{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T07:29:40Z","timestamp":1780558180576,"version":"3.54.1"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","type":"electronic"}],"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\/978-3-030-01252-6_13","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T09:48:05Z","timestamp":1538732885000},"page":"212-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["What Do I Annotate Next? An Empirical Study of Active Learning for Action Localization"],"prefix":"10.1007","author":[{"given":"Fabian Caba","family":"Heilbron","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon-Young","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"13_CR1","unstructured":"Bachman, P., Sordoni, A., Trischler, A.: Learning Algorithms for Active Learning. arXiv preprint arXiv:1708.00088 (2017)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Bandla, S., Grauman, K.: Active learning of an action detector from untrimmed videos. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.230"},{"key":"13_CR3","unstructured":"Brinker, K.: Incorporating diversity in active learning with support vector machines. In: International Conference on Machine Learning (ICML) (2003)"},{"issue":"5","key":"13_CR4","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/TPAMI.2009.57","volume":"32","author":"L Bruzzone","year":"2010","unstructured":"Bruzzone, L., Marconcini, M.: Domain adaptation problems: a DASVM classification technique and a circular validation strategy. PAMI 32(5), 770\u2013787 (2010)","journal-title":"PAMI"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Ghanem, B., Fei-Fei, L., Niebles, J.C.: End-to-end, single-stream temporal action detection in untrimmed videos. In: BMVC (2017)","DOI":"10.5244\/C.31.93"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: single-stream temporal action proposals. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Barrios, W., Escorcia, V., Ghanem, B.: SCC: semantic context cascade for efficient action detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.338"},{"key":"13_CR8","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: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Niebles, J.C.: Collecting and annotating human activities in web videos. In: Proceedings of International Conference on Multimedia Retrieval (ICMR) (2014)","DOI":"10.1145\/2578726.2578775"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Niebles, J.C., Ghanem, B.: Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.211"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Thabet, A., Niebles, J.C., Ghanem, B.: Camera motion and surrounding scene appearance as context for action recognition. In: ACCV (2014)","DOI":"10.1007\/978-3-319-16817-3_38"},{"key":"13_CR12","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":"13_CR13","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Chen, X., Shrivastava, A., Gupta, A.: NEIL: extracting visual knowledge from web data. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.178"},{"key":"13_CR15","unstructured":"Cisco: The Zettabyte Era: Trends and Analysis (2017). https:\/\/www.cisco.com\/c\/en\/us\/solutions\/collateral\/service-provider\/visual-networking-index-vni\/vni-hyperconnectivity-wp.html"},{"key":"13_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-540-88682-2_8","volume-title":"Computer Vision \u2013 ECCV 2008","author":"B Collins","year":"2008","unstructured":"Collins, B., Deng, J., Li, K., Fei-Fei, L.: Towards scalable dataset construction: an active learning approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 86\u201398. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_8"},{"issue":"3","key":"13_CR17","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"key":"13_CR18","unstructured":"Cronin, L., et al.: Human vs robots in the discovery and crystallization of gigantic polyoxometalates. Angewandte Chemie (2017)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"13_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Escorcia","year":"2016","unstructured":"Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"},{"key":"13_CR21","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9(Aug), 1871\u20131874 (2008)"},{"key":"13_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1007\/978-3-319-10593-2_37","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Freytag","year":"2014","unstructured":"Freytag, A., Rodner, E., Denzler, J.: Selecting Influential examples: active learning with expected model output changes. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 562\u2013577. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_37"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Actom sequence models for efficient action detection. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995646"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Sun, C., Chen, K., Nevatia, R.: Turn tap: temporal unit regression network for temporal action proposals. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Gavves, S., Mensink, T., Tommasi, T., Snoek, C., Tuytelaars, T.: Active transfer learning with zero-shot priors: reusing past datasets for future tasks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.313"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Giancola, S., Amine, M., Dghaily, T., Ghanem, B.: SoccerNet: a scalable dataset for action spotting in soccer videos. In: CVPR Workshops (2018)","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"13_CR27","unstructured":"Gilad-Bachrach, R., Navot, A., Tishby, N.: Query by committee made real. In: NIPS (2006)"},{"key":"13_CR28","unstructured":"Gkioxari, G., Hariharan, B., Girshick, R., Malik, J.: R-CNNs for pose estimation and action detection (2014)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"13_CR30","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2014)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Hakkani-T\u00fcr, D., Riccardi, G., Gorin, A.: Active learning for automatic speech recognition. In: 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2002)","DOI":"10.1109\/ICASSP.2002.1004771"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Finding tiny faces. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.166"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J., Jegou, H., Bouthemy, P., Snoek, C.G.: Action localization with tubelets from motion. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.100"},{"key":"13_CR35","unstructured":"Jiang, Y.G., et al.: THUMOS Challenge: Action Recognition with a Large Number of Classes (2014). http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206627"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Active learning with Gaussian processes for object categorization. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4408844"},{"key":"13_CR38","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":"13_CR39","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"13_CR40","unstructured":"Konyushkova, K., Sznitman, R., Fua, P.: Learning active learning from data. In: Advances in Neural Information Processing Systems, pp. 4226\u20134236 (2017)"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: ICML (1994)","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Lewis, D.D., Gale, W.A.: A sequential algorithm for training text classifiers. In: Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (1994)","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"13_CR45","unstructured":"Lin, X., Parikh, D.: Active learning for visual question answering: an empirical study. arXiv preprint arXiv:1711.01732 (2017)"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Liu, B., Ferrari, V.: Active learning for human pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.468"},{"key":"13_CR47","doi-asserted-by":"crossref","unstructured":"Maji, S., Bourdev, L., Malik, J.: Action recognition from a distributed representation of pose and appearance. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"13_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-642-15552-9_29","volume-title":"Computer Vision \u2013 ECCV 2010","author":"JC Niebles","year":"2010","unstructured":"Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 392\u2013405. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15552-9_29"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Efficient action localization with approximately normalized fisher vectors. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.326"},{"issue":"3","key":"13_CR51","first-page":"61","volume":"10","author":"J Platt","year":"1999","unstructured":"Platt, J., et al.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 10(3), 61\u201374 (1999)","journal-title":"Adv. Large Margin Classifiers"},{"issue":"6","key":"13_CR52","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R., et al.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"key":"13_CR53","unstructured":"Qi, G.J., Hua, X.S., Rui, Y., Tang, J., Zhang, H.J.: Two-dimensional active learning for image classification. In: CVPR (2008)"},{"issue":"3","key":"13_CR54","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"55\u201366","key":"13_CR55","first-page":"11","volume":"52","author":"B Settles","year":"2010","unstructured":"Settles, B.: Active learning literature survey. Univ. Wis. Madison 52(55\u201366), 11 (2010)","journal-title":"Univ. Wis. Madison"},{"key":"13_CR56","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNS. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"13_CR57","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. In: AAAI Conference on Human Computation and Crowdsourcing (HCOMP) (2016)","DOI":"10.1609\/hcomp.v4i1.13290"},{"key":"13_CR58","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., et al.: 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":"13_CR59","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"13_CR60","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"13_CR61","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"13_CR62","unstructured":"Thompson, C.A., Califf, M.E., Mooney, R.J.: Active learning for natural language parsing and information extraction"},{"key":"13_CR63","doi-asserted-by":"crossref","unstructured":"Tong, S., Chang, E.: Support vector machine active learning for image retrieval. In: Proceedings of the ninth ACM International Conference on Multimedia, pp. 107\u2013118. ACM (2001)","DOI":"10.1145\/500141.500159"},{"issue":"1\u20132","key":"13_CR64","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s11263-014-0721-9","volume":"108","author":"S Vijayanarasimhan","year":"2014","unstructured":"Vijayanarasimhan, S., Grauman, K.: Large-scale live active learning: training object detectors with crawled data and crowds. Int. J. Comput. Vis. 108(1\u20132), 97\u2013114 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR65","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s11263-012-0564-1","volume":"101","author":"C Vondrick","year":"2012","unstructured":"Vondrick, C., Patterson, D., Ramanan, D.: Efficiently scaling up crowdsourced video annotation. Int. J. Comput. Vis. 101, 184\u2013204 (2012)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR66","unstructured":"Vondrick, C., Ramanan, D.: Video annotation and tracking with active learning. In: NIPS (2011)"},{"key":"13_CR67","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"13_CR68","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: UntrimmedNets for weakly supervised action recognition and detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"13_CR69","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"13_CR70","unstructured":"Woodward, M., Finn, C.: Active one-shot learning. In: NIPS (2016)"},{"key":"13_CR71","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3d network for temporal activity detection (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"13_CR72","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Automatically labeling video data using multi-class active learning. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238391"},{"key":"13_CR73","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"13_CR74","doi-asserted-by":"crossref","unstructured":"Yeung, S., Ramanathan, V., Russakovsky, O., Shen, L., Mori, G., Fei-Fei, L.: Learning to learn from noisy web videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.788"},{"key":"13_CR75","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.293"},{"issue":"4","key":"13_CR76","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/1177352.1177355","volume":"38","author":"A Yilmaz","year":"2006","unstructured":"Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38(4), 13 (2006)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"13_CR77","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Lin, D., Tang, X.: Temporal action detection with structured segment networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.317"}],"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\/978-3-030-01252-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:47:49Z","timestamp":1773762469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}