{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T04:10:59Z","timestamp":1750911059929,"version":"3.41.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T00:00:00Z","timestamp":1506297600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61401286"],"award-info":[{"award-number":["61401286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation for Distinguished Young Talents in Higher Education in Guangdong","award":["2014KQNCX132"],"award-info":[{"award-number":["2014KQNCX132"]}]},{"name":"Shenzhen Science and Technology Project","award":["JCYJ20160307143441261"],"award-info":[{"award-number":["JCYJ20160307143441261"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1007\/s11760-017-1172-x","type":"journal-article","created":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T08:23:17Z","timestamp":1506327797000},"page":"403-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A unified model of appearance and motion of video and its application in STIP detection"],"prefix":"10.1007","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8814-4628","authenticated-orcid":false,"given":"Yanshan","family":"Li","sequence":"first","affiliation":[]},{"given":"Rongjie","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Weixin","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,9,25]]},"reference":[{"key":"1172_CR1","doi-asserted-by":"crossref","unstructured":"Laptev, I., Lindeberg, T.: Space-time interest points. In: International Conference on Computer Vision, vol. 1, pp. 432\u2013439. IEEE Xplore (2003)","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"1172_CR2","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Grauman, K.: Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, 13\u201318 June, pp. 2046\u20132053. DBLP (2010)","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"1172_CR3","doi-asserted-by":"crossref","unstructured":"Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1446\u20131453. DBLP (2009)","DOI":"10.1109\/CVPR.2009.5206771"},{"issue":"5","key":"1172_CR4","doi-asserted-by":"crossref","first-page":"2487","DOI":"10.1007\/s11042-015-2637-y","volume":"75","author":"Y Li","year":"2016","unstructured":"Li, Y., Liu, W., Huang, Q.: Traffic anomaly detection based on image descriptor in videos. Multimedia Tools Appl. 75(5), 2487\u20132505 (2016)","journal-title":"Multimedia Tools Appl."},{"key":"1172_CR5","doi-asserted-by":"crossref","unstructured":"Gao, H.P., Yang, Z.Q.: Content based video retrieval using spatiotemporal salient objects. In: International Symposium on Intelligence Information Processing and Trusted Computing, pp. 689\u2013692. IEEE Computer Society (2010)","DOI":"10.1109\/IPTC.2010.30"},{"issue":"1","key":"1172_CR6","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s13735-013-0042-8","volume":"3","author":"C Chattopadhyay","year":"2014","unstructured":"Chattopadhyay, C., Maurya, A.K.: Multivariate time series modeling of geometric features of spatio-temporal volumes for content based video retrieval. Int. J. Multimedia Inf. Retr. 3(1), 15\u201328 (2014)","journal-title":"Int. J. Multimedia Inf. Retr."},{"issue":"1","key":"1172_CR7","first-page":"150","volume":"39","author":"MY Chen","year":"2009","unstructured":"Chen, M.Y., Hauptmann, A.: MoSIFT: recognizing human actions in surveillance videos. Ann. Pharmacother. 39(1), 150\u2013152 (2009)","journal-title":"Ann. Pharmacother."},{"key":"1172_CR8","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.ins.2013.12.022","volume":"281","author":"Y Li","year":"2014","unstructured":"Li, Y., Liu, W., Li, X., et al.: GA-SIFT: a new scale invariant feature transform for multispectral image using geometric algebra. Inf. Sci. 281, 559\u2013572 (2014)","journal-title":"Inf. Sci."},{"issue":"7","key":"1172_CR9","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1109\/TSP.2003.812734","volume":"51","author":"CE Moxey","year":"2003","unstructured":"Moxey, C.E., Sangwine, S.J., Ell, T.A.: Hypercomplex correlation techniques for vector images. IEEE Trans. Signal Process. 51(7), 1941\u20131953 (2003)","journal-title":"IEEE Trans. Signal Process."},{"key":"1172_CR10","doi-asserted-by":"crossref","unstructured":"Ebling, J., Scheuermann, G.: Clifford convolution and pattern matching on vector fields. In: IEEE Visualization, p. 26. IEEE Computer Society (2003)","DOI":"10.1109\/VISUAL.2003.1250372"},{"issue":"3","key":"1172_CR11","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1023\/A:1007901028047","volume":"26","author":"J Lasenby","year":"1998","unstructured":"Lasenby, J., Fitzgerald, W.J., Lasenby, A.N., et al.: New geometric methods for computer vision: an application to structure and motion estimation. Int. J. Comput. Vis. 26(3), 191\u2013213 (1998)","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"1172_CR12","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s00006-009-0173-4","volume":"20","author":"E Bayro-Corrochano","year":"2010","unstructured":"Bayro-Corrochano, E.: What can Hamilton, Grassmann, Clifford and Hestenes tell us about perception and action systems. Adv. Appl. Clifford Algebras 20(2), 217\u2013240 (2010)","journal-title":"Adv. Appl. Clifford Algebras"},{"key":"1172_CR13","doi-asserted-by":"crossref","first-page":"10323","DOI":"10.1109\/ACCESS.2017.2712789","volume":"5","author":"Y Li","year":"2017","unstructured":"Li, Y., Xia, R., Huang, Q., et al.: Survey of spatio-temporal interest point detection algorithms in video. IEEE Access 5, 10323\u201310331 (2017)","journal-title":"IEEE Access"},{"key":"1172_CR14","doi-asserted-by":"crossref","unstructured":"Harris, C.: A combined corner and edge detector. In: Proceedings on Alvey Vision Conference, 1988, No. 3, pp. 147\u2013151 (1988)","DOI":"10.5244\/C.2.23"},{"key":"1172_CR15","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., et\u00a0al.: Behavior recognition via sparse spatio-temporal features. In: IEEE International Workshop on Visual Surveillance and PERFORMANCE Evaluation of Tracking and Surveillance, pp. 65\u201372. IEEE (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"issue":"3","key":"1172_CR16","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay, H., Ess, A., Tuytelaars, T., et al.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346\u2013359 (2008)","journal-title":"Comput. Vis. Image Underst."},{"key":"1172_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., Shah, M.: Learning human actions via information maximization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587723"},{"key":"1172_CR18","doi-asserted-by":"crossref","unstructured":"Willems, G., Tuytelaars, T., Gool, L.V.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Computer Vision\u2014ECCV 2008, European Conference on Computer Vision, Marseille, France, 12\u201318 Oct 2008, Proceedings, pp. 650\u2013663. DBLP (2008)","DOI":"10.1007\/978-3-540-88688-4_48"},{"issue":"3","key":"1172_CR19","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.cviu.2011.09.010","volume":"116","author":"B Chakraborty","year":"2012","unstructured":"Chakraborty, B., Holte, M.B., Moeslund, T.B., et al.: Selective spatio-temporal interest points. Comput. Vis. Image Underst. 116(3), 396\u2013410 (2012)","journal-title":"Comput. Vis. Image Underst."},{"key":"1172_CR20","doi-asserted-by":"crossref","unstructured":"Matikainen, P., Hebert, M., Sukthankar, R.: Representing pairwise spatial and temporal relations for action recognition. In: Computer Vision\u2014ECCV 2010, pp. 508\u2013521. Springer, Berlin (2010)","DOI":"10.1007\/978-3-642-15549-9_37"},{"key":"1172_CR21","doi-asserted-by":"crossref","unstructured":"Dhillon, P.S., Nowozin, S., Lampert, C.H.: Combining appearance and motion for human action classification in videos. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2009, vol. 36, no. 3, pp. 22\u201329. CVPR Workshops 2009 (2009)","DOI":"10.1109\/CVPRW.2009.5204237"},{"key":"1172_CR22","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild (2012). arXiv:1212.0402 (preprint)"},{"key":"1172_CR23","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., Shah, M.: A 3-dimensional SIFT descriptor and its application to action recognition. In: Proceedings of the 15th ACM International Conference on Multimedia, pp. 357\u2013360. ACM (2007)","DOI":"10.1145\/1291233.1291311"},{"key":"1172_CR24","unstructured":"Cho, H., Lee, H., Jiang, Z.: Evaluation of LC-KSVD on UCF101 action dataset. In: ICCV Workshop on Action Recognition with a Large Number of Classes (2013)"},{"key":"1172_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., et\u00a0al.: Large-scale video classification with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"1172_CR26","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Rohrbach, M., et\u00a0al.: Long-term recurrent convolutional networks for visual recognition and description. In: Computer Vision and Pattern Recognition, pp. 2625\u20132634. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1172_CR27","unstructured":"Du, T., Bourdev, L., Fergus, R., et\u00a0al.: C3D: generic features for video analysis. Eprint arXiv (2014)"},{"issue":"4","key":"1172_CR28","first-page":"568","volume":"1","author":"D Annane","year":"2014","unstructured":"Annane, D., Chevrolet, J.C., Chevret, S., et al.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 1(4), 568\u2013576 (2014)","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11760-017-1172-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-017-1172-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-017-1172-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T21:54:00Z","timestamp":1750888440000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11760-017-1172-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,25]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["1172"],"URL":"https:\/\/doi.org\/10.1007\/s11760-017-1172-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2017,9,25]]}}}