{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:12:59Z","timestamp":1743001979882,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250743"},{"type":"electronic","value":"9783031250750"}],"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\/978-3-031-25075-0_23","type":"book-chapter","created":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T09:16:53Z","timestamp":1676798213000},"page":"317-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Identifying Auxiliary or\u00a0Adversarial Tasks Using Necessary Condition Analysis for\u00a0Adversarial Multi-task Video Understanding"],"prefix":"10.1007","author":[{"given":"Stephen","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Kwong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"De-An","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Adeli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,19]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Adeli, E., et al.: Representation learning with statistical independence to mitigate bias. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2513\u20132523 (2021)","DOI":"10.1109\/WACV48630.2021.00256"},{"key":"23_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/978-3-030-46147-8_19","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"K Akuzawa","year":"2020","unstructured":"Akuzawa, K., Iwasawa, Y., Matsuo, Y.: Adversarial invariant feature learning with accuracy constraint for domain generalization. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) ECML PKDD 2019. LNCS (LNAI), vol. 11907, pp. 315\u2013331. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-46147-8_19"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Bagautdinov, T., Alahi, A., Fleuret, F., Fua, P., Savarese, S.: Social scene understanding: end-to-end multi-person action localization and collective activity recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.365"},{"key":"23_CR4","unstructured":"Carreira, J., Noland, E., Hillier, C., Zisserman, A.: A short note on the kinetics-700 human action dataset. arXiv preprint arXiv:1907.06987 (2019)"},{"key":"23_CR5","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":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., et al.: Deep analysis of CNN-based Spatio-temporal representations for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6165\u20136175 (2021)","DOI":"10.1109\/CVPR46437.2021.00610"},{"key":"23_CR7","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: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: The epic-kitchens dataset: Collection, challenges and baselines. TPAMI 43, 4125\u20134141 (2020)","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"23_CR9","unstructured":"Diba, A., et al.: Holistic large scale video understanding. arXiv preprint arXiv:1904.11451 38, 39 (2019)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Dul, J.: Necessary condition analysis (NCA) logic and methodology of \u201cnecessary but not sufficient\u201d causality. Organ. Res. Methods 19(1), 10\u201352 (2016)","DOI":"10.1177\/1094428115584005"},{"key":"23_CR11","doi-asserted-by":"publisher","unstructured":"Elazar, Y., Goldberg, Y.: Adversarial removal of demographic attributes from text data. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 11\u201321. Association for Computational Linguistics, Brussels, October\u2013November 2018. https:\/\/doi.org\/10.18653\/v1\/D18-1002. https:\/\/www.aclweb.org\/anthology\/D18-1002","DOI":"10.18653\/v1\/D18-1002"},{"key":"23_CR12","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1) (2016). 2096-2030"},{"key":"23_CR13","unstructured":"Girdhar, R., Ramanan, D.: CATER: a diagnostic dataset for compositional actions and temporal reasoning. In: ICLR (2020)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Hong, Y.W., Kim, H., Byun, H.: Multi-task joint learning for videos in the wild. In: Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild, CoVieW 2018, pp. 27\u201330. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3265987.3265988","DOI":"10.1145\/3265987.3265988"},{"key":"23_CR18","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: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7366\u20137375 (2018)","DOI":"10.1109\/CVPR.2018.00769"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., Niebles, J.C.: Action genome: actions as compositions of spatio-temporal scene graphs. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"23_CR20","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Kim, D., et al.: MILA: multi-task learning from videos via efficient inter-frame local attention (2020)","DOI":"10.1109\/ICCVW54120.2021.00251"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Vasconcelos, N.: Repair: Removing representation bias by dataset resampling (2019)","DOI":"10.1109\/CVPR.2019.00980"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Materzynska, J., Berger, G., Bax, I., Memisevic, R.: The jester dataset: a large-scale video dataset of human gestures. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 2874\u20132882 (2019). https:\/\/doi.org\/10.1109\/ICCVW.2019.00349","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Fang, F., Yamagishi, J., Echizen, I.: Multi-task learning for detecting and segmenting manipulated facial images and videos (2019)","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"23_CR25","doi-asserted-by":"publisher","first-page":"40757","DOI":"10.1109\/ACCESS.2019.2906654","volume":"7","author":"X Ouyang","year":"2019","unstructured":"Ouyang, X.: A 3D-CNN and LSTM based multi-task learning architecture for action recognition. IEEE Access 7, 40757\u201340770 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2906654","journal-title":"IEEE Access"},{"key":"23_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-030-01264-9_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Ray","year":"2018","unstructured":"Ray, J., et al.: Scenes-objects-actions: a multi-task, multi-label video dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 660\u2013676. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_39"},{"issue":"2","key":"23_CR27","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2019","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336\u2013359 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01228-7","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Zha, S., Yan, Z., Goswami, V., Feiszli, M., Torresani, L.: Only time can tell: discovering temporal data for temporal modeling. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 535\u2013544 (2021)","DOI":"10.1109\/WACV48630.2021.00058"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Shen, Z., Cui, P., Kuang, K., Li, B., Chen, P.: Causally regularized learning with agnostic data selection bias. In: Proceedings of the 26th ACM International Conference on Multimedia, October 2018. https:\/\/doi.org\/10.1145\/3240508.3240577","DOI":"10.1145\/3240508.3240577"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Russakovsky, O., Gupta, A.: What actions are needed for understanding human actions in videos? In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.235"},{"key":"23_CR31","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos (2014)"},{"key":"23_CR32","unstructured":"Standley, T., Zamir, A., Chen, D., Guibas, L., Malik, J., Savarese, S.: Which tasks should be learned together in multi-task learning? In: International Conference on Machine Learning, pp. 9120\u20139132. PMLR (2020)"},{"issue":"6","key":"23_CR33","doi-asserted-by":"publisher","first-page":"2769","DOI":"10.1214\/009053607000000505","volume":"35","author":"GJ Sz\u00e9kely","year":"2007","unstructured":"Sz\u00e9kely, G.J., Rizzo, M.L., Bakirov, N.K., et al.: Measuring and testing dependence by correlation of distances. Ann. Stat. 35(6), 2769\u20132794 (2007)","journal-title":"Ann. Stat."},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"23_CR35","unstructured":"Weinzaepfel, P., Rogez, G.: Mimetics: towards understanding human actions out of context. arXiv preprint arXiv:1912.07249 (2019)"},{"issue":"1","key":"23_CR36","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1146\/annurev.so.18.080192.001551","volume":"18","author":"C Winship","year":"1992","unstructured":"Winship, C., Mare, R.D.: Models for sample selection bias. Ann. Rev. Sociol. 18(1), 327\u2013350 (1992). https:\/\/doi.org\/10.1146\/annurev.so.18.080192.001551","journal-title":"Ann. Rev. Sociol."},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"23_CR38","unstructured":"Xie, Q., Dai, Z., Du, Y., Hovy, E., Neubig, G.: Controllable invariance through adversarial feature learning (2018)"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning (2018)","DOI":"10.1145\/3278721.3278779"},{"key":"23_CR40","doi-asserted-by":"publisher","unstructured":"Zhu, Y., Newsam, S.: Efficient action detection in untrimmed videos via multi-task learning. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 197\u2013206 (2017). https:\/\/doi.org\/10.1109\/WACV.2017.29","DOI":"10.1109\/WACV.2017.29"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25075-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T09:29:46Z","timestamp":1676798986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25075-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250743","9783031250750"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25075-0_23","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":"19 February 2023","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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}