{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T04:30:55Z","timestamp":1746246655450,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585228"},{"type":"electronic","value":"9783030585235"}],"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\/978-3-030-58523-5_2","type":"book-chapter","created":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T20:13:16Z","timestamp":1607026396000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos"],"prefix":"10.1007","author":[{"given":"Alex","family":"Andonian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Camilo","family":"Fosco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew","family":"Monfort","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allen","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carl","family":"Vondrick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aude","family":"Oliva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,12,4]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Alfassy, A., et al.: Laso: label-set operations networks for multi-label few-shot learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00671"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bannour, H., Hudelot, C.: Hierarchical image annotation using semantic hierarchies. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management, pp. 2431\u20132434. ACM (2012)","DOI":"10.1145\/2396761.2398659"},{"key":"2_CR3","unstructured":"Battaglia, P., Pascanu, R., Lai, M., Jimenez Rezende, D., Kavukcuoglu, K.: Interaction networks for learning about objects, relations and physics. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 4502\u20134510. Curran Associates, Inc. (2016)"},{"key":"2_CR4","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl\\_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017). https:\/\/doi.org\/10.1162\/tacl_a_00051","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2_CR5","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., Shah, R.: Signature verification using a \u201cSiamese\u201d time delay neural network. In: Proceedings of the 6th International Conference on Neural Information Processing Systems, NIPS 1993, pp. 737\u2013744. Morgan Kaufmann Publishers Inc., San Francisco (1993)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the ICCV (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2_CR7","unstructured":"Chang, X., Yang, Y., Hauptmann, A.G., Xing, E.P., Yu, Y.L.: Semantic concept discovery for large-scale zero-shot event detection. In: Proceedings of the 24th International Conference on Artificial Intelligence, IJCAI 2015, pp. 2234\u20132240. AAAI Press (2015)"},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-319-10590-1_4","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Deng","year":"2014","unstructured":"Deng, J., et al.: Large-scale object classification using label relation graphs. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 48\u201364. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_4"},{"key":"2_CR9","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":"2_CR10","unstructured":"Deng, J., Satheesh, S., Berg, A.C., Li, F.: Fast and balanced: efficient label tree learning for large scale object recognition. In: Advances in Neural Information Processing Systems, pp. 567\u2013575 (2011)"},{"key":"2_CR11","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":"2_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.607"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J.C., Mensink, T., Snoek, C.G.M.: Objects2action: classifying and localizing actions without any video example. In: The IEEE International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.521"},{"key":"2_CR17","unstructured":"Jia, Y., Abbott, J.T., Austerweil, J.L., Griffiths, T., Darrell, T.: Visual concept learning: combining machine vision and Bayesian generalization on concept hierarchies. In: Advances in Neural Information Processing Systems, pp. 1842\u20131850 (2013)"},{"key":"2_CR18","unstructured":"Jia, Y., Abbott, J.T., Austerweil, J.L., Griffiths, T., Darrell, T.: Visual concept learning: combining machine vision and Bayesian generalization on concept hierarchies. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 26, pp. 1842\u20131850. Curran Associates, Inc. (2013)"},{"key":"2_CR19","unstructured":"Kay, W., et al.: The kinetics human action video dataset. CoRR abs\/1705.06950 (2017)"},{"key":"2_CR20","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop (2015)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., Kompatsiaris, I.: Visil: fine-grained spatio-temporal video similarity learning. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00645"},{"key":"2_CR22","unstructured":"Lee, H., Seol, J., Lee, S.: Style2vec: representation learning for fashion items from style sets. CoRR abs\/1708.04014 (2017)"},{"key":"2_CR23","unstructured":"Lim, J.J., Salakhutdinov, R.R., Torralba, A.: Transfer learning by borrowing examples for multiclass object detection. In: Advances in Neural Information Processing Systems, pp. 118\u2013126 (2011)"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"McGreggor, K., Goel, A.: Finding the odd one out: a fractal analogical approach. In: Proceedings of the 8th ACM Conference on Creativity and Cognition, C&C 2011, pp. 289\u2013298. ACM, New York (2011). https:\/\/doi.org\/10.1145\/2069618.2069666","DOI":"10.1145\/2069618.2069666"},{"key":"2_CR25","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 26, pp. 3111\u20133119. Curran Associates, Inc. (2013)"},{"issue":"4","key":"2_CR26","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/ijl\/3.4.235","volume":"3","author":"GA Miller","year":"1990","unstructured":"Miller, G.A., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.J.: Introduction to wordnet: an on-line lexical database. Int. J. Lexicography 3(4), 235\u2013244 (1990)","journal-title":"Int. J. Lexicography"},{"key":"2_CR27","unstructured":"Monfort, M., et al.: Multi-moments in time: learning and interpreting models for multi-action video understanding (2019)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Muhammad, U.R., Yang, Y., Hospedales, T.M., Xiang, T., Song, Y.Z.: Goal-driven sequential data abstraction. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00016"},{"key":"2_CR29","unstructured":"Nauata, N., Hu, H., Zhou, G.T., Deng, Z., Liao, Z., Mori, G.: Structured label inference for visual understanding. arXiv preprint arXiv:1802.06459 (2018)"},{"key":"2_CR30","unstructured":"Nauata, N., Smith, J., Mori, G.: Hierarchical label inference for video classification. arXiv preprint arXiv:1706.05028 (2017)"},{"key":"2_CR31","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems, pp. 4967\u20134976 (2017)"},{"key":"2_CR32","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 4967\u20134976. Curran Associates, Inc. (2017)"},{"key":"2_CR33","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":"2_CR34","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1126\/science.1192788","volume":"31","author":"JB Tenenbaum","year":"2011","unstructured":"Tenenbaum, J.B., Kemp, C., Griffiths, T.L., Goodman, N.D.: How to grow a mind: statistics, structure and abstraction. Science 31, 1279\u20131285 (2011)","journal-title":"Science"},{"key":"2_CR35","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, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Verma, N., Mahajan, D., Sellamanickam, S., Nair, V.: Learning hierarchical similarity metrics. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2280\u20132287. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247938"},{"key":"2_CR37","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":"2_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Hoai, M.: Pulling actions out of context: explicit separation for effective combination. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00736"},{"issue":"1","key":"2_CR39","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-014-0748-y","volume":"119","author":"J Xiao","year":"2016","unstructured":"Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: Sun database: exploring a large collection of scene categories. Int. J. Comput. Vis. 119(1), 3\u201322 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"Ye, G., Li, Y., Xu, H., Liu, D., Chang, S.F.: EventNet: a large scale structured concept library for complex event detection in video. In: Proceedings of the 23rd ACM International Conference on Multimedia, MM 2015, pp. 471\u2013480. ACM, New York (2015). https:\/\/doi.org\/10.1145\/2733373.2806221","DOI":"10.1145\/2733373.2806221"},{"key":"2_CR41","doi-asserted-by":"publisher","unstructured":"Aytar, Y., Shah, M., Luo, J.: Utilizing semantic word similarity measures for video retrieval. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138, June 2008. https:\/\/doi.org\/10.1109\/CVPR.2008.4587822","DOI":"10.1109\/CVPR.2008.4587822"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Instance-based video search via multi-task retrieval and re-ranking. In: The IEEE International Conference on Computer Vision (ICCV) Workshops, October 2019","DOI":"10.1109\/ICCVW.2019.00234"},{"key":"2_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"},{"key":"2_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/978-3-030-01216-8_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Zolfaghari","year":"2018","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 713\u2013730. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_43"}],"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\/978-3-030-58523-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:03:59Z","timestamp":1733184239000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58523-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585228","9783030585235"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58523-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"4 December 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)"}}]}}