{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:44:34Z","timestamp":1742913874308,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263156"},{"type":"electronic","value":"9783031263163"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_21","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"347-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Using Privileged Information for\u00a0Zero-Shot Action Recognition"],"prefix":"10.1007","author":[{"given":"Zhiyi","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihui","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"21_CR2","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":"21_CR3","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4768\u20134777 (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Long, M., Wang, J., Yu, P.S.: Spatiotemporal pyramid network for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 529\u20131538 (2017) 1","DOI":"10.1109\/CVPR.2017.226"},{"key":"21_CR5","unstructured":"Zhu, Y., et al.: A comprehensive study of deep video action recognition. arXiv preprint arXiv:2012.06567 (2020)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., Savarese, S.: Recognizing human actions by attributes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3337\u20133344 (2011)","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"21_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-319-10605-2_38","volume-title":"Computer Vision","author":"Y Fu","year":"2014","unstructured":"Fu, Y., Hospedales, T.M., Xiang, T., Fu, Z., Gong, S.: Transductive multi-view embedding for zero-shot recognition and annotation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 584\u2013599. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_38"},{"key":"21_CR8","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1007\/s11263-017-1027-5","volume":"124","author":"Q Wang","year":"2017","unstructured":"Wang, Q., Chen, K.: Zero-shot visual recognition via bidirectional latent embedding. Int. J. Comput. Vis. 124, 356\u2013383 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"21_CR9","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"21_CR10","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 Conference on Computer Vision and Pattern Recognition, pp. 4613\u20134623 (2020)","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"21_CR11","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":"21_CR12","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":"21_CR13","doi-asserted-by":"publisher","first-page":"102380","DOI":"10.1016\/j.adhoc.2020.102380","volume":"113","author":"Y Su","year":"2021","unstructured":"Su, Y., Xing, M., An, S., Peng, W., Feng, Z.: Vdarn: video disentangling attentive relation network for few-shot and zero-shot action recognition. Ad Hoc Netw. 113, 102380 (2021)","journal-title":"Ad Hoc Netw."},{"key":"21_CR14","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., Vashist, A.: A new learning paradigm: learning using privileged information. Neural Netw. 22, 544\u2013557 (2009)","journal-title":"Neural Netw."},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Niebles, J.C., Chen, C.W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Proceedings of the European Conference on Computer Vision, Springer (2010) 392\u2013405","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"21_CR17","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 IEEE International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"21_CR18","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":"21_CR19","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, pp. 63\u201367. IEEE (2015)","DOI":"10.1109\/ICIP.2015.7350760"},{"key":"21_CR20","unstructured":"Bishay, M., Zoumpourlis, G., Patras, I.: Tarn: Temporal attentive relation network for few-shot and zero-shot action recognition. arXiv preprint arXiv:1907.09021 (2019)"},{"key":"21_CR21","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1016\/j.patcog.2017.06.035","volume":"72","author":"L Zhou","year":"2017","unstructured":"Zhou, L., Li, W., Ogunbona, P., Zhang, Z.: Semantic action recognition by learning a pose lexicon. Pattern Recogn. 72, 548\u2013562 (2017)","journal-title":"Pattern Recogn."},{"key":"21_CR22","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/TCSVT.2019.2890829","volume":"30","author":"L Zhou","year":"2019","unstructured":"Zhou, L., Li, W., Ogunbona, P., Zhang, Z.: Jointly learning visual poses and pose lexicon for semantic action recognition. IEEE Trans. Circuits Syst. Video Technol. 30, 457\u2013467 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Chen, S., Huang, D.: Elaborative rehearsal for zero-shot action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 13638\u201313647 (2021)","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 951\u2013958 (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"21_CR26","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang, H., Oneata, D., Verbeek, J., Schmid, C.: A robust and efficient video representation for action recognition. Int. J. Comput. Vis. 119, 219\u2013238 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"21_CR27","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":"21_CR28","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":"21_CR29","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. International Journal of Computer Vision 123, 309\u2013333 (2017)","journal-title":"International Journal of Computer Vision"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Niu, L., Li, W., Xu, D.: Visual recognition by learning from web data: a weakly supervised domain generalization approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2774\u20132783 (2015)","DOI":"10.1109\/CVPR.2015.7298894"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Motiian, S., Piccirilli, M., Adjeroh, D.A., Doretto, G.: Information bottleneck learning using privileged information for visual recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1496\u20131505 (2016)","DOI":"10.1109\/CVPR.2016.166"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: Mars: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"21_CR33","doi-asserted-by":"publisher","first-page":"2581","DOI":"10.1109\/TPAMI.2019.2929038","volume":"42","author":"NC Garcia","year":"2020","unstructured":"Garcia, N.C., Morerio, P., Murino, V.: Learning with privileged information via adversarial discriminative modality distillation. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2581\u20132593 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Mishra, A., Verma, V.K., Reddy, M.S.K., Arulkumar, S., Rai, P., Mittal, A.: A generative approach to zero-shot and few-shot action recognition. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 372\u2013380 (2018)","DOI":"10.1109\/WACV.2018.00047"},{"key":"21_CR35","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.neucom.2020.01.078","volume":"390","author":"A Mishra","year":"2020","unstructured":"Mishra, A., Pandey, A., Murthy, H.A.: Zero-shot learning for action recognition using synthesized features. Neurocomputing 390, 117\u2013130 (2020)","journal-title":"Neurocomputing"},{"key":"21_CR36","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":"21_CR37","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"21_CR38","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":"21_CR39","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"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Mandal, D., et al.: Out-of-distribution detection for generalized zero-shot action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9985\u20139993 (2019)","DOI":"10.1109\/CVPR.2019.01022"},{"key":"21_CR41","first-page":"8303","volume":"33","author":"J Gao","year":"2019","unstructured":"Gao, J., Zhang, T., Xu, C.: I know the relationships: zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. Proc. AAAI Conf. Artif. Intell. 33, 8303\u20138311 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"21_CR42","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:27:42Z","timestamp":1677659262000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","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":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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 Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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":"For the ACCV 2022 workshops 25 papers have been accepted from 40 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)"}}]}}