{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:41:06Z","timestamp":1743133266547,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319161983"},{"type":"electronic","value":"9783319161990"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-16199-0_7","type":"book-chapter","created":{"date-parts":[[2015,3,19]],"date-time":"2015-03-19T05:28:47Z","timestamp":1426742927000},"page":"95-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning Action Primitives for Multi-level Video Event Understanding"],"prefix":"10.1007","author":[{"given":"Tian","family":"Lan","sequence":"first","affiliation":[]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhiwei","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Guang-Tong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Greg","family":"Mori","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,3,20]]},"reference":[{"key":"7_CR1","unstructured":"Lan, T., Wang, Y., Yang, W., Mori, G.: Beyond actions: discriminative models for contextual group activities. In: NIPS (2010)"},{"key":"7_CR2","unstructured":"Lan, T., Sigal, L., Mori, G.: Social roles in hierarchical models for human activity recognition. In: CVPR (2012)"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-642-33765-9_16","volume-title":"Computer Vision \u2013 ECCV 2012","author":"W Choi","year":"2012","unstructured":"Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 215\u2013230. Springer, Heidelberg (2012)"},{"key":"7_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-642-33765-9_14","volume-title":"Computer Vision \u2013 ECCV 2012","author":"MR Amer","year":"2012","unstructured":"Amer, M.R., Xie, D., Zhao, M., Todorovic, S., Zhu, S.-C.: Cost-sensitive top-down\/bottom-up inference for multiscale activity recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 187\u2013200. Springer, Heidelberg (2012)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Yao, B., Fei-Fei, L.: Social role discovery in human events. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.320"},{"key":"7_CR6","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. T-PAMI 32, 1672\u20131645 (2010)","journal-title":"T-PAMI"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Turaga, P., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine recognition of human activities: A survey. T-CSVT (2008)","DOI":"10.1109\/TCSVT.2008.2005594"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: ICPR (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Grauman, K.: Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Maji, S., Bourdev, L., Malik, J.: Action recognition from a distributed representation of pose and appearance. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Jain, A., Gupta, A., Rodriguez, M., Davis, L.S.: Representing videos using mid-level discriminative patches. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.332"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., C.Schmid, Liu, C.L.: Action recognition by dense trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Raptis, M., Kokkinos, I., Soatto, S.: Discovering discriminative action parts from mid-level video representations. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Tian, Y., Sukthankar, R., Shah, M.: Spatiotemporal deformable part models for action detection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.341"},{"key":"7_CR15","unstructured":"Shugao Ma, Jianming Zhang, N.I.C., Sclaroff, S.: Action recognition and localization by hierarchical space-time segments. In: ICCV (2013)"},{"key":"7_CR16","unstructured":"Yamato, J., Ohya, J., Ishii, K.: Recognizing human action in time-sequential images using hidden markov model. In: CVPR (1992)"},{"key":"7_CR17","unstructured":"Moore, D., Essa, I.: Recognizing multitasked activities from video using stochastic context-free grammar. In: AAAI (2002)"},{"key":"7_CR18","unstructured":"Bobick, A., Wilson, A.: A state-based technique for the summarization and recognition of gesture. In: ICCV (1995)"},{"key":"7_CR19","unstructured":"Bregler, C.: Learning and recognizing human dynamics in video sequences. In: CVPR (1997)"},{"key":"7_CR20","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1109\/34.946990","volume":"23","author":"G M\u00e9dioni","year":"2001","unstructured":"M\u00e9dioni, G., Cohen, I., Br\u00e9mond, F., Hongeng, S., Nevatia, R.: Event detection and analysis from video streams. T-PAMI 23, 873\u2013889 (2001)","journal-title":"T-PAMI"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Ke, Y., Sukthankar, R., Hebert, M.: Event detection in crowded videos. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"7_CR22","unstructured":"Kl\u00e4ser, A., Marsza\u0142ek, M., Schmid, C., Zisserman, A.: Human focused action localization in video. In: International Workshop on Sign, Gesture, Activity (2010)"},{"key":"7_CR23","unstructured":"Lan, T., Wang, Y., Mori, G.: Discriminative figure-centric models for joint action localization and recognition. In: ICCV (2011)"},{"key":"7_CR24","unstructured":"Tran, D., Yuan, J.: Max-margin structured output regression for spatio-temporal action localization. In: NIPS (2012)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"7_CR26","unstructured":"Kitani, K.M., Okabe, T., Sato, Y., Sugimoto, A.: Discovering primitive action categories by leveraging relevant visual context. In: ECCV Workshop on Visual Surveillance (2008)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Hoai, M., Zisserman, A.: Discriminative sub-categorization. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.218"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Lan, T., Sigal, L., Raptis, M., Mori, G.: From subcategories to visual composites: a multi-level framework for object detection. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.53"},{"key":"7_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-642-15555-0_30","volume-title":"Computer Vision \u2013 ECCV 2010","author":"C Gu","year":"2010","unstructured":"Gu, C., Ren, X.: Discriminative mixture-of-templates for viewpoint classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 408\u2013421. Springer, Heidelberg (2010)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Todorovic, S., Ahuja, N.: Learning subcategory relevances for category recognition. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587366"},{"key":"7_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-642-33765-9_32","volume-title":"Computer Vision \u2013 ECCV 2012","author":"C Gu","year":"2012","unstructured":"Gu, C., Arbel\u00e1ez, P., Lin, Y., Yu, K., Malik, J.: Multi-component Models for object detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 445\u2013458. Springer, Heidelberg (2012)"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Sheikh, Y.A., Khan, E.A., Kanade, T.: Mode-seeking via medoidshifts. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408978"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Frey, B.J., Dueck, D.: Clustering by passing messages between data points. Science (2007)","DOI":"10.1126\/science.1136800"},{"key":"7_CR34","first-page":"265","volume":"2","author":"K Crammer","year":"2001","unstructured":"Crammer, K., Singer, Y.: On the algorithmic implementation of multiclass kernel-based vector machines. JMLR 2, 265\u2013292 (2001)","journal-title":"JMLR"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Do, T.M.T., Artieres, T.: Large margin training for hidden markov models with partially observed states. In: ICML (2009)","DOI":"10.1145\/1553374.1553408"},{"key":"7_CR36","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: collective activity classification using spatial-temporal relationship among people. In: International Workshop on Visual Surveillance (2009)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.J.: Action Bank: a high-level representation of activity in video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: Action MACH: a spatial-temporal maximum average correlation height filter for action recognition. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselares, T., Ferrari, V.: What is an object?. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"7_CR40","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88, 303\u2013338 (2010)","journal-title":"IJCV"}],"container-title":["Lecture Notes in Computer Science","Computer Vision - ECCV 2014 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-16199-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T09:29:44Z","timestamp":1575278984000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-16199-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319161983","9783319161990"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-16199-0_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"20 March 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}