{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:35:44Z","timestamp":1783398944728,"version":"3.54.6"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319168166","type":"print"},{"value":"9783319168173","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-16817-3_15","type":"book-chapter","created":{"date-parts":[[2015,4,16]],"date-time":"2015-04-16T02:30:47Z","timestamp":1429151447000},"page":"222-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Thread-Safe: Towards Recognizing Human Actions Across Shot Boundaries"],"prefix":"10.1007","author":[{"given":"Minh","family":"Hoai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,4,17]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of the International Conference on Computer Vision (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"15_CR4","doi-asserted-by":"publisher","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, 2441\u20132453 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Hoai, M., Lan, Z.Z., De la Torre, F.: Joint segmentation and classification of human actions in video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2011)","DOI":"10.1109\/CVPR.2011.5995470"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Hoai, M., Zisserman, A.: Talking heads: detecting humans and recognizing their interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.117"},{"key":"15_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-540-88693-8_12","volume-title":"Computer Vision \u2013 ECCV 2008","author":"T Cour","year":"2008","unstructured":"Cour, T., Jordan, C., Miltsakaki, E., Taskar, B.: Movie\/Script: alignment and parsing of video and text transcription. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 158\u2013171. Springer, Heidelberg (2008)"},{"key":"15_CR9","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1109\/TMM.2006.876299","volume":"8","author":"Y Zhai","year":"2006","unstructured":"Zhai, Y., Shah, M.: Video scene segmentation using markov chain monte carlo. IEEE Trans. Multimed. 8, 686\u2013697 (2006)","journal-title":"IEEE Trans. Multimed."},{"key":"15_CR10","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1006\/cviu.1997.0628","volume":"71","author":"M Yeung","year":"1998","unstructured":"Yeung, M., Yeo, B.L., Liu, B.: Segmentation of video by clustering and graph analysis. Comput. Vis. Image Underst. 71, 94\u2013109 (1998)","journal-title":"Comput. Vis. Image Underst."},{"key":"15_CR11","unstructured":"Kender, J., Yeo, B.L.: Video scene segmentation via continuous video coherence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (1998)"},{"key":"15_CR12","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/TMM.2008.2008924","volume":"11","author":"VT Chasanis","year":"2009","unstructured":"Chasanis, V.T., Likas, A.C., Galatsanos, N.P.: Scene detection in videos using shot clustering and sequence alignment. IEEE Trans. Multimed. 11, 89\u2013100 (2009)","journal-title":"IEEE Trans. Multimed."},{"key":"15_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/11526346_32","volume-title":"Image and Video Retrieval","author":"B Lehane","year":"2005","unstructured":"Lehane, B., O\u2019Connor, N.E., Murphy, N.: Dialogue sequence detection in movies. In: Leow, W.-K., Lew, M., Chua, T.-S., Ma, W.-Y., Chaisorn, L., Bakker, E.M. (eds.) CIVR 2005. LNCS, vol. 3568, pp. 286\u2013296. Springer, Heidelberg (2005)"},{"key":"15_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/11944577_33","volume-title":"Technologies for Interactive Digital Storytelling and Entertainment","author":"B Lehane","year":"2006","unstructured":"Lehane, B., O\u2019Connor, N.E., Smeaton, A.F., Lee, H.: A system for event-based film browsing. In: G\u00f6bel, S., Malkewitz, R., Iurgel, I. (eds.) TIDSE 2006. LNCS, vol. 4326, pp. 334\u2013345. Springer, Heidelberg (2006)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Pickup, L., Zisserman, A.: Automatic retrieval of visual continuity errors in movies. In: ACM International Conference on Image and Video Retrieval (2009)","DOI":"10.1145\/1646396.1646406"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Bauml, M., Stiefelhagen, R.: Storygraphs: visualizing character interactions as a timeline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.111"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: Proceedings of the International Conference on Pattern Recognition (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"15_CR18","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. IEEE Trans. Pattern Anal. Mach. Intell. 29, 2247\u20132253 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR19","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2012","unstructured":"Reddy, K.K., Shah, M.: Recognizing 50 human action categories of web videos. Mach. Vis. Appl. 24, 971\u2013981 (2012)","journal-title":"Mach. Vis. Appl."},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Everingham, M., Sivic, J., Zisserman, A.: \u201chello! my name is ... Buffy\u201d - automatic naming of characters in tv video. In: Proceedings of the British Machine Vision Conference (2006)","DOI":"10.5244\/C.20.92"},{"key":"15_CR21","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1117\/12.238675","volume":"5","author":"JS Boreczky","year":"1996","unstructured":"Boreczky, J.S., Rowe, L.A.: Comparison of video shot boundary detection techniques. J. Electron. Imaging 5, 122\u2013128 (1996)","journal-title":"J. Electron. Imaging"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lienhart, R.: Comparison of automatic shot boundary detection algorithms. In: SPIE, vol. 3656 (1998)","DOI":"10.1117\/12.333848"},{"key":"15_CR23","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1142\/S021946780100027X","volume":"1","author":"R Lienhart","year":"2001","unstructured":"Lienhart, R.: Reliable transition detection in videos: a survey and practitioner\u2019s guide. Int. J. Image Graph. 1, 469\u2013486 (2001)","journal-title":"Int. J. Image Graph."},{"key":"15_CR24","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2005)"},{"key":"15_CR25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"15_CR26","series-title":"Lecturer Notes in Computer Science","first-page":"3","volume-title":"ACCV 2014","author":"M Hoai","year":"2014","unstructured":"Hoai, M., Zisserman, A.: Improving human action recognition using score distribution and ranking. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9007, pp. 3\u201320. Springer, Heidelberg (2014)"},{"key":"15_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher Kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010)"},{"key":"15_CR28","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1023\/A:1018628609742","volume":"9","author":"JAK Suykens","year":"1999","unstructured":"Suykens, J.A.K., Vandewalle, J.: Least squares support vector machine classifiers. Neural Process. Lett. 9, 293\u2013300 (1999)","journal-title":"Neural Process. Lett."},{"key":"15_CR29","unstructured":"Saunders, C., Gammerman, A., Vovk, V.: Ridge regression learning algorithm in dual variables. In: Proceedings of the International Conference on Machine Learning (1998)"},{"key":"15_CR30","doi-asserted-by":"publisher","DOI":"10.1142\/9789812776655","volume-title":"Least Squares Support Vector Machines","author":"JAK Suykens","year":"2002","unstructured":"Suykens, J.A.K., Gestel, T.V., Brabanter, J.D., DeMoor, B., Vandewalle, J.: Least Squares Support Vector Machines. World Scientific, Singapore (2002)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Tommasi, T., Caputo, B.: The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories. In: Proceedings of the British Machine Vision Conference (2009)","DOI":"10.5244\/C.23.80"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Hoai, M.: Regularized max pooling for image categorization. In: Proceedings of the British Machine Vision Conference (2014)","DOI":"10.5244\/C.28.32"},{"key":"15_CR33","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1016\/j.neunet.2004.07.002","volume":"17","author":"GC Cawley","year":"2004","unstructured":"Cawley, G.C., Talbot, N.L.: Fast exact leave-one-out cross-validation of sparse least-squares support vector machines. Neural Netw. 17, 1467\u20131475 (2004)","journal-title":"Neural Netw."},{"key":"15_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-642-33786-4_7","volume-title":"Computer Vision \u2013 ECCV 2012","author":"E Vig","year":"2012","unstructured":"Vig, E., Dorr, M., Cox, D.: Space-variant descriptor sampling for action recognition based on saliency and eye movements. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 84\u201397. Springer, Heidelberg (2012)"},{"key":"15_CR35","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1016\/j.patrec.2012.10.018","volume":"34","author":"MJ Marin-Jimenez","year":"2013","unstructured":"Marin-Jimenez, M.J., Yeguas, E., de la Blanca, N.P.: Exploring STIP-based models for recognizing human interactions in TV videos. PRL 34, 1819\u20131828 (2013)","journal-title":"PRL"},{"key":"15_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/978-3-642-33715-4_31","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y-G Jiang","year":"2012","unstructured":"Jiang, Y.-G., Dai, Q., Xue, X., Liu, W., Ngo, C.-W.: Trajectory-based modeling of human actions with motion reference points. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 425\u2013438. Springer, Heidelberg (2012)"},{"key":"15_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1007\/978-3-642-33709-3_60","volume-title":"Computer Vision \u2013 ECCV 2012","author":"S Mathe","year":"2012","unstructured":"Mathe, S., Sminchisescu, C.: Dynamic eye movement datasets and learnt saliency models for visual action recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 842\u2013856. Springer, Heidelberg (2012)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Recognizing activities with cluster-trees of tracklets. In: Proceedings of the British Machine Vision Conference (2012)","DOI":"10.5244\/C.26.30"}],"container-title":["Lecture Notes in Computer Science","Computer Vision -- ACCV 2014"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-16817-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:14:55Z","timestamp":1676938495000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-16817-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319168166","9783319168173"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-16817-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"17 April 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}