{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:35:12Z","timestamp":1778891712022,"version":"3.51.4"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,12,11]],"date-time":"2013-12-11T00:00:00Z","timestamp":1386720000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1007\/s11263-013-0677-1","type":"journal-article","created":{"date-parts":[[2013,12,10]],"date-time":"2013-12-10T12:41:16Z","timestamp":1386679276000},"page":"219-238","source":"Crossref","is-referenced-by-count":78,"title":["Activity representation with motion hierarchies"],"prefix":"10.1007","volume":"107","author":[{"given":"Adrien","family":"Gaidon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaid","family":"Harchaoui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,12,11]]},"reference":[{"key":"677_CR1","doi-asserted-by":"crossref","unstructured":"Bilen, H., Namboodiri, V.P., & Van Gool, L.J. (2011). Object and action classification with latent variables. In BMVC, Bristol.","DOI":"10.5244\/C.25.17"},{"key":"677_CR2","volume-title":"Learning OpenCV: Computer vision with the OpenCV library","author":"G Bradski","year":"2008","unstructured":"Bradski, G., & Kaehler, A. (2008). Learning OpenCV: Computer vision with the OpenCV library. Sebastopol: O\u2019Reilly Media."},{"key":"677_CR3","doi-asserted-by":"crossref","unstructured":"Brendel, W., & Todorovic, S. (2011). Learning spatiotemporal graphs of human activities. In ICCV, Boston.","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"677_CR4","doi-asserted-by":"crossref","unstructured":"Brox, T., & Malik, J. (2010). Object segmentation by long term analysis of point trajectories. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-15555-0_21"},{"key":"677_CR5","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B., & Schmid, C. (2006). Human detection using oriented histograms of flow and appearance. In ECCV, Berlin.","DOI":"10.1007\/11744047_33"},{"key":"677_CR6","doi-asserted-by":"crossref","unstructured":"De Castro, E., & Morandi, C. (1987). Registration of translated and rotated images using finite Fourier transforms. In PAMI, Portage la Prairie.","DOI":"10.1109\/TPAMI.1987.4767966"},{"key":"677_CR7","unstructured":"Diestel, R. (2005). Graph theory. Heidelberg: Springer."},{"key":"677_CR8","unstructured":"Duda, R., Hart, P., & Stork, D. (2001). Pattern classification. New York: Wiley"},{"key":"677_CR9","doi-asserted-by":"crossref","unstructured":"Dup\u00e9, F., & Brun, L. (2008). Hierarchical bag of paths for kernel based shape classification. In Structural, Syntactic, and Statistical Pattern Recognition, Windsor.","DOI":"10.1007\/978-3-540-89689-0_27"},{"key":"677_CR10","doi-asserted-by":"crossref","unstructured":"Farneb\u00e4ck, G. (2003). Two-frame motion estimation based on polynomial expansion. In Image Analysis, Lowa.","DOI":"10.1007\/3-540-45103-X_50"},{"key":"677_CR11","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. In PAMI, Portage la Prairie.","DOI":"10.1109\/TPAMI.2009.167"},{"key":"677_CR12","unstructured":"Foster, L., Waagen, A., Aijaz, N., Hurley, M., Luis, A., Rinsky, J., Satyavolu, C., Way, M.J., Gazis, P., & Srivastava, A. (2009). Stable and efficient gaussian process calculations. In JMLR, Las Vegas."},{"key":"677_CR13","doi-asserted-by":"crossref","unstructured":"Fowlkes, C., Belongie, S., Chung, F., & Malik, J. (2004). Spectral grouping using the Nystrom method. In PAMI, London.","DOI":"10.1109\/TPAMI.2004.1262185"},{"key":"677_CR14","doi-asserted-by":"crossref","unstructured":"Fradet, M., Robert, P., & P\u00e9rez, P. (2009). Clustering point trajectories with various life-spans. In CVMP, London.","DOI":"10.1109\/CVMP.2009.24"},{"key":"677_CR15","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Harchaoui, Z., & Schmid, C. (2011). Actom sequence models for efficient action detection. In CVPR, Providence.","DOI":"10.1109\/CVPR.2011.5995646"},{"key":"677_CR16","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Harchaoui, Z., & Schmid, C. (2012). Recognizing activities with cluster-trees of tracklets. In BMVC, Bristol.","DOI":"10.5244\/C.26.30"},{"key":"677_CR17","unstructured":"Gilbert, A., Illingworth, J., & Bowden, R. (2010). Action recognition using mined hierarchical compound features. In PAMI, Portage la Prairie."},{"key":"677_CR18","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Meier, F., & Essa, I. (2008). 3D shape context and distance transform for action recognition. In ICPR, Delhi.","DOI":"10.1109\/ICPR.2008.4761435"},{"key":"677_CR19","unstructured":"Hastie, T., Tibshirani, R., & Friedman, J. (2008). The elements of statistical, learning (2nd edition). New York: Springer."},{"key":"677_CR20","unstructured":"Hongeng, S., & Nevatia, R. (2003). Large-scale event detection using semi-hidden markov models. In ICCV, Boston."},{"key":"677_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, Carlton.","DOI":"10.1007\/978-3-642-15549-9_36"},{"key":"677_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Dai, Q., Xue, X., Liu, W., & Ngo, C. (2012a), Trajectory-based modeling of human actions with motion reference points. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-33715-4_31"},{"key":"677_CR23","unstructured":"Jiang, Z., Lin, Z., & Davis, L. (2012b). Recognizing human actions by learning and matching shape-motion prototype trees. In PAMI, Portage la Prairie."},{"key":"677_CR24","doi-asserted-by":"crossref","unstructured":"Kliper-Gross, O., Gurovich, Y., Hassner, T., & Wolf, L. (2012). Motion interchange patterns for action recognition in unconstrained videos. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-33783-3_19"},{"key":"677_CR25","doi-asserted-by":"crossref","unstructured":"Kovashka, A., & Grauman, K. (2010). Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In CVPR, Providence.","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"677_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, New York.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"677_CR27","doi-asserted-by":"crossref","unstructured":"Laptev, I. (2005). On space-time interest points. In IJCV, Rosario.","DOI":"10.1007\/s11263-005-1838-7"},{"key":"677_CR28","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., & Rozenfeld, B. (2008). Learning realistic human actions from movies. In CVPR, Providence.","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"677_CR29","doi-asserted-by":"crossref","unstructured":"Laxton, B., Lim, J., & Kriegman, D. (2007). Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video. In CVPR, Providence.","DOI":"10.1109\/CVPR.2007.383074"},{"key":"677_CR30","doi-asserted-by":"crossref","unstructured":"Lezama, J., Alahari, K., Sivic, J., & Laptev, I. (2011). Track to the future: Spatio-temporal video segmentation with long-range motion cues. In CVPR, Providence.","DOI":"10.1109\/CVPR.2011.6044588"},{"key":"677_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., & Savarese, S. (2011). Recognizing human actions by attributes. In CVPR, Providence.","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"677_CR32","doi-asserted-by":"crossref","unstructured":"Lowe, D.G. (2004). Distinctive image features from scale-invariant keypoints. In IJCV, Ho Chi Minh.","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"677_CR33","doi-asserted-by":"crossref","unstructured":"Maji, S., Berg, A., & Malik, J. (2008). Classification using intersection kernel support vector machines is efficient. In CVPR, Providence.","DOI":"10.1109\/CVPR.2008.4587630"},{"key":"677_CR34","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., & Schmid, C. (2009). Actions in context. In CVPR, Providence.","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"677_CR35","doi-asserted-by":"crossref","unstructured":"Matikainen, P., Hebert, M., & Sukthankar, R. (2010). Representing pairwise spatial and temporal relations for action recognition. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-15549-9_37"},{"key":"677_CR36","doi-asserted-by":"crossref","unstructured":"Mikolajczyk, K., & Uemura, H. (2008). Action recognition with motion-appearance vocabulary forest. In CVPR, Providence.","DOI":"10.1109\/CVPR.2008.4587628"},{"key":"677_CR37","doi-asserted-by":"crossref","unstructured":"Niebles, J.C., & Fei-Fei, L. (2007). Hierarchical model of shape and appearance for human action classification. In CVPR, Providence.","DOI":"10.1109\/CVPR.2007.383132"},{"key":"677_CR38","doi-asserted-by":"crossref","unstructured":"Niebles, J.C., Chen, C., & Fei-Fei, L. (2010) Modeling temporal structure of decomposable motion segments for activity classification. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"677_CR39","doi-asserted-by":"crossref","unstructured":"Oliver, N.M., Rosario, B., & Pentland, A.P. (2000). A Bayesian computer vision system for modeling human interactions. In PAMI, Portage la Prairie.","DOI":"10.1109\/34.868684"},{"key":"677_CR40","unstructured":"Pablo, A., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour detection and hierarchical image segmentation. In PAMI, Portage la Prairie."},{"key":"677_CR41","unstructured":"Patron-Perez, A., Marszalek, M., Zisserman, A., & Reid, I.D. (2010). High five: Recognising human interactions in TV shows. In BMVC, Bristol."},{"key":"677_CR42","unstructured":"Prest, A., Ferrari, V., & Schmid, C. (2012). Explicit modeling of human-object interactions in realistic videos. In PAMI, Portage la Prairie."},{"key":"677_CR43","doi-asserted-by":"crossref","unstructured":"Raptis, M., Kokkinos, I., & Soatto, S. (2012). Discovering discriminative action parts from mid-level video representations. In CVPR, Providence.","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"677_CR44","doi-asserted-by":"crossref","unstructured":"Reddy, K. K., Liu, J., & Shah, M. (2009). Incremental action recognition using feature-tree. In CVPR, Providence.","DOI":"10.1109\/ICCV.2009.5459374"},{"key":"677_CR45","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J. J. (2012). Action bank: A high-level representation of activity in video. In CVPR, New York.","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"677_CR46","doi-asserted-by":"crossref","unstructured":"Sapienza, M., Cuzzolin, F., & Torr, P. (2012). Learning discriminative space-time actions from weakly labelled videos. In BMVC, Bristol.","DOI":"10.5244\/C.26.123"},{"key":"677_CR47","volume-title":"Learning with Kernels","author":"B Sch\u00f6lkopf","year":"2002","unstructured":"Sch\u00f6lkopf, B., & Smola, A. J. (2002). Learning with Kernels. Mexico: MIT Press."},{"key":"677_CR48","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1162\/089976698300017467","volume":"10","author":"B Sch\u00f6lkopf","year":"1998","unstructured":"Sch\u00f6lkopf, B., Smola, A., & M\u00fcller, K. R. (1998). Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 10, 1299\u20131319.","journal-title":"Neural Computation"},{"key":"677_CR49","doi-asserted-by":"crossref","unstructured":"Sculley, D. (2010). Web-scale k-means clustering. In WWW, New York.","DOI":"10.1145\/1772690.1772862"},{"key":"677_CR50","volume-title":"Cristianini","author":"J Shawe-Taylor","year":"2004","unstructured":"Shawe-Taylor, J. (2004). Cristianini. Cambridge: Cambridge Univ Press."},{"key":"677_CR51","unstructured":"Shi, J., & Malik, J. (1998). Motion segmentation and tracking using normalized cuts. In ICCV, IEEE, Beijing."},{"key":"677_CR52","unstructured":"Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. In PAMI, London."},{"key":"677_CR53","unstructured":"Shi, J., & Tomasi, C. (1994). Good features to track. In CVPR, Providence."},{"key":"677_CR54","unstructured":"Suard, F., Rakotomamonjy, A., & Bensrhair, A. (2007). Kernel on bag of paths for measuring similarity of shapes. In European Symposium on Artificial Neural Networks, pp 1\u20136."},{"key":"677_CR55","volume-title":"Computer vision: Algorithms and applications","author":"R Szeliski","year":"2010","unstructured":"Szeliski, R. (2010). Computer vision: Algorithms and applications. New York: Springer."},{"key":"677_CR56","doi-asserted-by":"crossref","unstructured":"Tang, K., Fei-Fei, L., & Koller, D. (2012). Learning latent temporal structure for complex event detection. In CVPR, Providence.","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"677_CR57","doi-asserted-by":"crossref","unstructured":"Todorovic, S. (2012). Human activities as stochastic kronecker graphs. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-33709-3_10"},{"key":"677_CR58","doi-asserted-by":"crossref","unstructured":"Vig, E., Dorr, M., & Cox, D. (2012). Space-variant descriptor sampling for action recognition based on saliency and eye movements. In ECCV, Carlton.","DOI":"10.1007\/978-3-642-33786-4_7"},{"key":"677_CR59","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., & Cheng-Lin, L. (2013). Dense trajectories and motion boundary descriptors for action recognition. In IJCV, Dublin.","DOI":"10.1007\/s11263-012-0594-8"},{"key":"677_CR60","unstructured":"Wang, Y. (2011). & Mori, G. Probabilistic versus max-margin. PAMI: Hidden part models for human action recognition."},{"key":"677_CR61","unstructured":"Williams, C., & Seeger, M. (2001). Using the Nystr\u00f6m method to speed up kernel machines. In NIPS, Allahabad."},{"key":"677_CR62","doi-asserted-by":"crossref","unstructured":"Yu, G., Yuan, J., & Liu, Z. (2012). Propagative hough voting for human activity recognition. In ECCV, New York.","DOI":"10.1007\/978-3-642-33712-3_50"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-013-0677-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-013-0677-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-013-0677-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,4]],"date-time":"2019-08-04T19:03:12Z","timestamp":1564945392000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-013-0677-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12,11]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,5]]}},"alternative-id":["677"],"URL":"https:\/\/doi.org\/10.1007\/s11263-013-0677-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,12,11]]}}}