{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:51:39Z","timestamp":1777654299425,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197710","type":"print"},{"value":"9783031197727","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19772-7_7","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"104-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Rethinking Zero-shot Action Recognition: Learning from\u00a0Latent Atomic Actions"],"prefix":"10.1007","author":[{"given":"Yijun","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander G.","family":"Hauptmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"issue":"7","key":"7_CR1","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","volume":"38","author":"Z Akata","year":"2015","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(7), 1425\u20131438 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2927\u20132936 (2015)","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Brattoli, B., Tighe, J., Zhdanov, F., Perona, P., Chalupka, K.: Rethinking zero-shot video classification: end-to-end training for realistic applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4613\u20134623 (2020)","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"7_CR5","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"7_CR6","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018)"},{"key":"7_CR7","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, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., Huang, D.: Elaborative rehearsal for zero-shot action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13638\u201313647 (2021)","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"7_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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"7_CR11","unstructured":"Diba, A., et al.: Temporal 3d convnets using temporal transition layer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1117\u20131121 (2018)"},{"key":"7_CR12","unstructured":"Diba, A., et al.: Temporal 3d convnets: new architecture and transfer learning for video classification. arXiv preprint arXiv:1711.08200 (2017)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: Rubiksnet: learnable 3d-shift for efficient video action recognition. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58529-7_30"},{"issue":"4","key":"7_CR14","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi, L., Chiriatti, M.: Gpt-3: Its nature, scope, limits, and consequences. Minds Mach. 30(4), 681\u2013694 (2020)","journal-title":"Minds Mach."},{"key":"7_CR15","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. Adv. Neural Inf. Process. Syst. 26 (2013)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Gan, C., Lin, M., Yang, Y., De Melo, G., Hauptmann, A.G.: Concepts not alone: exploring pairwise relationships for zero-shot video activity recognition. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: I know the relationships: zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8303\u20138311 (2019)","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12046\u201312055 (2019)","DOI":"10.1109\/CVPR.2019.01232"},{"key":"7_CR19","unstructured":"Ghosh, P., Saini, N., Davis, L.S., Shrivastava, A.: All about knowledge graphs for actions. arXiv preprint arXiv:2008.12432 (2020)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Guo, M., Chou, E., Huang, D.A., Song, S., Yeung, S., Fei-Fei, L.: Neural graph matching networks for fewshot 3d action recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 653\u2013669 (2018)","DOI":"10.1007\/978-3-030-01246-5_40"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3d CNNs retrace the history of 2d CNNs and imagenet? In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Jain, M., Van Gemert, J.C., Mensink, T., Snoek, C.G.: Objects2action: classifying and localizing actions without any video example. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4588\u20134596 (2015)","DOI":"10.1109\/ICCV.2015.521"},{"key":"7_CR23","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"7_CR24","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","volume-title":"Computer Vision","author":"A Kolesnikov","year":"2020","unstructured":"Kolesnikov, A., et al.: Big transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491\u2013507. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29"},{"key":"7_CR26","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: Proceedings of the International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 951\u2013958. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206594"},{"key":"7_CR28","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, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., Savarese, S.: Recognizing human actions by attributes. In: CVPR 2011, pp. 3337\u20133344. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Mandal, D., et al.: Out-of-distribution detection for generalized zero-shot action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9985\u20139993 (2019)","DOI":"10.1109\/CVPR.2019.01022"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Qian, Y., Kang, G., Yu, L., Liu, W., Hauptmann, A.G.: Trm: temporal relocation module for video recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 151\u2013160 (2022)","DOI":"10.1109\/WACVW54805.2022.00021"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Qin, J., et al.: Zero-shot action recognition with error-correcting output codes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2833\u20132842 (2017)","DOI":"10.1109\/CVPR.2017.117"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Shao, H., Qian, S., Liu, Y.: Temporal interlacing network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11966\u201311973 (2020)","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"7_CR35","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":"7_CR36","unstructured":"Smaira, L., Carreira, J., Noland, E., Clancy, E., Wu, A., Zisserman, A.: A short note on the kinetics-700-2020 human action dataset. arXiv preprint arXiv:2010.10864 (2020)"},{"key":"7_CR37","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":"7_CR38","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":"7_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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"7_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"7_CR41","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","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":"7_CR42","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-71249-9_6","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Q Wang","year":"2017","unstructured":"Wang, Q., Chen, K.: Alternative semantic representations for zero-shot human action recognition. In: Ceci, M., Hollm\u00e9n, J., Todorovski, L., Vens, C., D\u017eeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10534, pp. 87\u2013102. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71249-9_6"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Xu, X., Hospedales, T., Gong, S.: Semantic embedding space for zero-shot action recognition. In: 2015 IEEE International Conference on Image Processing (ICIP), pp. 63\u201367. IEEE (2015)","DOI":"10.1109\/ICIP.2015.7350760"},{"issue":"3","key":"7_CR44","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11263-016-0983-5","volume":"123","author":"X Xu","year":"2017","unstructured":"Xu, X., Hospedales, T., Gong, S.: Transductive zero-shot action recognition by word-vector embedding. Int. J. Comput. Vision 123(3), 309\u2013333 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-319-46475-6_22","volume-title":"Computer Vision","author":"X Xu","year":"2016","unstructured":"Xu, X., Hospedales, T.M., Gong, S.: Multi-task zero-shot action recognition with prioritised data augmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 343\u2013359. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_22"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Zellers, R., Choi, Y.: Zero-shot activity recognition with verb attribute induction. arXiv preprint arXiv:1707.09468 (2017)","DOI":"10.18653\/v1\/D17-1099"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 917\u2013925 (2021)","DOI":"10.1145\/3474085.3475272"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2021\u20132030 (2017)","DOI":"10.1109\/CVPR.2017.321"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 803\u2013818 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Long, Y., Guan, Y., Newsam, S., Shao, L.: Towards universal representation for unseen action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9436\u20139445 (2018)","DOI":"10.1109\/CVPR.2018.00983"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19772-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:48:11Z","timestamp":1710262091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}