{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:10:43Z","timestamp":1742998243895,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030884826"},{"type":"electronic","value":"9783030884833"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-88483-3_27","type":"book-chapter","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T13:55:25Z","timestamp":1633874125000},"page":"345-353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-stage Multi-modal Pre-training for Video Representation"],"prefix":"10.1007","author":[{"given":"Chunquan","family":"Chen","sequence":"first","affiliation":[]},{"given":"Lujia","family":"Bao","sequence":"additional","affiliation":[]},{"given":"Weikang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaoshuai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xinghai","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Qi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"27_CR2","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":"27_CR3","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: Cnn architectures for large-scale audio classification. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"27_CR5","unstructured":"Huang, G., Pang, B., Zhu, Z., Rivera, C., Soricut, R.: Multimodal pre-training for dense video captioning. arXiv preprint arXiv:2011.11760 (2020a)"},{"key":"27_CR6","unstructured":"Lan, Z., et al.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"key":"27_CR7","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.-J., Chang, K.-W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"27_CR8","unstructured":"Ngiam, J., et al.: Multimodal deep learning. In ICML (2011)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4594\u20134602 (2016)","DOI":"10.1109\/CVPR.2016.497"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A.J., Angelova, A., Toshev, A., Ryoo, M.S.: Evolving space-time neural architectures for videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1793\u20131802 (2019)","DOI":"10.1109\/ICCV.2019.00188"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Qi, F., Yang, X., Xu, C.: A unified framework for multimodal domain adaptation. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 429\u2013437 (2018)","DOI":"10.1145\/3240508.3240633"},{"key":"27_CR12","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Silberer, C., Lapata, M.: Learning grounded meaning representations with autoencoders. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 721\u2013732 (2014)","DOI":"10.3115\/v1\/P14-1068"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: a joint model for video and language representation learning. In Proceedings of the IEEE International Conference on Computer Vision, pp. 7464\u20137473 (2019a)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"27_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-32381-3_16","volume-title":"Chinese Computational Linguistics","author":"C Sun","year":"2019","unstructured":"Sun, C., Qiu, X., Xu, Y., Huang, X.: How to Fine-Tune BERT for text classification? In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds.) CCL 2019. LNCS (LNAI), vol. 11856, pp. 194\u2013206. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Wang, W., Tran, D., Feiszli, M.: What makes training multi-modal classification networks hard? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12695\u201312705 (2020)","DOI":"10.1109\/CVPR42600.2020.01271"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88483-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:34:32Z","timestamp":1710257672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88483-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030884826","9783030884833"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88483-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2021\/","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"446","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":"66","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":"15% - 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":"1.5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23 poster papers and 27 workshop papers are also included.","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)"}}]}}