{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:11:24Z","timestamp":1742994684515,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030923099"},{"type":"electronic","value":"9783030923105"}],"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\/978-3-030-92310-5_55","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T14:04:20Z","timestamp":1638799460000},"page":"476-484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-interaction Model with\u00a0Cross-Branch Feature Fusion for\u00a0Video-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Junting","family":"Li","sequence":"first","affiliation":[]},{"given":"Dehao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yuesheng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"55_CR1","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., et al.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: CVPR, pp. 10638\u201310647 (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous Visual-semantic embedding for cross-modal retrieval. arXiv preprint arXiv:1906.04402 (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"55_CR3","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: ECCV, pp. 471\u2013487 (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"55_CR5","unstructured":"Liu, Y., et al.: Use what you have: video retrieval using representations from collaborative experts. In: BMVC (2019)"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., et al.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Loko, J., et al.: A W2VV++ case study with automated and interactive text-to-video retrieval. In: MM, pp. 2553\u20132561 (2020)","DOI":"10.1145\/3394171.3414002"},{"key":"55_CR8","unstructured":"Faghri, F., et al.: VSE++: improving visual-semantic embeddings with hard negatives. In: BMVC (2018)"},{"key":"55_CR9","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. In: TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Universal weighting metric learning for cross-modal matching. In: CVPR, pp. 13005\u201313014 (2020)","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"55_CR11","unstructured":"Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Circle loss: a unified perspective of pair similarity optimization. In: CVPR, pp. 6398\u20136407 (2020)","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Feng, F., et al.: Cross-modal retrieval with correspondence autoencoder. In: MM, pp. 7\u201316 (2014)","DOI":"10.1145\/2647868.2654902"},{"key":"55_CR14","doi-asserted-by":"crossref","unstructured":"Wu, D., et al.: Multi-dimensional attentive hierarchical graph pooling network for video-text retrieval. In: ICME (2021)","DOI":"10.1109\/ICME51207.2021.9428153"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"55_CR16","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: CVPR, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TGIF: a new dataset and benchmark on animated GIF description. In: CVPR, pp. 4641\u20134650 (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"55_CR18","unstructured":"Kingma, DP., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"55_CR19","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Xie, S., et al.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 1492\u20131500. (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: CVPR, pp: 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92310-5_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T08:11:51Z","timestamp":1655799111000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92310-5_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030923099","9783030923105"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92310-5_55","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","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":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}