{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:30:59Z","timestamp":1781587859963,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031282379","type":"print"},{"value":"9783031282386","type":"electronic"}],"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\/978-3-031-28238-6_40","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T17:03:18Z","timestamp":1678986198000},"page":"493-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Dialogue-to-Video Retrieval"],"prefix":"10.1007","author":[{"given":"Chenyang","family":"Lyu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manh-Duy","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Van-Tu","family":"Ninh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liting","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer","family":"Foster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Alamri, H., et al.: Audio-visual scene-aware dialog. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00774"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Anne Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"40_CR3","unstructured":"Bahdanau, D., Cho, K.H., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)"},{"key":"40_CR4","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: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"40_CR5","unstructured":"Cheng, X., Lin, H., Wu, X., Yang, F., Shen, D.: Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv:2109.04290 (2021)"},{"key":"40_CR6","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, pp. 4171\u20134186. Association for Computational Linguistics, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"40_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Dzabraev, M., Kalashnikov, M., Komkov, S., Petiushko, A.: MDMMT: multidomain multimodal transformer for video retrieval. In: CVPR (2021)","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"40_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. In: Empirical Methods in Natural Language Processing (EMNLP) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"He, F., et al.: Improving video retrieval by adaptive margin. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1359\u20131368 (2021)","DOI":"10.1145\/3404835.3462927"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR13","doi-asserted-by":"publisher","unstructured":"Hezel, N., Schall, K., Jung, K., Barthel, K.U.: Efficient search and\u00a0browsing of\u00a0large-scale video collections with\u00a0vibro. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 487\u2013492. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_43","DOI":"10.1007\/978-3-030-98355-0_43"},{"issue":"8","key":"40_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"issue":"6","key":"40_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"40_CR17","doi-asserted-by":"publisher","unstructured":"Le, T.-K., Ninh, V.-T., Tran, M.-K., Healy, G., Gurrin, C., Tran, M.-T.: AVSeeker: an active video retrieval engine at\u00a0VBS2022. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 537\u2013542. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_51","DOI":"10.1007\/978-3-030-98355-0_51"},{"issue":"11","key":"40_CR18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"40_CR19","doi-asserted-by":"publisher","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703. https:\/\/www.aclweb.org\/anthology\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"40_CR20","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. arXiv:1907.13487 (2019)"},{"key":"40_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"40_CR22","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of CLIP for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Madasu, A., Oliva, J., Bertasius, G.: Learning to retrieve videos by asking questions. arXiv preprint arXiv:2205.05739 (2022)","DOI":"10.1145\/3503161.3548361"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Maeoki, S., Uehara, K., Harada, T.: Interactive video retrieval with dialog. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 952\u2013953 (2020)","DOI":"10.1109\/CVPRW50498.2020.00484"},{"key":"40_CR25","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learning a text-video embedding from incomplete and heterogeneous data. arXiv:1804.02516 (2018)"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: ICMR (2018)","DOI":"10.1145\/3206025.3206064"},{"key":"40_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Song, Y., Chen, S., Jin, Q.: Towards diverse paragraph captioning for untrimmed videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11245\u201311254 (2021)","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"40_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, USA, pp. 6000\u20136010. Curran Associates Inc. (2017). http:\/\/dl.acm.org\/citation.cfm?id=3295222.3295349"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"40_CR31","doi-asserted-by":"publisher","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, October 2020. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6. https:\/\/aclanthology.org\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"issue":"9","key":"40_CR32","doi-asserted-by":"publisher","first-page":"2360","DOI":"10.1109\/TMM.2018.2807588","volume":"20","author":"X Yang","year":"2018","unstructured":"Yang, X., Zhang, T., Xu, C.: Text2Video: an end-to-end learning framework for expressing text with videos. IEEE Trans. Multimedia 20(9), 2360\u20132370 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"40_CR33","unstructured":"Zheng, Y., Chen, G., Liu, X., Sun, J.: MMChat: multi-modal chat dataset on social media. In: Proceedings of the 13th Language Resources and Evaluation Conference. European Language Resources Association (2022)"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-28238-6_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T13:50:12Z","timestamp":1709646612000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-28238-6_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031282379","9783031282386"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-28238-6_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dublin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ireland","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":"2 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"45","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2023.org\/index.html?v=1.0","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"489","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":"77","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":"83","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":"16% - 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":"3","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)"}}]}}