{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T15:42:57Z","timestamp":1792856577657,"version":"4.5.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2-4","license":[{"start":{"date-parts":[[2017,5,22]],"date-time":"2017-05-22T00:00:00Z","timestamp":1495411200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1007\/s11263-017-1013-y","type":"journal-article","created":{"date-parts":[[2017,5,22]],"date-time":"2017-05-22T10:51:33Z","timestamp":1495450293000},"page":"375-389","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":258,"title":["Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos"],"prefix":"10.1007","volume":"126","author":[{"given":"Serena","family":"Yeung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Russakovsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykhaylo","family":"Andriluka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greg","family":"Mori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,5,22]]},"reference":[{"key":"1013_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 ."},{"key":"1013_CR2","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R. (2005). Actions as space-time shapes. In The Tenth IEEE International Conference on Computer Vision (ICCV\u201905).","DOI":"10.1109\/ICCV.2005.28"},{"key":"1013_CR3","doi-asserted-by":"crossref","unstructured":"Choi, M.\u00a0J., Lim, J.\u00a0J., Torralba, A., Willsky, A.\u00a0S. (2010). Exploiting hierarchical context on a large database of object categories. In CVPR.","DOI":"10.1109\/CVPR.2010.5540221"},{"key":"1013_CR4","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.\u00a0A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T. (2014). Long-term recurrent convolutional networks for visual recognition and description. arXiv:1411.4389 .","DOI":"10.21236\/ADA623249"},{"key":"1013_CR5","unstructured":"Fabian Caba\u00a0Heilbron, B.\u00a0G., Victor\u00a0Escorcia and Niebles, J.\u00a0C. (2015). Activitynet: A large-scale video benchmark for human activity understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (pp. 961\u2013970)."},{"key":"1013_CR6","unstructured":"Gkioxari, G., Malik, J. (2014). Finding action tubes. arXiv:1411.6031 ."},{"issue":"8","key":"1013_CR7","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"issue":"11","key":"1013_CR8","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., & Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. PAMI, 20(11), 1254\u20131259.","journal-title":"PAMI"},{"key":"1013_CR9","unstructured":"Jiang, Y.-G., Liu, J., Roshan\u00a0Zamir, A., Toderici, G., Laptev, I., Shah, M., Sukthankar, R. (2014). THUMOS challenge: Action recognition with a large number of classes. http:\/\/crcv.ucf.edu\/THUMOS14\/ ."},{"key":"1013_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2014.223"},{"key":"1013_CR11","doi-asserted-by":"crossref","unstructured":"Ke, Y., Sukthankar, R., Hebert, M. (2007). Event detection in crowded videos. In ICCV.","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"1013_CR12","doi-asserted-by":"crossref","unstructured":"Kitani, K.\u00a0M., Ziebart, B., Bagnell, J.\u00a0D., Hebert, M. (2012). Activity forecasting. In ECCV.","DOI":"10.1007\/978-3-642-33765-9_15"},{"key":"1013_CR13","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T. (2014). The language of actions: Recovering the syntax and semantics of goal-directed human activities. In CVPR.","DOI":"10.1109\/CVPR.2014.105"},{"key":"1013_CR14","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T. (2011). Hmdb: a large video database for human motion recognition. In ICCV.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1013_CR15","unstructured":"Lan, T., Wang, Y., Mori, G. (2011). Discriminative figure-centric models for joint action localization and recognition. In ICCV."},{"key":"1013_CR16","doi-asserted-by":"crossref","unstructured":"Lv, F.\u00a0J., Nevatia, R. (2007). Single view human action recognition using key pose matching and viterbi path searching. In CVPR.","DOI":"10.1109\/CVPR.2007.383131"},{"key":"1013_CR17","unstructured":"Mansimov, E., Srivastava, N., Salakhutdinov, R. (2015). Initialization strategies of spatio-temporal convolutional neural networks. arXiv:1503.07274 ."},{"key":"1013_CR18","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., Laptev, I., Schmid, C. (2009). Actions in context. In IEEE Conference on Computer Vision & Pattern Recognition.","DOI":"10.1109\/CVPR.2009.5206557"},{"issue":"1","key":"1013_CR19","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s00138-013-0527-8","volume":"25","author":"GK Myers","year":"2014","unstructured":"Myers, G. K., Nallapati, R., van Hout, J., Pancoast, S., Nevatia, R., Sun, C., et al. (2014). Evaluating multimedia features and fusion for example-based event detection. Machine Vision and Applications, 25(1), 17\u201332.","journal-title":"Machine Vision and Applications"},{"key":"1013_CR20","unstructured":"Ng, J.\u00a0Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G. (2015). Beyond short snippets: Deep networks for video classification. arXiv:1503.08909 ."},{"key":"1013_CR21","doi-asserted-by":"crossref","unstructured":"Ni, B., Paramathayalan, V.\u00a0R., Moulin, P. (2014). Multiple granularity analysis for fine-grained action detection. In CVPR.","DOI":"10.1109\/CVPR.2014.102"},{"key":"1013_CR22","doi-asserted-by":"crossref","unstructured":"Niebles, J.\u00a0C., Chen, C.-W., Fei-Fei, L. (2010). Modeling temporal structure of decomposable motion segments for activity classification. In ECCV.","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"1013_CR23","doi-asserted-by":"crossref","unstructured":"Oh, S., Hoogs, A., Perera, A., Cuntoor, N., Chen, C.-C., Lee, J.\u00a0T., Mukherjee, S., Aggarwal, J.\u00a0K., Lee, H., Davis, L., Swears, E., Wang, X., Ji, Q., Reddy, K., Shah, M., Vondrick, C., Pirsiavash, H., Ramanan, D., Yuen, J., Torralba, A., Song, B., Fong, A., Roy-Chowdhury, A., Desai, M. (2011) A large-scale benchmark dataset for event recognition in surveillance video. In IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2011.5995586"},{"issue":"1","key":"1013_CR24","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/s00138-013-0525-x","volume":"25","author":"S Oh","year":"2014","unstructured":"Oh, S., Mccloskey, S., Kim, I., Vahdat, A., Cannons, K. J., Hajimirsadeghi, H., et al. (2014). Multimedia event detection with multimodal feature fusion and temporal concept localization. Machine Vision and Applications, 25(1), 49\u201369.","journal-title":"Machine Vision and Applications"},{"key":"1013_CR25","unstructured":"Over, P., Awad, G., Michel, M., Fiscus, J., Kraaij, W., Smeaton, A.\u00a0F., Quenot, G. (2011). Trecvid 2011\u2014An overview of the goals, tasks, data, evaluation mechansims and metrics. In Proceedings of TRECVID 2011."},{"key":"1013_CR26","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D. (2014). Parsing videos of actions with segmental grammars. In CVPR.","DOI":"10.1109\/CVPR.2014.85"},{"key":"1013_CR27","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R. (2010). A survey on vision-based human action recognition. IVC, 28, 976\u2013990.","journal-title":"IVC"},{"key":"1013_CR28","unstructured":"Qinfeng\u00a0Shi, L.\u00a0W. A.\u00a0S., Cheng, Li (2011). Human action segmentation and recognition using discriminative semi-markov models. International Journal of Computer Vision, 93, May."},{"key":"1013_CR29","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B. (2012). A database for fine grained activity detection of cooking activities. In CVPR.","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"1013_CR30","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Rohrbach, A., Regneri, M., Amin, S., Andriluka, M., Pinkal, M., Schiele, B. (2015) Recognizing fine-grained and composite activities using hand-centric features and script data. arXiv:1502.06648 .","DOI":"10.1007\/s11263-015-0851-8"},{"issue":"3","key":"1013_CR31","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1013_CR32","doi-asserted-by":"crossref","unstructured":"Ryoo, M.\u00a0S., Aggarwal, J.\u00a0K. (2009). Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In IEEE International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"1013_CR33","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B. (2004). Recognizing human actions: A local svm approach. In ICPR.","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"1013_CR34","unstructured":"Shapovalova, N., Raptis, M., Sigal, L., Mori, G. (2013). Action is in the eye of the beholder: Eye-gaze driven model for spatio-temporal action localization. In NIPS."},{"key":"1013_CR35","unstructured":"Simonyan, K., Zisserman, A. (2014a). Two-stream convolutional networks for action recognition in videos. In NIPS."},{"key":"1013_CR36","unstructured":"Simonyan, K., Zisserman, A. (2014b). Very deep convolutional networks for large-scale image recognition. abs\/1409.1556."},{"key":"1013_CR37","unstructured":"Soomro, K., Zamir, A.\u00a0R., Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 ."},{"key":"1013_CR38","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R. (2015). Unsupervised learning of video representations using LSTMs. arXiv:1502.04681 ."},{"key":"1013_CR39","doi-asserted-by":"crossref","unstructured":"Tang, K., Fei-Fei, L., Koller, D. (2012). Learning latent temporal structure for complex event detection. In CVPR.","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"1013_CR40","doi-asserted-by":"crossref","unstructured":"Tian, Y., Sukthankar, R., Shah, M. (2013). Spatiotemporal deformable part models for action detection. In CVPR.","DOI":"10.1109\/CVPR.2013.341"},{"issue":"2","key":"1013_CR41","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., & Hinton, G. (2012). Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 4(2), 26\u201331.","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"issue":"1","key":"1013_CR42","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00138-013-0529-6","volume":"25","author":"W Tong","year":"2014","unstructured":"Tong, W., Yang, Y., Jiang, L., Yu, S.-I., Lan, Z., Ma, Z., et al. (2014). E-lamp: Integration of innovative ideas for multimedia event detection. Machine Vision and Applications, 25(1), 5\u201315.","journal-title":"Machine Vision and Applications"},{"key":"1013_CR43","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M. (2015) C3d: Generic features for video analysis. arXiv:1412.0767 ."},{"key":"1013_CR44","doi-asserted-by":"crossref","unstructured":"Vahdat, A., Gao, B., Ranjbar, M., Mori, G. (2011). A discriminative key pose sequence model for recognizing human interactions. In VS.","DOI":"10.1109\/ICCVW.2011.6130458"},{"key":"1013_CR45","unstructured":"Wang, P., Cao, Y., Shen, C., Liu, L., Shen, H.\u00a0T. (2015). Temporal pyramid pooling based convolutional neural networks for action recognition. arXiv:1503.01224 ."},{"key":"1013_CR46","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.-L. (2011). Action recognition by dense trajectories. In CVPR.","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"1013_CR47","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C. (2013). Action recognition with improved trajectories. In IEEE International Conference on Computer Vision, Sydney.","DOI":"10.1109\/ICCV.2013.441"},{"key":"1013_CR48","doi-asserted-by":"crossref","unstructured":"Weinland, D., Ronfard, R., Boyer, E. (2010). A survey of vision-based methods for action representation, segmentation and recognition. In CVIU, 115(2), (pp. 224\u2013241).","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"1013_CR49","unstructured":"Xu, K. et\u00a0al. (2015). Show, attend and tell: Neural image caption generation with visual attention. arXiv:1502.03044 ."},{"key":"1013_CR50","doi-asserted-by":"crossref","unstructured":"Yamato, J., Ohya, J., Ishii, K. (1992). Recognizing human action in time-sequential images using hidden markov model. In CVPR.","DOI":"10.1109\/CVPR.1992.223161"},{"key":"1013_CR51","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., & Courville, A. (2015). Video description generation incorporating spatio-temporal features and a soft-attention mechanism. arXiv:1502.08029 ."},{"key":"1013_CR52","unstructured":"Zha, S., Luisier, F., Andrews, W., Srivastava, N., Salakhutdinov, R. (2015). Exploiting image-trained cnn architectures for unconstrained video classification. arXiv:1503.04144 ."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-017-1013-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1013-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1013-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T18:51:14Z","timestamp":1569351074000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-017-1013-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,22]]},"references-count":52,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[2018,4]]}},"alternative-id":["1013"],"URL":"https:\/\/doi.org\/10.1007\/s11263-017-1013-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,22]]}}}