{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:38Z","timestamp":1777657478976,"version":"3.51.4"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198205","type":"print"},{"value":"9783031198212","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\/978-3-031-19821-2_14","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"242-259","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Learn2Augment: Learning to\u00a0Composite Videos for\u00a0Data Augmentation in\u00a0Action Recognition"],"prefix":"10.1007","author":[{"given":"Shreyank N.","family":"Gowda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Rohrbach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Keller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Sevilla-Lara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N.E., McGuinness, K.: Pseudo-labeling and confirmation bias in deep semi-supervised learning. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"14_CR2","unstructured":"Berthelot, D., et al.: RemixMatch: semi-supervised learning with distribution matching and augmentation anchoring. In: International Conference on Learning Representations (2019)"},{"key":"14_CR3","first-page":"1","volume":"32","author":"D Berthelot","year":"2019","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. Adv. Neural. Inf. Process. Syst. 32, 1\u201311 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR4","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":"14_CR5","unstructured":"Choi, J., Gao, C., Messou, J.C., Huang, J.B.: Why can\u2019t I dance in the mall? learning to mitigate scene bias in action recognition. In: NeurIPS (2019)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00020"},{"key":"14_CR7","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: Randaugment: Practical automated data augmentation with a reduced search space. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 18613\u201318624. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/d85b63ef0ccb114d0a3bb7b7d808028f-Paper.pdf"},{"key":"14_CR8","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":"14_CR9","unstructured":"DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. In: ICLR Workshop (2017)"},{"key":"14_CR10","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Sevilla-Lara, L.: Smart frame selection for action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35(2), pp. 1451\u20131459, May 2021. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16235","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"14_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-92659-5_12","volume-title":"Pattern Recognition","author":"SN Gowda","year":"2021","unstructured":"Gowda, S.N., Sevilla-Lara, L., Kim, K., Keller, F., Rohrbach, M.: A new split for\u00a0evaluating true zero-shot action recognition. In: Bauckhage, C., Gall, J., Schwing, A. (eds.) DAGM GCPR 2021. LNCS, vol. 13024, pp. 191\u2013205. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-92659-5_12"},{"key":"14_CR13","first-page":"281","volume":"367","author":"Y Grandvalet","year":"2005","unstructured":"Grandvalet, Y., Bengio, Y., et al.: Semi-supervised learning by entropy minimization. CAP 367, 281\u2013296 (2005)","journal-title":"CAP"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"14_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"14_CR16","doi-asserted-by":"publisher","unstructured":"Huang, D.A., et al.: What makes a video a video: analyzing temporal information in video understanding models and datasets, pp. 7366\u20137375, June 2018. https:\/\/doi.org\/10.1109\/CVPR.2018.00769","DOI":"10.1109\/CVPR.2018.00769"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Iosifidis, A., Tefas, A., Pitas, I.: Semi-supervised classification of human actions based on neural networks. In: 2014 22nd International Conference on Pattern Recognition, pp. 1336\u20131341. IEEE (2014)","DOI":"10.1109\/ICPR.2014.239"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Jing, L., Parag, T., Wu, Z., Tian, Y., Wang, H.: VideoSSL: semi-supervised learning for video classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1110\u20131119, January 2021","DOI":"10.1109\/WACV48630.2021.00115"},{"key":"14_CR19","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":"14_CR20","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., Torresani, L.: SCSampler: sampling salient clips from video for efficient action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6232\u20136242 (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"14_CR21","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: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"14_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/978-3-030-58523-5_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C-W Kuo","year":"2020","unstructured":"Kuo, C.-W., Ma, C.-Y., Huang, J.-B., Kira, Z.: FeatMatch: feature-based augmentation for semi-supervised learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 479\u2013495. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_28"},{"key":"14_CR23","unstructured":"Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)"},{"key":"14_CR24","unstructured":"Lee, D.H., et al.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges In Representation Learning, ICML, vol. 3, p. 896 (2013)"},{"key":"14_CR25","doi-asserted-by":"publisher","first-page":"5858","DOI":"10.1109\/ACCESS.2017.2696121","volume":"5","author":"J Lemley","year":"2017","unstructured":"Lemley, J., Bazrafkan, S., Corcoran, P.M.: Smart augmentation learning an optimal data augmentation strategy. IEEE Access 5, 5858\u20135869 (2017)","journal-title":"IEEE Access"},{"key":"14_CR26","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context (2014). http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01252-6_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Liu","year":"2018","unstructured":"Liu, G., Reda, F.A., Shih, K.J., Wang, T.-C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 89\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_6"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Pagliardini, M., Gupta, P., Jaggi, M.: Unsupervised learning of sentence embeddings using compositional n-gram features. In: NAACL 2018 - Conference of the North American Chapter of the Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/N18-1049"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Perrett, T., Masullo, A., Burghardt, T., Mirmehdi, M., Damen, D.: Temporal-relational crosstransformers for few-shot action recognition. arXiv preprint arXiv:2101.06184 (2021)","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Semi-supervised action recognition with temporal contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10389\u201310399 (2021)","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"14_CR31","unstructured":"Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 (2017)"},{"key":"14_CR32","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":"14_CR33","doi-asserted-by":"crossref","unstructured":"Sun, D., et al.: Autoflow: learning a better training set for optical flow. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00996"},{"key":"14_CR34","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780 (2017)"},{"issue":"3","key":"14_CR35","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"14_CR36","unstructured":"Yoon, J., Arik, S., Pfister, T.: Data valuation using reinforcement learning. In: International Conference on Machine Learning, pp. 10842\u201310851. PMLR (2020)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"14_CR38","unstructured":"Yun, S., Oh, S.J., Heo, B., Han, D., Kim, J.: VideoMix: rethinking data augmentation for video classification. arXiv preprint arXiv:2012.03457 (2020)"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Zhai, X., Oliver, A., Kolesnikov, A., Beyer, L.: S4l: self-supervised semi-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1476\u20131485 (2019)","DOI":"10.1109\/ICCV.2019.00156"},{"key":"14_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-030-58558-7_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Zhang, L., Qi, X., Li, H., Torr, P.H.S., Koniusz, P.: Few-shot action recognition with permutation-invariant attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 525\u2013542. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_31"},{"key":"14_CR41","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"},{"key":"14_CR42","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Jia, G., Chen, L., Zhang, M., Yong, J.: Self-paced video data augmentation by generative adversarial networks with insufficient samples. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1652\u20131660. MM 2020, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3394171.3414003","DOI":"10.1145\/3394171.3414003"},{"key":"14_CR43","unstructured":"Zou, Y., Choi, J., Wang, Q., Huang, J.: Learning representational invariances for data-efficient action recognition. CoRR abs\/2103.16565 (2021). https:\/\/arxiv.org\/abs\/2103.16565"}],"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\/978-3-031-19821-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:50:40Z","timestamp":1666443040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19821-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198205","9783031198212"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19821-2_14","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":"23 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)"}}]}}