{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:51:39Z","timestamp":1778082699848,"version":"3.51.4"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585198","type":"print"},{"value":"9783030585204","type":"electronic"}],"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\/978-3-030-58520-4_33","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"557-573","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Self-supervised Multi-task Procedure Learning from Instructional Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5517-548X","authenticated-orcid":false,"given":"Ehsan","family":"Elhamifar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6349-2597","authenticated-orcid":false,"given":"Dat","family":"Huynh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Bojanowski, P., Agrawal, N., Sivic, J., Laptev, I., Lacoste-Julien, S.: Unsupervised learning from narrated instruction videos. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.495"},{"key":"33_CR2","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep?. In: Neural Information Processing Systems (2013)"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., et al.: Weakly supervised action labeling in videos under ordering constraints. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_41"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"33_CR5","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)"},{"key":"33_CR6","unstructured":"Du, X., et al.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: Annual Meeting of the North American Association for Computational Linguistics (2019)"},{"key":"33_CR7","unstructured":"Elhamifar, E.: Sequential facility location: approximate submodularity and greedy algorithm. In: International Conference on Machine Learning (2019)"},{"key":"33_CR8","unstructured":"Elhamifar, E., De-Paolis-Kaluza, M.C.: Subset selection and summarization in sequential data. In: Neural Information Processing Systems (2017)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Elhamifar, E., Naing, Z.: Unsupervised procedure learning via joint dynamic summarization. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00644"},{"key":"33_CR10","unstructured":"Goel, K., Brunskill, E.: Learning procedural abstractions and evaluating discrete latent temporal structure. In: International Conference on Learning Representation (2019)"},{"key":"33_CR11","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. ArXiv (2015)"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Huang, D., Buch, S., Dery, L., Garg, A., Fei-Fei, L., Niebles, J.C.: Finding it?: Weakly-supervised reference-aware visual grounding in instructional videos. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00623"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Huang, D.A., Fei-Fei, L., Niebles, J.C.: Connectionist temporal modeling for weakly supervised action labeling. In: European Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Huynh, D., Elhamifar, E.: Fine-grained generalized zero-shot learning via dense attribute-based attention. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00454"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Huynh, D., Elhamifar, E.: A shared multi-attention framework for multi-label zero-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Kukleva, A., Kuehne, H., Sener, F., Gall, J.: Unsupervised learning of action classes with continuous temporal embedding. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01234"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Malmaud, J., Huang, J., Rathod, V., Johnston, N., Rabinovich, A., Murphy, K.: What\u2019s cookin\u2019? Interpreting cooking videos using text, speech and vision. In: NAACL (2015)","DOI":"10.3115\/v1\/N15-1015"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. arXiv:1912.06430 (2019)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"33_CR21","unstructured":"Phuong, M., Lampert, C.: Towards understanding knowledge distillation. In: International Conference on Machine learning (2019)"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Puig, X., et al.: Simulating household activities via programs. In: IEEE Conference on computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00886"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Weakly supervised action learning with RNN based fine-to-coarse modeling. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.140"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Rochan, M., Ye, L., Wang, Y.: Video summarization using fully convolutional sequence networks. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"33_CR25","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: International Conference on Learning Representations (2014)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Sculley, D.: Web-scale k-means clustering. WWW (2010)","DOI":"10.1145\/1772690.1772862"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Sener, F., Yao, A.: Unsupervised learning and segmentation of complex activities from video. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00873"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Sener, F., Yao, A.: Zero-shot anticipation for instructional activities. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00095"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Sener, O., Zamir, A.R., Savarese, S., Saxena, A.: Unsupervised semantic parsing of video collections. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.509"},{"key":"33_CR30","unstructured":"Tijmen, T., Hinton, G.: Lecture 6.5-RMSProp: divide the gradient by a running average of its recent magnitude. In: COURSERA: Neural networks for machine learning 4.2 (2012)"},{"key":"33_CR31","unstructured":"Xu, C., Elhamifar, E.: Deep supervised summarization: algorithm and application to learning instructions. In: Neural Information Processing Systems (2019)"},{"key":"33_CR32","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention (2015)"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Yang, Y., Li, Y., Ferm\u00fcller, C., Aloimonos, Y.: Robot learning manipulation action plans by watching unconstrained videos from the World Wide Web. In: AAAI (2015)","DOI":"10.1609\/aaai.v29i1.9671"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Yu, S.I., Jiang, L., Hauptmann, A.: Instructional videos for unsupervised harvesting and learning of action examples. In: ACM International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654997"},{"key":"33_CR35","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: International Conference on Learning Representations (2017)"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Zhukov, D., Alayrac, J.B., Cinbis, R.G., Fouhey, D., Laptev, I., Sivic, J.: Cross-task weakly supervised learning from instructional videos. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00365"}],"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\/978-3-030-58520-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:24:00Z","timestamp":1731889440000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58520-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585198","9783030585204"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58520-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 November 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)"}}]}}