{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:18:45Z","timestamp":1761059925246,"version":"3.41.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,5,2]],"date-time":"2015-05-02T00:00:00Z","timestamp":1430524800000},"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":["World Wide Web"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s11280-015-0348-y","type":"journal-article","created":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T05:02:54Z","timestamp":1430456574000},"page":"265-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["From constrained to unconstrained datasets: an evaluation of local action descriptors and fusion strategies for interaction recognition"],"prefix":"10.1007","volume":"19","author":[{"given":"Chenqiang","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinhe","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeming","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,2]]},"reference":[{"key":"348_CR1","unstructured":"Cai, Y., Chen, Q., Brown, L., Datta, A., Fan, Q., Feris, R., Yan, S., Hauptmann, A., Pankanti, S.: Cmu-ibm-nus@trecvid 2012: Surveillance event detection. In: Proc. TRECVID (2012)"},{"issue":"3","key":"348_CR2","first-page":"27","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang, C-C., Lin, C-J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"issue":"5","key":"348_CR3","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1007\/s11280-013-0258-9","volume":"17","author":"S Chelaru","year":"2014","unstructured":"Chelaru, S., Orellana-Rodriguez, C., Altingovde, I.S.: How useful is social feedback for learning to rank youtube videos? World Wide Web 17(5), 997\u20131025 (2014)","journal-title":"World Wide Web"},{"key":"348_CR4","unstructured":"Chen, M-y., Hauptmann, A.: Mosift: Recognizing human actions in surveillance videos (2009)"},{"issue":"7","key":"348_CR5","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1109\/TIP.2005.849319","volume":"14","author":"DA Clausi","year":"2005","unstructured":"Clausi, D.A., Deng, H.: Design-based texture feature fusion using gabor filters and co-occurrence probabilities. IEEE Trans. Image Process. 14(7), 925\u2013936 (2005)","journal-title":"IEEE Trans. Image Process."},{"key":"348_CR6","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, ECCV, volume 1, pp. 1\u20132. Prague (2004)"},{"key":"348_CR7","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1, pp 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"348_CR8","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Computer Vision\u2013ECCV 2006, pp 428\u2013441. Springer (2006)","DOI":"10.1007\/11744047_33"},{"key":"348_CR9","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005. 2nd Joint IEEE International Workshop on, pp. 65\u201372. IEEE (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"issue":"4","key":"348_CR10","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/TMM.2010.2046265","volume":"12","author":"M Douze","year":"2010","unstructured":"Douze, M., J\u00e9gou, H., Schmid, C.: An image-based approach to video copy detection with spatio-temporal post-filtering. IEEE Trans. Multimedia 12(4), 257\u2013266 (2010)","journal-title":"IEEE Trans. Multimedia"},{"key":"348_CR11","unstructured":"Fu, Y., Jia, Y., Kong, Y.: Interactive phrases: Semantic descriptions for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell., 1 (2014)"},{"issue":"3","key":"348_CR12","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s11263-013-0677-1","volume":"107","author":"A Gaidon","year":"2014","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Activity representation with motion hierarchies. Int. J. Comput. Vis. 107(3), 219\u2013238 (2014)","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"348_CR13","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1093\/brain\/119.2.593","volume":"119","author":"V Gallese","year":"1996","unstructured":"Gallese, V., Fadiga, L., Fogassi, L., Rizzolatti, G.: Action recognition in the premotor cortex. Brain 119(2), 593\u2013609 (1996)","journal-title":"Brain"},{"issue":"7","key":"348_CR14","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1631\/jzus.C0910453","volume":"11","author":"Y-h Han","year":"2010","unstructured":"Han, Y-h., Shao, J., Wu, F., Wei, B-g.: Multiple hypergraph ranking for video concept detection. J. Zhejiang Univ. Sci. C 11(7), 525\u2013537 (2010)","journal-title":"J. Zhejiang Univ. Sci. C"},{"issue":"2","key":"348_CR15","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/TNNLS.2014.2314123","volume":"26","author":"Y Han","year":"2015","unstructured":"Han, Y., Yang, Y., Yan, Y., Ma, Z., Sebe, N., Zhou, X.: Semisupervised feature selection via spline regression for video semantic recognition. IEEE Trans. Neural Netw. Learn. Syst. 26(2), 252\u2013264 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"348_CR16","doi-asserted-by":"crossref","unstructured":"Hoai, M., Zisserman, A.: Improving human action recognition using score distribution and ranking. In: Proceedings of the Asian Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-16814-2_1"},{"issue":"4","key":"348_CR17","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1007\/s11280-013-0203-y","volume":"17","author":"G Huang","year":"2014","unstructured":"Huang, G., Zhang, Y., Cao, J., Steyn, M., Taraporewalla, K.: Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web 17(4), 569\u2013587 (2014)","journal-title":"World Wide Web"},{"key":"348_CR18","doi-asserted-by":"crossref","unstructured":"Kong, Y., Jia, Y., Yun, F.: Learning human interaction by interactive phrases. In: Computer Vision\u2013ECCV 2012, pp. 300\u2013313. Springer (2012)","DOI":"10.1007\/978-3-642-33718-5_22"},{"key":"348_CR19","doi-asserted-by":"crossref","unstructured":"Lan, Z-z., Bao, L., Yu, S-I., Liu, W., Hauptmann, A.G.: Double fusion for multimedia event detection. Springer (2012)","DOI":"10.1007\/978-3-642-27355-1_18"},{"issue":"2-3","key":"348_CR20","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2-3), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"348_CR21","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"348_CR22","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.inffus.2014.01.002","volume":"20","author":"G Lin","year":"2014","unstructured":"Lin, G., Zhu, H., Kang, X., Fan, C., Zhang, E.: Feature structure fusion and its application. Information Fusion 20, 146\u2013154 (2014)","journal-title":"Information Fusion"},{"key":"348_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Han, Y.: A real-world web cross-media dataset containing images, texts and videos. In: Proceedings of International Conference on Internet Multimedia Computing and Service, p. 332. ACM (2014)","DOI":"10.1145\/2632856.2632928"},{"issue":"2","key":"348_CR24","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"348_CR25","doi-asserted-by":"crossref","unstructured":"Ma, Z., Yang, Y., Sebe, N., Hauptmann, A. G.: Multiple features but few labels?: A symbiotic solution exemplified for video analysis. In: Proceedings of the ACM International Conference on Multimedia, pp. 77\u201386. ACM (2014)","DOI":"10.1145\/2647868.2654907"},{"key":"348_CR26","unstructured":"Nour el Houda Slimani, K., Benezeth, Y., Souami, F.: Human interaction recognition based on the co-occurrence of visual words. In: Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on, pp. 461\u2013466. IEEE (2014)"},{"key":"348_CR27","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with fisher vectors on a compact feature set. In: Computer Vision (ICCV), 2013 IEEE International Conference on, pp. 1817\u20131824. IEEE (2013)","DOI":"10.1109\/ICCV.2013.228"},{"issue":"12","key":"348_CR28","doi-asserted-by":"crossref","first-page":"2441","DOI":"10.1109\/TPAMI.2012.24","volume":"34","author":"A Patron-Perez","year":"2012","unstructured":"Patron-Perez, A., Marszalek, M., Reid, I., Zisserman, A.: Structured learning of human interactions in tv shows. IEEE Trans. Pattern Anal. Mach. Intell. 34(12), 2441\u20132453 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"348_CR29","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Computer Vision\u2013ECCV 2010, pp. 143\u2013156. Springer (2010)","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"348_CR30","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S.: Human activity prediction: Early recognition of ongoing activities from streaming videos. In: Computer Vision (ICCV), 2011 IEEE International Conference on, pp. 1036\u20131043. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"348_CR31","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: Computer vision, 2009 ieee 12th international conference on, pp. 1593\u20131600. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"348_CR32","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Chen, C-C., Aggarwal, J.K., Roy-Chowdhury, A.: An overview of contest on semantic description of human activities (sdha) 2010. In: Recognizing Patterns in Signals, Speech, Images and Videos, pp. 270\u2013285. Springer (2010)","DOI":"10.1007\/978-3-642-17711-8_28"},{"key":"348_CR33","doi-asserted-by":"crossref","unstructured":"Sener, F., Bas, C., Ikizler-Cinbis, N.: On recognizing actions in still images via multiple features. In: Computer Vision\u2013ECCV 2012. Workshops and Demonstrations, pp. 263\u2013272. Springer (2012)","DOI":"10.1007\/978-3-642-33885-4_27"},{"key":"348_CR34","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, pp. 1470\u20131477. IEEE (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"348_CR35","doi-asserted-by":"crossref","unstructured":"Snoek, C.G.M., Worring, M., Smeulders, A.W.M: Early versus late fusion in semantic video analysis. In: Proceedings of the 13th annual ACM international conference on Multimedia, pp. 399\u2013402. ACM (2005)","DOI":"10.1145\/1101149.1101236"},{"key":"348_CR36","doi-asserted-by":"crossref","unstructured":"Vahdat, A., Gao, B., Ranjbar, M., Mori, G.: A discriminative key pose sequence model for recognizing human interactions. In: Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, pp. 1729\u20131736. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130458"},{"key":"348_CR37","doi-asserted-by":"crossref","unstructured":"Waltisberg, D., Yao, A., Gall, J., Gool, L.V.: Variations of a hough-voting action recognition system. In: Recognizing Patterns in Signals, Speech, Images and Videos, pp. 306\u2013312. Springer (2010)","DOI":"10.1007\/978-3-642-17711-8_31"},{"key":"348_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Klaser, A., Schmid, C., Liu, C-L.: Action recognition by dense trajectories. In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pp. 3169\u20133176. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"348_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Ullah, M.M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: BMVC 2009-British Machine Vision Conference, pp. 124\u20131. BMVA Press (2009)","DOI":"10.5244\/C.23.124"},{"issue":"2","key":"348_CR40","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.cviu.2006.07.013","volume":"104","author":"D Weinland","year":"2006","unstructured":"Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Comput. Vis. Image Underst. 104(2), 249\u2013257 (2006)","journal-title":"Comput. Vis. Image Underst."},{"key":"348_CR41","doi-asserted-by":"crossref","unstructured":"Wu, J., Chen, F., Hu, D.: Human interaction recognition by spatial structure models. In: Intelligence Science and Big Data Engineering, pp. 216\u2013222. Springer (2013)","DOI":"10.1007\/978-3-642-42057-3_28"},{"key":"348_CR42","doi-asserted-by":"crossref","unstructured":"Xia, L., Aggarwal, J.K.: Spatio-temporal depth cuboid similarity feature for activity recognition using depth camera. In: Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 2834\u20132841. IEEE (2013)","DOI":"10.1109\/CVPR.2013.365"},{"key":"348_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ma, Z., Nie, F., Chang, X., Hauptmann, A.G.: Multi-class active learning by uncertainty sampling with diversity maximization. Int. J. Comput. Vis., 1\u201315 (2014)","DOI":"10.1007\/s11263-014-0781-x"},{"key":"348_CR44","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ma, Z., Xu, Z., Yan, S., Hauptmann, A.G.: How related exemplars help complex event detection in web videos?. In: Computer Vision (ICCV), 2013 IEEE International Conference on, pp. 2104\u20132111. IEEE (2013)","DOI":"10.1109\/ICCV.2013.456"},{"issue":"3","key":"348_CR45","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1109\/TMM.2012.2234731","volume":"15","author":"Y Yang","year":"2013","unstructured":"Yang, Y., Song, J., Huang, Z., Ma, Z., Sebe, N., Hauptmann, A.G.: Multi-feature fusion via hierarchical regression for multimedia analysis. IEEE Trans. Multimedia 15(3), 572\u2013581 (2013)","journal-title":"IEEE Trans. Multimedia"},{"key":"348_CR46","unstructured":"Ye, G., Liu, D., Jhuo, I-H., Chang, S-F.: Robust late fusion with rank minimization. In: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 3021\u20133028. IEEE (2012)"},{"key":"348_CR47","doi-asserted-by":"crossref","unstructured":"Yu, T-H., Kim, T-K., Cipolla, R.: Real-time action recognition by spatiotemporal semantic and structural forests. In: BMVC, vol. 2 (2010)","DOI":"10.5244\/C.24.52"},{"key":"348_CR48","unstructured":"Yuan, C., Li, X., Hu, W., Ling, H., Maybank, S.: 3d r transform on spatio-temporal interest points for action recognition. In: Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 724\u2013730. IEEE (2013)"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-015-0348-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-015-0348-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-015-0348-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T19:20:42Z","timestamp":1748373642000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-015-0348-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,2]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["348"],"URL":"https:\/\/doi.org\/10.1007\/s11280-015-0348-y","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2015,5,2]]}}}