{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:34:15Z","timestamp":1783636455548,"version":"3.55.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464473","type":"print"},{"value":"9783319464480","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46448-0_31","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T08:27:24Z","timestamp":1474014444000},"page":"510-526","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":623,"title":["Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding"],"prefix":"10.1007","author":[{"given":"Gunnar A.","family":"Sigurdsson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"31_CR2","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: Neural Information Processing Systems (NIPS), pp. 487\u2013495 (2014)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Computer Vision and Pattern Recognition (CVPR), pp. 961\u2013970. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos in the wild. In: Computer Vision and Pattern Recognition (CVPR), pp. 1996\u20132003. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"31_CR5","unstructured":"Gorban, A., Idrees, H., Jiang, Y.G., Roshan Zamir, A., Laptev, I., Shah, M., Sukthankar, R.: THUMOS challenge: action recognition with a large number of classes (2015). http:\/\/www.thumos.info\/"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Computer Vision and Pattern Recognition (CVPR), pp. 1725\u20131732. IEEE (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"31_CR7","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: International Conference on Computer Vision (ICCV), pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"31_CR8","unstructured":"Soomro, K., Roshan Zamir, A., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. In: CRCV-TR-12-01 (2012)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marsza\u0142ek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Computer Vision and Pattern Recognition (CVPR), pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: Computer Vision and Pattern Recognition (CVPR), pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: Computer Vision and Pattern Recognition (CVPR). IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Sch\u00fcldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: International Conference on Pattern Recognition (ICPR), vol. 3, pp. 32\u201336. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"issue":"12","key":"31_CR13","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. Trans. Pattern Anal. Mach. Intell. 29(12), 2247\u20132253 (2007)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: Computer Vision and Pattern Recognition (CVPR), pp. 1194\u20131201. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Oh, S., Hoogs, A., Perera, A., Cuntoor, N., Chen, C.C., Lee, J.T., Mukherjee, S., Aggarwal, J., Lee, H., Davis, L., et al.: A large-scale benchmark dataset for event recognition in surveillance video. In: Computer Vision and Pattern Recognition (CVPR), pp. 3153\u20133160. IEEE (2011)","DOI":"10.1109\/AVSS.2011.6027400"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A.B., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Computer Vision and Pattern Recognition (CVPR). IEEE (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"31_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1007\/978-3-319-11752-2_15","volume-title":"Pattern Recognition","author":"A Rohrbach","year":"2014","unstructured":"Rohrbach, A., Rohrbach, M., Qiu, W., Friedrich, A., Pinkal, M., Schiele, B.: Coherent multi-sentence video description with variable level of detail. In: Jiang, X., Hornegger, J., Koch, R. (eds.) GCPR 2014. LNCS, vol. 8753, pp. 184\u2013195. Springer, Heidelberg (2014)"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., Schmid, C.: Actions in context. In: Computer Vision and Pattern Recognition (CVPR). IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"31_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1007\/978-3-642-03061-1_7","volume-title":"Statistical and Geometrical Approaches to Visual Motion Analysis","author":"V Ferrari","year":"2009","unstructured":"Ferrari, V., Mar\u00edn-Jim\u00e9nez, M., Zisserman, A.: 2D human pose estimation in TV shows. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds.) Statistical and Geometrical Approaches to Visual Motion Analysis. LNCS, vol. 5604, pp. 128\u2013147. Springer, Heidelberg (2009)"},{"key":"31_CR20","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pp. 190\u2013200. Association for Computational Linguistics (2011)"},{"key":"31_CR21","unstructured":"Torabi, A., Pal, C., Larochelle, H., Courville, A.: Using descriptive video services to create a large data source for video annotation research. arXiv preprint arXiv:1503.01070 (2015)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.S.: Objects in action: an approach for combining action understanding and object perception. In: Computer Vision and Pattern Recognition (CVPR), pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383331"},{"key":"31_CR23","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: International Conference on Computer Vision (ICCV), pp. 1593\u20131600. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Tuite, K., Snavely, N., Hsiao, D.Y., Tabing, N., Popovic, Z.: Photocity: training experts at large-scale image acquisition through a competitive game. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1383\u20131392. ACM (2011)","DOI":"10.1145\/1978942.1979146"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D.: Detecting activities of daily living in first-person camera views. In: Computer Vision and Pattern Recognition (CVPR), pp. 2847\u20132854. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Iwashita, Y., Takamine, A., Kurazume, R., Ryoo, M.S.: First-person animal activity recognition from egocentric videos. In: International Conference on Pattern Recognition (ICPR), Stockholm, Sweden, August 2014","DOI":"10.1109\/ICPR.2014.739"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Zitnick, C., Parikh, D.: Bringing semantics into focus using visual abstraction. In: Computer Vision and Pattern Recognition (CVPR), pp. 3009\u20133016. IEEE (2013)","DOI":"10.1109\/CVPR.2013.387"},{"key":"31_CR28","unstructured":"Salton, G., Mcgill, M.J.: Introduction to Modern Information Retrieval, pp. 24\u201351 (1983)"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Russakovsky, O., Farhadi, A., Laptev, I., Gupta, A.: Much ado about time: exhaustive annotation of temporal data. arXiv preprint arXiv:1607.07429 (2016)","DOI":"10.1609\/hcomp.v4i1.13290"},{"key":"31_CR30","unstructured":"Zipf, G.K.: The psycho-biology of language (1935)"},{"issue":"1","key":"31_CR31","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1146\/annurev.neuro.24.1.1193","volume":"24","author":"EP Simoncelli","year":"2001","unstructured":"Simoncelli, E.P., Olshausen, B.A.: Natural image statistics and neural representation. Ann. Rev. Neurosci. 24(1), 1193\u20131216 (2001)","journal-title":"Ann. Rev. Neurosci."},{"issue":"2579\u20132605","key":"31_CR32","first-page":"85","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(2579\u20132605), 85 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"31_CR34","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":"31_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"31_CR36","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems (NIPS) (2012)"},{"key":"31_CR37","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Neural Information Processing Systems (NIPS) (2014)"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"31_CR39","unstructured":"Chen, X., Fang, H., Lin, T., Vedantam, R., Gupta, S., Doll, P., Zitnick, C.L.: Microsoft coco captions: data collection and evaluation server. arXiv:1504.00325 (2015)"},{"key":"31_CR40","unstructured":"Devlin, J., Gupta, S., Girshick, R., Mitchell, M., Zitnick, C.L.: Exploring nearest neighbor approaches for image captioning. arXiv preprint arXiv:1505.04467 (2015)"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: International Conference on Computer Vision (ICCV), pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46448-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T04:25:31Z","timestamp":1692505531000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46448-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464473","9783319464480"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}