{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T10:34:27Z","timestamp":1742639667244,"version":"3.37.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319735993"},{"type":"electronic","value":"9783319736006"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-73600-6_14","type":"book-chapter","created":{"date-parts":[[2018,1,12]],"date-time":"2018-01-12T04:13:02Z","timestamp":1515730382000},"page":"153-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Global and Local C3D Ensemble System for First Person Interactive Action Recognition"],"prefix":"10.1007","author":[{"given":"Lingling","family":"Fa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,1,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"issue":"1","key":"14_CR2","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60\u201379 (2013)","journal-title":"Int. J. Comput. Vis."},{"issue":"2\u20133","key":"14_CR3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I., Lindeberg, T.: On space-time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition, pp. 357\u2013360 (2007)","DOI":"10.1145\/1291233.1291311"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks, pp. 4489\u20134497 (2014)","DOI":"10.1109\/ICCV.2015.510"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Singh, S., Arora, C., Jawahar, C.V.: First person action recognition using deep learned descriptors. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.287"},{"key":"14_CR7","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: Computer Vision and Pattern Recognition, pp. 3281\u20133288 (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"14_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/978-3-642-33718-5_23","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Fathi","year":"2012","unstructured":"Fathi, A., Li, Y., Rehg, J.M.: Learning to recognize daily actions using gaze. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 314\u2013327. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_23"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition, pp. 1894\u20131903 (2016)","DOI":"10.1109\/CVPR.2016.209"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Poleg, Y., Ephrat, A., Peleg, S., Arora, C.: Compact CNN for indexing egocentric videos. Computer Science, pp. 1\u20139 (2016)","DOI":"10.1109\/WACV.2016.7477708"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Lee, J., Ryoo, M.S.: Learning robot activities from first-person human videos using convolutional future regression (2017)","DOI":"10.1109\/CVPRW.2017.63"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Kitani, K.M., Okabe, T., Sato, Y., Sugimoto, A.: Fast unsupervised ego-action learning for first-person sports videos. In: Computer Vision and Pattern Recognition, pp. 3241\u20133248 (2011)","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Matthies, L.: First-person activity recognition: what are they doing to me? In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2730\u20132737 (2013)","DOI":"10.1109\/CVPR.2013.352"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Choi, J., Jeon, W.J., Lee, S.C.: Spatio-temporal pyramid matching for sports videos. In: ACM International Conference on Multimedia Information Retrieval, pp. 291\u2013297 (2008)","DOI":"10.1145\/1460096.1460144"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S.: Human activity prediction: early recognition of ongoing activities from streaming videos. In: IEEE International Conference on Computer Vision, pp. 1036\u20131043 (2012)","DOI":"10.1109\/ICCV.2011.6126349"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-73600-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T04:55:23Z","timestamp":1570596923000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-73600-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319735993","9783319736006"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-73600-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}