{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T23:09:06Z","timestamp":1779318546910,"version":"3.51.4"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319106014","type":"print"},{"value":"9783319106021","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1007\/978-3-319-10602-1_28","type":"book-chapter","created":{"date-parts":[[2014,8,14]],"date-time":"2014-08-14T07:07:56Z","timestamp":1408000076000},"page":"421-436","source":"Crossref","is-referenced-by-count":35,"title":["Predicting Actions from Static Scenes"],"prefix":"10.1007","author":[{"given":"Tuan-Hung","family":"Vu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine","family":"Olsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aude","family":"Oliva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"28_CR1","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":"28_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-642-15552-9_29","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J.C. Niebles","year":"2010","unstructured":"Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 392\u2013405. Springer, Heidelberg (2010)"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.: Action bank: A high-level representation of activity in video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Cheng-Lin, L.: Action Recognition by Dense Trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206557"},{"key":"28_CR6","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)"},{"key":"28_CR7","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A. Oliva","year":"2001","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV\u00a042, 145\u2013175 (2001)","journal-title":"IJCV"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"28_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-540-27814-6_27","volume-title":"Image and Video Retrieval","author":"J. Vogel","year":"2004","unstructured":"Vogel, J., Schiele, B.: Natural scene retrieval based on a semantic modeling step. In: Enser, P.G.B., Kompatsiaris, Y., O\u2019Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol.\u00a03115, pp. 207\u2013215. Springer, Heidelberg (2004)"},{"key":"28_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-642-33765-9_15","volume-title":"Computer Vision \u2013 ECCV 2012","author":"K.M. Kitani","year":"2012","unstructured":"Kitani, K.M., Ziebart, B.D., Bagnell, J.A., Hebert, M.: Activity forecasting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol.\u00a07575, pp. 201\u2013214. Springer, Heidelberg (2012)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A., Hebert, M.: From 3d scene geometry to human workspace. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"28_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/978-3-642-33783-3_21","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V. Delaitre","year":"2012","unstructured":"Delaitre, V., Fouhey, D.F., Laptev, I., Sivic, J., Gupta, A., Efros, A.A.: Scene semantics from long-term observation of people. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol.\u00a07577, pp. 284\u2013298. Springer, Heidelberg (2012)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Jianxiong, X., Hays, J., Ehinger, K., Oliva, A., Torralba, A.: Sun database: Large-scale scene recognition from abbey to zoo. In: CVPR, pp. 3485\u20133492 (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Li, L.J., Fei-Fei, L.: What, where and who? classifying events by scene and object recognition. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Patch to the future: Unsupervised visual prediction. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.416"},{"key":"28_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-642-15552-9_51","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J. Yuen","year":"2010","unstructured":"Yuen, J., Torralba, A.: A data-driven approach for event prediction. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 707\u2013720. Springer, Heidelberg (2010)"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Patterson, G., Hays, J.: Sun attribute database: Discovering, annotating, and recognizing scene attributes. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"28_CR19","unstructured":"Arietta, S., Agrawala, M., Ramamoorthi, R.: On relating visual elements to city statistics. Technical Report UCB\/EECS-2013-157, EECS Department, University of California, Berkeley (September 2013)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Khosla, A., An, B., Lim, J., Torralba, A.: Looking beyond the visible scene. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.474"},{"key":"28_CR21","unstructured":"Ehinger, K.A., Xiao, J., Torralba, A., Oliva, A.: Estimating scene typicality from human ratings and image features (2011)"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Toutanova, K., Klein, D., Manning, C., Singer, Y.: Feature-rich part-of-speech tagging with a cyclic dependency network. In: Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, pp. 173\u2013180 (2003)","DOI":"10.3115\/1073445.1073478"},{"key":"28_CR23","unstructured":"http:\/\/www.di.ens.fr\/willow\/research\/actionsfromscenes"},{"issue":"2","key":"28_CR24","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D.G. Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV\u00a060(2), 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"28_CR25","unstructured":"Abdel-Hakim, A.E., Farag, A.A.: Csift: A sift descriptor with color invariant characteristics. In: CVPR (2006)"},{"issue":"1","key":"28_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/TMM.2010.2091400","volume":"13","author":"K.E.A. Sande van de","year":"2011","unstructured":"van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Empowering visual categorization with the gpu. IEEE Transactions on Multimedia\u00a013(1), 60\u201370 (2011)","journal-title":"IEEE Transactions on Multimedia"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Chang, C.C., Lin, C.J.: Libsvm: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1\u201327:27 (2011)","DOI":"10.1145\/1961189.1961199"},{"issue":"2","key":"28_CR28","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","volume":"73","author":"J. Zhang","year":"2007","unstructured":"Zhang, J., Marsza\u0142ek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: A comprehensive study. IJCV\u00a073(2), 213\u2013238 (2007)","journal-title":"IJCV"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers, pp. 61\u201374. MIT Press (1999)","DOI":"10.7551\/mitpress\/1113.003.0008"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"28_CR31","unstructured":"Google: Panoramio service (2007), http:\/\/www.panoramio.com"},{"key":"28_CR32","unstructured":"Map of ski stations in france (2013), http:\/\/www.skiinfo.fr\/france\/carte.html"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2014"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10602-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T08:57:23Z","timestamp":1717232243000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10602-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319106014","9783319106021"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10602-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}