{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T21:10:02Z","timestamp":1748898602139,"version":"3.41.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2016,4,20]],"date-time":"2016-04-20T00:00:00Z","timestamp":1461110400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012164","name":"863 Program","doi-asserted-by":"crossref","award":["2014AA015104"],"award-info":[{"award-number":["2014AA015104"]}],"id":[{"id":"10.13039\/501100012164","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (CN)","doi-asserted-by":"publisher","award":["61273034"],"award-info":[{"award-number":["61273034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s00530-016-0514-9","type":"journal-article","created":{"date-parts":[[2016,4,20]],"date-time":"2016-04-20T06:32:04Z","timestamp":1461133924000},"page":"667-677","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic group activity annotation for mobile videos"],"prefix":"10.1007","volume":"23","author":[{"given":"Chaoyang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,20]]},"reference":[{"key":"514_CR1","doi-asserted-by":"crossref","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: ECCV (2012)","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"514_CR2","doi-asserted-by":"crossref","unstructured":"Antic, B., Ommer, B.: Learning latent constituents for recognition of group activities in video. In: European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10590-1_3"},{"key":"514_CR3","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. KDD workshop, vol. 10, pp. 359\u2013370 (1994)"},{"key":"514_CR4","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: Tenth IEEE International Conference on Computer Vision (ICCV), vol. 2, pp. 1395\u20131402 (2005)","DOI":"10.1109\/ICCV.2005.28"},{"issue":"6","key":"514_CR5","doi-asserted-by":"crossref","first-page":"1906","DOI":"10.1109\/TIP.2015.2404782","volume":"24","author":"X Chang","year":"2015","unstructured":"Chang, X., Zheng, W.-S., Zhang, J.: Learning person-person interaction in collective activity recognition. IEEE Trans. Image Process. 24(6), 1906\u20131918 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"514_CR6","doi-asserted-by":"crossref","unstructured":"Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: European Conference on Computer Vision (ECCV) (2012)","DOI":"10.1007\/978-3-642-33765-9_16"},{"key":"514_CR7","doi-asserted-by":"crossref","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing? Collective activity classification using spatio\u2013temporal relationship among people. In: IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1282\u20131289 (2009)","DOI":"10.1109\/ICCVW.2009.5457461"},{"key":"514_CR8","doi-asserted-by":"crossref","unstructured":"Choi, W., Shahid, K., Savarese, S.: Learning context for collective activity recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3273\u20133280 (2011)","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"514_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"issue":"1","key":"514_CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-011-0439-x","volume":"95","author":"C Desai","year":"2011","unstructured":"Desai, C., Ramanan, D., Fowlkes, C.C.: Discriminative models for multi-class object layout. Int. J. Comput. Vis. 95(1), 1\u201312 (2011)","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"514_CR11","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"P Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"514_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Srinivasan, P., Shi, J., Davis, L.S.: Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2012\u20132019 (2009)","DOI":"10.1109\/CVPRW.2009.5206492"},{"key":"514_CR13","doi-asserted-by":"crossref","unstructured":"Han, D., Bo, L., Sminchisescu, C.: Selection and context for action recognition. In: IEEE International Conference on Computer Vision (ICCV), vol. 9, pp. 1933\u20131940 (2009)","DOI":"10.1109\/ICCV.2009.5459427"},{"key":"514_CR14","doi-asserted-by":"crossref","unstructured":"Han, Y., Wu, F., Lu, X., Tian, Q., Zhuang, Y., Luo, J.: Correlated attribute transfer with multi-task graph-guided fusion. In: Proceedings of the 20th ACM international conference on Multimedia, ACM, pp. 529\u2013538 (2012)","DOI":"10.1145\/2393347.2393422"},{"issue":"6","key":"514_CR15","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1109\/TMM.2014.2321530","volume":"16","author":"Y Han","year":"2014","unstructured":"Han, Y., Wei, X., Cao, X., Yang, Y., Zhou, X.: Augmenting image descriptions using structured prediction output. IEEE Trans. Multimed. 16(6), 1665\u20131676 (2014)","journal-title":"IEEE Trans. Multimed."},{"key":"514_CR16","doi-asserted-by":"crossref","unstructured":"Jain, A., Gupta, A., Davis. L.S.: Learning what and how of contextual models for scene labeling. In: Computer Vision\u2014ECCV 2010. Springer, pp. 199\u2013212 (2010)","DOI":"10.1007\/978-3-642-15561-1_15"},{"key":"514_CR17","doi-asserted-by":"crossref","unstructured":"Kjellstr\u00f6m, H., Romero, J., Mart\u00ednez, D., Kragi\u0107, D.: Simultaneous visual recognition of manipulation actions and manipulated objects. In: Computer Vision\u2013ECCV 2008. Springer, pp. 336\u2013349 (2008)","DOI":"10.1007\/978-3-540-88688-4_25"},{"key":"514_CR18","unstructured":"Lan, T., Yang, W., Wang, Y., Mori, G.: Beyond actions: Discriminative models for contextual group activities. In: Advances in Neural Information Processing Systems 23, pp. 1216\u20131224 (2010)"},{"key":"514_CR19","doi-asserted-by":"crossref","unstructured":"Lan, T., Sigal, L., Mori, G.: Social roles in hierarchical models for human activity recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1354\u20131361 (2012)","DOI":"10.1109\/CVPR.2012.6247821"},{"issue":"8","key":"514_CR20","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1109\/TPAMI.2011.228","volume":"34","author":"T Lan","year":"2012","unstructured":"Lan, T., Wang, Y., Yang, W., et al.: Discriminative latent models for recognizing contextual group activities. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1549\u20131562 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"514_CR21","doi-asserted-by":"crossref","unstructured":"Li, R., Porfilio, P., Zickler, T.: Finding group interactions in social clutter. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2722\u20132729 (2013)","DOI":"10.1109\/CVPR.2013.351"},{"key":"514_CR22","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, IEEE, pp. 2929\u20132936 (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"514_CR23","first-page":"1499","volume":"16","author":"K Murphy","year":"2003","unstructured":"Murphy, K., Torralba, A., Freeman, W.: Using the forest to see the trees: a graphical model relating features, objects and scenes. Adv. Neural Inf. Process. Syst. 16, 1499\u20131506 (2003)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"514_CR24","doi-asserted-by":"crossref","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: IEEE 11th international conference on Computer Vision, 2007. ICCV 2007, IEEE, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"514_CR25","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio\u2013temporal relationship match: video structure comparison for recognition of complex human activities. In: IEEE 12th International Conference on Computer Vision, IEEE, pp. 1593\u20131600 (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"514_CR26","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, IEEE, vol. 3, pp. 32\u201336 (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"514_CR27","doi-asserted-by":"crossref","unstructured":"Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: Proceedings of the twenty-first international conference on Machine learning, ACM, p. 104 (2004)","DOI":"10.1145\/1015330.1015341"},{"issue":"16","key":"514_CR28","first-page":"1242","volume":"36","author":"W Choi","year":"2013","unstructured":"Choi, W., Savarese, S.: Understanding collective activities of people from videos. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1242\u20131257 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"514_CR29","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Grouplet: a structured image representation for recognizing human and object interactions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 9\u201316 (2010)","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"514_CR30","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 17\u201324 (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"514_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Nayak, N., Roy-Chowdhury, A.: Context-aware modeling and recognition of activities in video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2491\u20132498 (2013)","DOI":"10.1109\/CVPR.2013.322"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-016-0514-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-016-0514-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-016-0514-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-016-0514-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T20:33:09Z","timestamp":1748896389000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-016-0514-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,20]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["514"],"URL":"https:\/\/doi.org\/10.1007\/s00530-016-0514-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2016,4,20]]}}}