{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T01:23:19Z","timestamp":1781054599898,"version":"3.54.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585167","type":"print"},{"value":"9783030585174","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58517-4_10","type":"book-chapter","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T19:03:11Z","timestamp":1602270191000},"page":"154-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":99,"title":["Temporal Aggregate Representations for Long-Range Video Understanding"],"prefix":"10.1007","author":[{"given":"Fadime","family":"Sener","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dipika","family":"Singhania","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,10]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Abu Farha, Y., Richard, A., Gall, J.: When will you do what? - Anticipating temporal occurrences of activities. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5343\u20135352 (2018)","DOI":"10.1109\/CVPR.2018.00560"},{"key":"10_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised learning of universal sentence representations from natural language inference data. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 670\u2013680 (2017)","DOI":"10.18653\/v1\/D17-1070"},{"key":"10_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"10_CR6","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6508\u20136516 (2018)"},{"key":"10_CR7","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 (CVPR), pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Furnari, A., Farinella, G.M.: What would you expect? Anticipating egocentric actions with rolling-unrolling LSTMs and modality attention. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00635"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 971\u2013980 (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"10_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-319-46493-0_9","volume-title":"Computer Vision \u2013 ECCV 2016","author":"D-A Huang","year":"2016","unstructured":"Huang, D.-A., Fei-Fei, L., Niebles, J.C.: Connectionist temporal modeling for weakly supervised action labeling. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 137\u2013153. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_9"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Huang, D.A., et al.: What makes a video a video: analyzing temporal information in video understanding models and datasets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7366\u20137375 (2018)","DOI":"10.1109\/CVPR.2018.00769"},{"key":"10_CR14","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Ke, Q., Fritz, M., Schiele, B.: Time-conditioned action anticipation in one shot. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.01016"},{"key":"10_CR16","unstructured":"Kline, N., Snodgrass, R.T.: Computing temporal aggregates. In: Proceedings of the Eleventh International Conference on Data Engineering, pp. 222\u2013231. IEEE (1995)"},{"issue":"1","key":"10_CR17","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TPAMI.2015.2430335","volume":"38","author":"HS Koppula","year":"2015","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 38(1), 14\u201329 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 780\u2013787 (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"10_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-319-10578-9_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lan","year":"2014","unstructured":"Lan, T., Chen, T.-C., Savarese, S.: A hierarchical representation for future action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 689\u2013704. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_45"},{"key":"10_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-11018-5_18","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"J Lee","year":"2019","unstructured":"Lee, J., Natsev, A.P., Reade, W., Sukthankar, R., Toderici, G.: The 2nd YouTube-8M large-scale video understanding challenge. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 193\u2013205. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_18"},{"key":"10_CR21","unstructured":"Li, F., et al.: Temporal modeling approaches for large-scale Youtube-8M video understanding. arXiv preprint arXiv:1707.04555 (2017)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"10_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-030-11018-5_19","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"R Lin","year":"2019","unstructured":"Lin, R., Xiao, J., Fan, J.: NeXtVLAD: an efficient neural network to aggregate frame-level features for large-scale video classification. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 206\u2013218. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_19"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Mahmud, T., Hasan, M., Roy-Chowdhury, A.K.: Joint prediction of activity labels and starting times in untrimmed videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5773\u20135782 (2017)","DOI":"10.1109\/ICCV.2017.616"},{"key":"10_CR25","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification. arXiv preprint arXiv:1706.06905 (2017)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Miech, A., Laptev, I., Sivic, J., Wang, H., Torresani, L., Tran, D.: Leveraging the present to anticipate the future in videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, p. 0 (2019)","DOI":"10.1109\/CVPRW.2019.00351"},{"key":"10_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1007\/978-3-030-11018-5_23","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"P Ostyakov","year":"2019","unstructured":"Ostyakov, P., et al.: Label denoising with large ensembles of heterogeneous neural networks. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 250\u2013261. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_23"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Richard, A., Gall, J.: Temporal action detection using a statistical language model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3131\u20133140 (2016)","DOI":"10.1109\/CVPR.2016.341"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Weakly supervised action learning with RNN based fine-to-coarse modeling. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 754\u2013763 (2017)","DOI":"10.1109\/CVPR.2017.140"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Sener, F., Yao, A.: Unsupervised learning and segmentation of complex activities from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00873"},{"key":"10_CR31","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":"10_CR32","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CoRR abs\/1212.0402 (2012). http:\/\/arxiv.org\/abs\/1212.0402"},{"issue":"1","key":"10_CR33","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Stein, S., McKenna, S.J.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 729\u2013738. ACM (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"10_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-030-11018-5_20","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"Y Tang","year":"2019","unstructured":"Tang, Y., Zhang, X., Wang, J., Chen, S., Ma, L., Jiang, Y.-G.: Non-local NetVLAD encoding for video classification. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 219\u2013228. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_20"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"10_CR37","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. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 98\u2013106 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"10_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Kr\u00e4henb\u00fchl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"10_CR43","unstructured":"Xiao, F., Lee, Y.J., Grauman, K., Malik, J., Feichtenhofer, C.: Audiovisual SlowFast networks for video recognition. arXiv preprint arXiv:2001.08740 (2020)"},{"key":"10_CR44","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 (CVPR), pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58517-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:09:19Z","timestamp":1728432559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58517-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585167","9783030585174"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58517-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"10 October 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}