015). tensorflow.org"},{"issue":"1","key":"43_CR33","doi-asserted-by":"publisher","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. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"43_CR34","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255, June 2009","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"43_CR35","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems (2012)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11009-3_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:15:28Z","timestamp":1674350128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11009-3_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110086","9783030110093"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11009-3_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}