{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:43:35Z","timestamp":1765039415262,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012632"},{"type":"electronic","value":"9783030012649"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01264-9_39","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:20:53Z","timestamp":1538986853000},"page":"660-676","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Scenes-Objects-Actions: A Multi-task, Multi-label Video Dataset"],"prefix":"10.1007","author":[{"given":"Jamie","family":"Ray","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Du","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matt","family":"Feiszli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Torresani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manohar","family":"Paluri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"39_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)"},{"key":"39_CR2","unstructured":"Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432 (2015)"},{"key":"39_CR3","unstructured":"Caffe2-Team: Caffe2: A New Lightweight, Modular, and Scalable Deep Learning Framework. https:\/\/caffe2.ai\/"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"39_CR5","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: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"39_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","volume-title":"Image Analysis","author":"G Farneb\u00e4ck","year":"2003","unstructured":"Farneb\u00e4ck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363\u2013370. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45103-X_50"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.C.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The? Something something? Video database for learning and evaluating visual common sense. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNS retrace the history of 2D CNNS and ImageNet? arXiv preprint arXiv:1711.09577 (2017)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR12","unstructured":"Huh, M., Agrawal, P., Efros, A.A.: What makes ImageNet good for transfer learning? arXiv preprint arXiv:1608.08614 (2016)"},{"key":"39_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-642-15549-9_36","volume-title":"Computer Vision \u2013 ECCV 2010","author":"N Ikizler-Cinbis","year":"2010","unstructured":"Ikizler-Cinbis, N., Sclaroff, S.: Object, scene and actions: combining multiple features for human action recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 494\u2013507. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_36"},{"key":"39_CR14","unstructured":"ILSVRC-2015-VID: ImageNet Object Detection from Video Challenge. https:\/\/www.kaggle.com\/c\/imagenet-object-detection-from-video-challenge"},{"key":"39_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"issue":"1","key":"39_CR16","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE TPAMI 35(1), 221\u2013231 (2013)","journal-title":"IEEE TPAMI"},{"issue":"5","key":"39_CR17","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/TCSVT.2011.2129870","volume":"21","author":"YG Jiang","year":"2011","unstructured":"Jiang, Y.G., Li, Z., Chang, S.F.: Modeling scene and object contexts for human action retrieval with few examples. IEEE Trans. Circuits Syst. Video Technol. 21(5), 674\u2013681 (2011)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"39_CR18","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"39_CR19","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"39_CR20","volume-title":"Probabilistic Graphical Models: Principles and Techniques","author":"D Koller","year":"2009","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB51: a large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"39_CR22","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: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"2\u20133","key":"39_CR23","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Long, X., et al.: Multimodal keyless attention fusion for video classification (2018)","DOI":"10.1609\/aaai.v32i1.12319"},{"key":"39_CR25","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579\u20132605 (2008)"},{"issue":"11","key":"39_CR26","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"39_CR27","unstructured":"Pantofaru, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions (2017)"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Real, E., Shlens, J., Mazzocchi, S., Pan, X., Vanhoucke, V.: YouTube-BoundingBoxes: a large high-precision human-annotated data set for object detection in video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137473. IEEE (2017)","DOI":"10.1109\/CVPR.2017.789"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 3, pp. 32\u201336. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Russakovsky, O., Gupta, A.: What actions are needed for understanding human actions in videos? In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017, pp. 2156\u20132165 (2017)","DOI":"10.1109\/ICCV.2017.235"},{"key":"39_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"39_CR32","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"39_CR33","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild. In: CRCV-TR-12-01 (2012)"},{"key":"39_CR34","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"39_CR35","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMS. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"39_CR36","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"39_CR37","doi-asserted-by":"crossref","unstructured":"Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521\u20131528. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"39_CR38","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"39_CR39","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. arXiv preprint arXiv:1711.11248 (2017)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169\u20133176. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"39_CR41","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Learning to model the tail. In: Advances in Neural Information Processing Systems, pp. 7029\u20137039 (2017)"},{"key":"39_CR42","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv preprint arXiv:1712.04851 (2017)"},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"39_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Torralba, A.: Temporal relational reasoning in videos. arXiv preprint arXiv:1711.08496 (2017)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"39_CR45","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS (2014)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01264-9_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:57:11Z","timestamp":1665190631000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}