{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T04:20:54Z","timestamp":1745382054086,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642357480"},{"type":"electronic","value":"9783642357497"}],"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\/978-3-642-35749-7_13","type":"book-chapter","created":{"date-parts":[[2012,11,30]],"date-time":"2012-11-30T04:03:40Z","timestamp":1354248220000},"page":"168-180","source":"Crossref","is-referenced-by-count":7,"title":["Middle-Level Representation for Human Activities Recognition: The Role of Spatio-Temporal Relationships"],"prefix":"10.1007","author":[{"given":"Fei","family":"Yuan","sequence":"first","affiliation":[]},{"given":"V\u00e9ronique","family":"Prinet","sequence":"additional","affiliation":[]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"13_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1007\/3-540-47969-4_42","volume-title":"Computer Vision - ECCV 2002","author":"J. Sullivan","year":"2002","unstructured":"Sullivan, J., Carlsson, S.: Recognizing and Tracking Human Action. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part I. LNCS, vol.\u00a02350, pp. 629\u2013644. Springer, Heidelberg (2002)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local svm approach. In: Proc. of Int. Computer Vision and Pattern Recognition, CVPR (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: Proc. of Int. Conf. on Computer Vision, ICCV, pp. 1395\u20131402 (2005)","DOI":"10.1109\/ICCV.2005.28"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Li, R., Chellappa, R.: Recognizing coordinated multi-object activities using a dynamic event ensemble model. In: Proc. of Int. Acoustics, Speech, and Signal Processing, pp. 3541\u20133544 (2009)","DOI":"10.1109\/ICASSP.2009.4960390"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Turaga, P., Chellappa, R.: Locally time-invariant models of human activities using trajectories on the grassmannian. In: Proc. of Int. Computer Vision and Pattern Recognition, CVPR, pp. 2435\u20132441 (2009)","DOI":"10.1109\/CVPRW.2009.5206710"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In: Proc. of Int. Conf. on Computer Vision, ICCV, pp. 1593\u20131600 (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marsza\u0142ek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proc. of Conf. on Computer Vision and Pattern Recognition, CVPR, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"13_CR8","unstructured":"Yuan, J., Liu, Z., Wu, Y.: Discriminative video pattern search for efficient action detection. In: Proc. of Int. Computer Vision and Pattern Recognition, CVPR (2009)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Cao, L., Liu, Z., Huang, T.S.: Cross-dataset action recognition. In: Proc. of Int. Computer Vision and Pattern Recognition, CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539875"},{"key":"13_CR10","unstructured":"Wang, Y., Mori, G.: Learning a discriminative hidden part model for human action recognition. In: Advances in Neural Information Processing Systems, NIPS, vol.\u00a021 (2008)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Thi, T.H., Lu, S., Zhang, J., Cheng, L., Wang, L.: Human body articulation for action recognition in video sequences. In: Proc. of Int. Conf. on Advanced Video and Signal Based Surveillance, pp. 92\u201397 (2009)","DOI":"10.1109\/AVSS.2009.41"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Yao, B., Zhu, S.C.: Learning deformable action templates from cluttered videos. In: Proc. of Int. Conf. on Computer Vision, ICCV, pp. 1507\u20131514 (2009)","DOI":"10.1109\/ICCV.2009.5459277"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Niebles, J., Fei-Fei, L.: A hierarchical model of shape and appearance for human action classification. In: Proc. of Conf. in Computer Vision and Pattern Recognition, CVPR (2007)","DOI":"10.1109\/CVPR.2007.383132"},{"key":"13_CR14","unstructured":"Sun, J., Wu, X., Yan, S., Cheong, L.F., Chua, T.S., Li, J.: Hierarchical spatio-temporal context modeling for action recognition. In: Proc. of Conf. on Computer Vision and Pattern Recognition, CVPR, pp. 2004\u20132011 (2009)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Messing, R., Pal, C., Kautz, H.: Activity recognition using the velocity histories of tracked keypoints. In: Proc. of Int. Conf. on Computer Vision, ICCV, Washington, DC, USA (2009)","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Laptev, I., Lindeberg, T.: On space-time interest points. In: Proc. Int. Conf. on Computer Vision, ICCV, pp. 432\u2013439 (2003)","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: Proc. Int. Conf. on Computer Vision, ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238420"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Lin, Z., Jiang, Z., Davis, L.: Recognizing actions by shape-motion prototype trees. In: Proc. Int. Conf. on Computer Vision, ICCV, pp. 444\u2013451 (2009)","DOI":"10.1109\/ICCV.2009.5459184"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Li, L.J., Fei-Fei, L.: What, where and who? classifying event by scene and object recognition. In: Proc. of IEEE Intern. Conf. in Computer Vision, ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos \u2019in the wild\u2019. In: Proc. of Int. Computer Vision and Pattern Recognition, CVPR, pp. 1996\u20132003 (2009)","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Wu, J., Osuntogun, A., Choudhury, T., Philipose, M., Rehg, J.M.: A scalable approach to activity recognition based on object use. In: Proc. of IEEE Intern. Conf. in Computer Vision, ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408865"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Ke, Y., Sukthankar, R., Hebert, M.: Event detection in crowded videos. In: Proc. of IEEE Intern. Conf. in Computer Vision, ICCV (2007)","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"13_CR23","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","volume":"27","author":"K. Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. on Pattern Analysis & Machine Intelligence\u00a027, 1615\u20131630 (2005)","journal-title":"IEEE Trans. on Pattern Analysis & Machine Intelligence"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Rao, S., Tron, R., Vidal, R., Ma, Y.: Motion segmentation in the presence of outlying, incomplete, or corrupted trajectories. IEEE Trans. on Pattern Analysis and Machine Intelligence 99 (2009)","DOI":"10.1109\/CVPR.2008.4587437"},{"key":"13_CR25","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"P.F. Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision\u00a059, 167\u2013181 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR26","doi-asserted-by":"publisher","first-page":"201","DOI":"10.3758\/BF03212378","volume":"14","author":"G. Johansson","year":"1973","unstructured":"Johansson, G.: Visual perception of biological motion and a model for its analysis. Perception and Psychophysics\u00a014, 201\u2013211 (1973)","journal-title":"Perception and Psychophysics"},{"key":"13_CR27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1006\/cviu.2000.0890","volume":"81","author":"Y. Song","year":"2001","unstructured":"Song, Y., Goncalves, L., Bernardo, E.D., Perona, P.: Monocular perception of biological motion in johansson displays. Comput. Vis. Image Underst.\u00a081, 303\u2013327 (2001)","journal-title":"Comput. Vis. Image Underst."},{"key":"13_CR28","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1023\/A:1020350100748","volume":"50","author":"C. Rao","year":"2002","unstructured":"Rao, C., Yilmaz, A., Shah, M.: View-invariant representation and recognition of actions. Int. J. Comput. Vision\u00a050, 203\u2013226 (2002)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR29","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/34.56205","volume":"12","author":"P. Perona","year":"1990","unstructured":"Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a012, 629\u2013639 (1990)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"13_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-540-88688-4_22","volume-title":"Computer Vision \u2013 ECCV 2008","author":"I.N. Junejo","year":"2008","unstructured":"Junejo, I.N., Dexter, E., Laptev, I., P\u00e9rez, P.: Cross-View Action Recognition from Temporal Self-similarities. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol.\u00a05303, pp. 293\u2013306. Springer, Heidelberg (2008)"}],"container-title":["Lecture Notes in Computer Science","Trends and Topics in Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35749-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T00:18:35Z","timestamp":1745367515000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35749-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642357480","9783642357497"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35749-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}