{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:24:40Z","timestamp":1761060280310,"version":"3.37.3"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"2-4","license":[{"start":{"date-parts":[[2017,2,2]],"date-time":"2017-02-02T00:00:00Z","timestamp":1485993600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,2,2]],"date-time":"2017-02-02T00:00:00Z","timestamp":1485993600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000083","name":"Directorate for Computer and Information Science and Engineering","doi-asserted-by":"publisher","award":["1029430"],"award-info":[{"award-number":["1029430"]}],"id":[{"id":"10.13039\/100000083","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1007\/s11263-016-0980-8","type":"journal-article","created":{"date-parts":[[2017,2,2]],"date-time":"2017-02-02T12:40:59Z","timestamp":1486039259000},"page":"314-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Space-Time Tree Ensemble for Action Recognition and Localization"],"prefix":"10.1007","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4986-2221","authenticated-orcid":false,"given":"Shugao","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stan","family":"Sclaroff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nazli","family":"Ikizler-Cinbis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonid","family":"Sigal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,2,2]]},"reference":[{"issue":"2","key":"980_CR1","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.jvcir.2013.11.003","volume":"25","author":"NB Aoun","year":"2014","unstructured":"Aoun, N. B., Mejdoub, M., & Amar, C. B. (2014). Graph-based approach for human action recognition using spatio-temporal features. Journal of Visual Communication and Image Representation, 25(2), 329\u2013338.","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"980_CR2","doi-asserted-by":"crossref","unstructured":"Arbelaez, P., Maire, M., Fowlkes, C. C., Malik J. (2009). From contours to regions: An empirical evaluation. In CVPR.","DOI":"10.1109\/CVPR.2009.5206707"},{"issue":"3","key":"980_CR3","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick, A. F., & Davis, J. W. (2001). The recognition of human movement using temporal templates. TPAMI, 23(3), 257\u2013267.","journal-title":"TPAMI"},{"key":"980_CR4","doi-asserted-by":"crossref","unstructured":"Brendel, W., Todorovic, S. (2011). Learning spatiotemporal graphs of human activities. In ICCV.","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"980_CR5","doi-asserted-by":"crossref","unstructured":"Che\u00e1ron, G., Laptev, I., Schmid, C. (2015). P-CNN: Pose-based CNN features for action recognition. In ICCV.","DOI":"10.1109\/ICCV.2015.368"},{"key":"980_CR6","first-page":"265","volume":"2","author":"K Crammer","year":"2001","unstructured":"Crammer, K., & Singer, Y. (2001). On the algorithmic implementation of multiclass kernel-based vector machines. JMLR, 2, 265\u2013292.","journal-title":"JMLR"},{"key":"980_CR7","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. JMLR, 9, 1871\u20131874.","journal-title":"JMLR"},{"issue":"4","key":"980_CR8","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1109\/TPAMI.2010.135","volume":"33","author":"PF Felzenszwalb","year":"2011","unstructured":"Felzenszwalb, P. F., & Zabih, R. (2011). Dynamic programming and graph algorithms in computer vision. TPAMI, 33(4), 721\u2013740.","journal-title":"TPAMI"},{"key":"980_CR9","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","volume":"315","author":"BJ Frey","year":"2007","unstructured":"Frey, B. J., & Dueck, D. (2007). Clustering by passing messages between data points. Science, 315, 972\u2013976.","journal-title":"Science"},{"issue":"3","key":"980_CR10","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-013-0677-1","volume":"107","author":"A Gaidon","year":"2014","unstructured":"Gaidon, A., Harchaoui, Z., & Schmid, C. (2014). Activity representation with motion hierarchies. IJCV, 107(3), 219\u2013238.","journal-title":"IJCV"},{"key":"980_CR11","unstructured":"Gilbert, A., Bowden, R. (2014). Data mining for action recognition. In ACCV."},{"issue":"5","key":"980_CR12","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1109\/TPAMI.2010.144","volume":"33","author":"A Gilbert","year":"2011","unstructured":"Gilbert, A., Illingworth, J., & Bowden, R. (2011). Action recognition using mined hierarchical compound features. TPAMI, 33(5), 883\u2013897.","journal-title":"TPAMI"},{"key":"980_CR13","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":"980_CR14","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J. (2015). Finding action tubes. In CVPR.","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"980_CR15","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J. (2015). Contextual action recognition with R*CNN. In ICCV.","DOI":"10.1109\/ICCV.2015.129"},{"issue":"12","key":"980_CR16","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., & Basri, R. (2007). Actions as space-time shapes. TPAMI, 29(12), 2247\u20132253.","journal-title":"TPAMI"},{"key":"980_CR17","doi-asserted-by":"crossref","unstructured":"Hadfield, S., Bowden, R. (2013). Hollywood 3D: Recognizing actions in 3D natural scenes. In CVPR.","DOI":"10.1109\/CVPR.2013.436"},{"key":"980_CR18","doi-asserted-by":"crossref","unstructured":"Hadfield, S., Lebeda, K., Bowden, R. (2014). Natural action recognition using invariant 3D motion encoding. In ECCV.","DOI":"10.1007\/978-3-319-10605-2_49"},{"key":"980_CR19","doi-asserted-by":"crossref","unstructured":"Hoai, M., Zisserman, A. (2013). Discriminative sub-categorization. In CVPR.","DOI":"10.1109\/CVPR.2013.218"},{"issue":"3","key":"980_CR20","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s11263-008-0142-8","volume":"80","author":"N Ikizler","year":"2008","unstructured":"Ikizler, N., & Forsyth, D. A. (2008). Searching for complex human activities with no visual examples. IJCV, 80(3), 337\u2013357.","journal-title":"IJCV"},{"key":"980_CR21","doi-asserted-by":"crossref","unstructured":"Ikizler-Cinbis, N., Sclaroff, S. (2010). Object, scene and actions: Combining multiple features for human action recognition. In ECCV.","DOI":"10.1007\/978-3-642-15549-9_36"},{"key":"980_CR22","doi-asserted-by":"crossref","unstructured":"Iosifidis, A., Tefas, A., Pitas, I. (2014). Human action recognition based on bag of features and multi-view neural networks. In ICIP.","DOI":"10.1109\/ICIP.2014.7025302"},{"key":"980_CR23","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M. J. (2013). Towards understanding action recognition. In ICCV.","DOI":"10.1109\/ICCV.2013.396"},{"key":"980_CR24","doi-asserted-by":"crossref","unstructured":"Kantorov, V., Laptev, I. (2014). Efficient feature extraction, encoding, and classification for action recognition. In CVPR.","DOI":"10.1109\/CVPR.2014.332"},{"key":"980_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2014.223"},{"key":"980_CR26","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T. (2011). HMDB: A large video database for human motion recognition. In ICCV.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"980_CR27","unstructured":"Lan, T., Wang, Y., Mori, G. (2011). Discriminative figure-centric models for joint action localization and recognition. In ICCV."},{"key":"980_CR28","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marsza\u0142ek, M., Schmid, C., Rozenfeld, B. (2008). Learning realistic human actions from movies. In CVPR.","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"980_CR29","doi-asserted-by":"crossref","unstructured":"Leordeanu, M., Sukthankar, R., Sminchisescu, C. (2012). Efficient closed-form solution to generalized boundary detection. In ECCV.","DOI":"10.1007\/978-3-642-33765-9_37"},{"key":"980_CR30","doi-asserted-by":"crossref","unstructured":"Ma, S., Zhang, J., Ikizler-Cinbis, N., Sclaroff, S. (2013). Action recognition and localization by hierarchical space-time segments. In ICCV.","DOI":"10.1109\/ICCV.2013.341"},{"key":"980_CR31","doi-asserted-by":"crossref","unstructured":"Ma, S., Sigal, L., Sclaroff, S. (2015). Space-time tree ensemble for action recognition. In CVPR.","DOI":"10.1109\/CVPR.2015.7299137"},{"key":"980_CR32","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., Schmid, C. (2009). Actions in context. In CVPR.","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"980_CR33","doi-asserted-by":"crossref","unstructured":"Matikainen, P., Hebert, M., Sukthankar, R. (2010). Representing pairwise spatial and temporal relations for action recognition. In ECCV.","DOI":"10.1007\/978-3-642-15549-9_37"},{"issue":"3","key":"980_CR34","first-page":"426","volume":"115","author":"K Mikolajczyk","year":"2011","unstructured":"Mikolajczyk, K., & Uemura, H. (2011). Action recognition with appearance-motion features and fast search trees. CVIU, 115(3), 426\u2013438.","journal-title":"CVIU"},{"key":"980_CR35","unstructured":"Ng, J. Y. H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G. (2015). Beyond short snippets: deep networks for video classification. In CVPR."},{"key":"980_CR36","unstructured":"Nijssen, S., Kok, J. N. (2005). A quickstart in frequent structure mining can make a difference. In ICCS."},{"key":"980_CR37","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C. (2013). Action and event recognition with fisher vectors on a compact feature set. In ICCV.","DOI":"10.1109\/ICCV.2013.228"},{"key":"980_CR38","unstructured":"Patron-Perez, A., Marszalek, M., Zisserman, A., Reid, I. D. (2010). High five: Recognising human interactions in TV shows. In BMVC."},{"issue":"12","key":"980_CR39","doi-asserted-by":"publisher","first-page":"2441","DOI":"10.1109\/TPAMI.2012.24","volume":"34","author":"A Patron-Perez","year":"2012","unstructured":"Patron-Perez, A., Marszalek, M., Reid, I., & Zisserman, A. (2012). Structured learning of human interactions in TV shows. TPAMI, 34(12), 2441\u20132453.","journal-title":"TPAMI"},{"key":"980_CR40","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T. (2010). Improving the fisher kernel for large-scale image classification. In ECCV.","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"980_CR41","unstructured":"Ramanan, D., Forsyth, D. A. (2003). Automatic annotation of everyday movements. In NIPS."},{"key":"980_CR42","doi-asserted-by":"crossref","unstructured":"Raptis, M., Sigal, L. (2013). Poselet key-framing: A model for human activity recognition. In CVPR.","DOI":"10.1109\/CVPR.2013.342"},{"key":"980_CR43","doi-asserted-by":"crossref","unstructured":"Raptis, M., Kokkinos, I., Soatto, S. (2012). Discovering discriminative action parts from mid-level video representations. In CVPR.","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"980_CR44","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":"980_CR45","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J. J. (2012). Action bank: A high-level representation of activity in video. In CVPR.","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"980_CR46","unstructured":"Simonyan, K., Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In NIPS."},{"key":"980_CR47","doi-asserted-by":"crossref","unstructured":"Tian, Y., Sukthankar, R., Shah, M. (2013). Spatiotemporal deformable part models for action detection. In CVPR.","DOI":"10.1109\/CVPR.2013.341"},{"key":"980_CR48","doi-asserted-by":"crossref","unstructured":"Todorovic, S. (2012). Human activities as stochastic kronecker graphs. In ECCV.","DOI":"10.1007\/978-3-642-33709-3_10"},{"key":"980_CR49","doi-asserted-by":"crossref","unstructured":"Tran, D., Yuan, J. (2011). Optimal spatio-temporal path discovery for video event detection. In CVPR.","DOI":"10.1109\/CVPR.2011.5995416"},{"key":"980_CR50","unstructured":"Tran, D., Yuan, J. (2012). Max-margin structured output regression for spatio-temporal action localization. In NIPS."},{"key":"980_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C. (2013). Action recognition with improved trajectories. In ICCV.","DOI":"10.1109\/ICCV.2013.441"},{"issue":"1","key":"980_CR52","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., & Liu, C. L. (2013). Dense trajectories and motion boundary descriptors for action recognition. IJCV, 103(1), 60\u201379.","journal-title":"IJCV"},{"issue":"3","key":"980_CR53","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang, H., Oneata, D., Verbeek, J., & Schmid, C. (2016). A robust and efficient video representation for action recognition. IJCV, 119(3), 219\u2013238.","journal-title":"IJCV"},{"key":"980_CR54","doi-asserted-by":"crossref","unstructured":"Wang, L., Sahbi, H. (2013). Directed acyclic graph kernels for action recognition. In ICCV.","DOI":"10.1109\/ICCV.2013.393"},{"key":"980_CR55","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X. (2014). Video action detection with relational dynamic-poselets. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"980_CR56","unstructured":"Wang, Y., Mori, G. (2008). Learning a discriminative hidden part model for human action recognition. In NIPS."},{"issue":"7","key":"980_CR57","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TPAMI.2010.214","volume":"33","author":"Y Wang","year":"2011","unstructured":"Wang, Y., & Mori, G. (2011). Hidden part models for human action recognition: Probabilistic versus max margin. TPAMI, 33(7), 1310\u20131323.","journal-title":"TPAMI"},{"key":"980_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y., Huang, K., Tan, T. (2007). Human activity recognition based on r transform. In CVPR.","DOI":"10.1109\/CVPR.2007.383505"},{"key":"980_CR59","first-page":"30753102","volume":"13","author":"Y Wang","year":"2012","unstructured":"Wang, Y., Tran, D., Liao, Z., & Forsyth, D. (2012). Discriminative hierarchical part-based models for human parsing and action recognition. JMLR, 13, 30753102.","journal-title":"JMLR"},{"key":"980_CR60","doi-asserted-by":"crossref","unstructured":"Weinland, D., Boyer, E., Ronfard, R. (2007). Action recognition from arbitrary views using 3D exemplars. In ICCV.","DOI":"10.1109\/ICCV.2007.4408849"},{"key":"980_CR61","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":"980_CR62","doi-asserted-by":"crossref","unstructured":"Wu, B., Yuan, C., Hu, W. (2014). Human action recognition based on context-dependent graph kernels. In CVPR.","DOI":"10.1109\/CVPR.2014.334"},{"key":"980_CR63","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, X., Jiang, Y., Ye, H., Xue, X. (2015). Modeling spatial-temporal clues in a hybrid deep learning framework for video classification. In Proceedings of the 23rd ACM international conference on Multimedia.","DOI":"10.1145\/2733373.2806222"},{"key":"980_CR64","doi-asserted-by":"crossref","unstructured":"Xie, Y., Chang, H., Li, Z., Liang, L., Chen, X., Zhao, D. (2011). A unified framework for locating and recognizing human actions. In CVPR.","DOI":"10.1109\/CVPR.2011.5995648"},{"key":"980_CR65","doi-asserted-by":"crossref","unstructured":"Yang, X., Tian, Y. (2014). Action recognition using super sparse coding vector with spatio-temporal awareness. In ECCV.","DOI":"10.1007\/978-3-319-10605-2_47"},{"key":"980_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhou, W., Reardon, C. M., Parker, L. E. (2014). Simplex-based 3D spatio-temporal feature description for action recognition. In CVPR.","DOI":"10.1109\/CVPR.2014.265"},{"key":"980_CR67","doi-asserted-by":"crossref","unstructured":"Zitnick, C. L., Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In European Conference on Computer Vision.","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\/s11263-016-0980-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0980-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0980-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T07:20:37Z","timestamp":1589700037000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0980-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,2]]},"references-count":67,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[2018,4]]}},"alternative-id":["980"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0980-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2017,2,2]]},"assertion":[{"value":"2 March 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2017","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}