{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:59:00Z","timestamp":1778083140556,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642337642","type":"print"},{"value":"9783642337659","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33765-9_14","type":"book-chapter","created":{"date-parts":[[2012,9,26]],"date-time":"2012-09-26T04:07:02Z","timestamp":1348632422000},"page":"187-200","source":"Crossref","is-referenced-by-count":79,"title":["Cost-Sensitive Top-Down\/Bottom-Up Inference for Multiscale Activity Recognition"],"prefix":"10.1007","author":[{"given":"Mohamed R.","family":"Amer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingtian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sinisa","family":"Todorovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"14_CR1","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1561\/0600000018","volume":"2","author":"S.C. Zhu","year":"2006","unstructured":"Zhu, S.C., Mumford, D.: A stochastic grammar of images. Found. Trends. Comput. Graph. Vis.\u00a02, 259\u2013362 (2006)","journal-title":"Trends. Comput. Graph. Vis."},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Gupta, A., Srinivasan, P., Shi, J., Davis, L.: Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Si, Z., Pei, M., Yao, B., Zhu, S.C.: Unsupervised learning of event AND-OR grammar and semantics from video. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126223"},{"key":"14_CR4","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/s11263-010-0346-6","volume":"93","author":"T. Wu","year":"2011","unstructured":"Wu, T., Zhu, S.C.: A numerical study of the bottom-up and top-down inference processes in and-or graphs. IJCV\u00a093, 226\u2013252 (2011)","journal-title":"IJCV"},{"key":"14_CR5","unstructured":"UCLA Courtyard Dataset (2012), \n                    \n                      http:\/\/vcla.stat.ucla.edu\/Projects\/Multiscale_Activity_Recognition\/"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Wu, X., Xu, D., Duan, L., Luo, J.: Action recognition using context and appearance distribution features. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995624"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Yao, B., Zhu, S.C.: Learning deformable action templates from cluttered videos. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459277"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Amer, M., Todorovic, S.: Sum-product networks for modeling activities with stochastic structure. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247816"},{"key":"14_CR9","unstructured":"Lan, T., Wang, Y., Yang, W., Mori, G.: Beyond actions: Discriminative models for contextual group activities. In: NIPS (2010)"},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s11263-010-0355-5","volume":"93","author":"M.S. Ryoo","year":"2011","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Stochastic representation and recognition of high-level group activities. IJCV\u00a093, 183\u2013200 (2011)","journal-title":"IJCV"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Choi, W., Shahid, K., Savarese, S.: Learning context for collective activity recognition. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"14_CR12","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1109\/JPROC.2008.916343","volume":"96","author":"J. Sivic","year":"2008","unstructured":"Sivic, J., Zisserman, A.: Efficient visual search for objects in videos. Proceedings of the IEEE\u00a096, 548\u2013566 (2008)","journal-title":"Proceedings of the IEEE"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Yao, A., Gall, J., Van Gool, L.J.: A hough transform-based voting framework for action recognition. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539883"},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"P.F. Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a032, 1627\u20131645 (2010)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"14_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1007\/978-3-642-15549-9_37","volume-title":"Computer Vision \u2013 ECCV 2010","author":"P. Matikainen","year":"2010","unstructured":"Matikainen, P., Hebert, M., Sukthankar, R.: Representing Pairwise Spatial and Temporal Relations for Action Recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol.\u00a06311, pp. 508\u2013521. Springer, Heidelberg (2010)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"14_CR17","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: Collective activity classification using spatio-temporal relationship among people. In: ICCV (2009)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Amer, M., Todorovic, S.: A Chains model for localizing group activities in videos. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126317"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2012"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33765-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T08:44:01Z","timestamp":1575276241000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33765-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642337642","9783642337659"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33765-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}