{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:40:55Z","timestamp":1742985655834,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031441943"},{"type":"electronic","value":"9783031441950"}],"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\/978-3-031-44195-0_29","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:04:08Z","timestamp":1695297848000},"page":"349-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Token Excitation with\u00a0Negative Selection for\u00a0Video-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Juntao","family":"Yu","sequence":"first","affiliation":[]},{"given":"Zhangkai","family":"Ni","sequence":"additional","affiliation":[]},{"given":"Taiyi","family":"Su","sequence":"additional","affiliation":[]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: A joint video and image encoder for end-to-end retrieval. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"29_CR2","unstructured":"Cai, T.T., Frankle, J., Schwab, D.J., Morcos, A.S.: Are all negatives created equal in contrastive instance discrimination? In: arXiv:2010.06682 (2020)"},{"key":"29_CR3","unstructured":"Chen, D., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of Annual Meeting of the Association for Computational Linguistics ACL 2011, pp. 190\u2013200 (2011)"},{"key":"29_CR4","unstructured":"Cheng, X., Lin, H., Wu, X., Yang, F., Shen, D.: Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. In: arXiv:2109.04290 (2021)"},{"key":"29_CR5","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: CLIP2Video: Mastering video-text retrieval via image clip. In: arXiv:2106.11097 (2021)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Proceedings of ECCV 2020, pp. 214\u2013229 (2020)","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Gao, L., Zhang, Y., Han, J., Callan, J.: Scaling deep contrastive learning batch size under memory limited setup. In: Proceedings RepL4NLP 2021 (2021)","DOI":"10.18653\/v1\/2021.repl4nlp-1.31"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Gorti, S.K., et al.: X-Pool: Cross-modal language-video attention for text-video retrieval. In: Proceedings of CVPR 2022, pp. 5006\u20135015 (2022)","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Huynh, T., Kornblith, S., Walter, M.R., Maire, M., Khademi, M.: Boosting contrastive self-supervised learning with false negative cancellation. In: Proceedings of WACV 2022, pp. 2785\u20132795 (2022)","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Ji, K., Liu, J., Hong, W., Zhong, L., Wang, J., et al.: CRET: Cross-modal retrieval transformer for efficient text-video retrieval. In: Proceedings of SIGIR 2022, pp. 949\u2013959 (2022)","DOI":"10.1145\/3477495.3531960"},{"key":"29_CR11","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. In: Proceedings of BMVC 2019 (2019)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xiong, P., Xu, L., Cao, S., Jin, Q.: TS2-Net: token shift and selection transformer for text-video retrieval. In: Proceedings of ECCV 2022, pp. 319\u2013335 (2022)","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Luo, H., Ji, L., Zhong, M., Chen, Y., Lei, W., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval and captioning. In: Neurocomputing. vol. 508, pp. 293\u2013304 (2022)","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"29_CR14","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. In: arXiv:1807.03748 (2018)"},{"key":"29_CR15","unstructured":"Patrick, M., Huang, P.Y., Asano, Y., Metze, F., Hauptmann, A.G., et al.: Support-set bottlenecks for video-text representation learning. In: Proceedings of ICLR 2020 (2020)"},{"key":"29_CR16","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of ICML 2021, pp. 8748\u20138763 (2021)"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-319-24947-6_17","volume-title":"Pattern Recognition","author":"A Rohrbach","year":"2015","unstructured":"Rohrbach, A., Rohrbach, M., Schiele, B.: The long-short story of movie description. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 209\u2013221. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24947-6_17"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2VLAD: global-local sequence alignment for text-video retrieval. In: Proceedings of CVPR 2021, pp. 5079\u20135088 (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"29_CR19","unstructured":"Wu, M., Mosse, M., Zhuang, C., Yamins, D., Goodman, N.: Conditional negative sampling for contrastive learning of visual representations. In: Proceedings of ICLR 2020 (2020)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of CVPR 2018, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of CVPR 2016, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: Proceedings of ECCV 2018, pp. 471\u2013487 (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Zhu, Y., Gehler, P., Brox, T.: CrossCLR: cross-modal contrastive learning for multi-modal video representations. In: Proceedings of ICCV 2021, pp. 1450\u20131459 (2021)","DOI":"10.1109\/ICCV48922.2021.00148"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44195-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:08:30Z","timestamp":1695298110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44195-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441943","9783031441950"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44195-0_29","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":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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":"type of other papers accepted  : 9 Abstract","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)"}}]}}