{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:40:12Z","timestamp":1781584812906,"version":"3.54.5"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197802","type":"print"},{"value":"9783031197819","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19781-9_14","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"233-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Multi-query Video Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7057-1613","authenticated-orcid":false,"given":"Zeyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1680-8253","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9894-9983","authenticated-orcid":false,"given":"Karthik","family":"Narasimhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5272-3241","authenticated-orcid":false,"given":"Olga","family":"Russakovsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: Overcoming priors for visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"14_CR2","unstructured":"Alayrac, J.B., et al.: Self-supervised multimodal versatile networks. In: NeurIPS (2020)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Andr\u00e9s Portillo-Quintero, J., Ortiz-Bayliss, J.C., Terashima-Mar\u00edn, H.: A straightforward framework for video retrieval using CLIP. arXiv:2102.12443 (2021)","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"14_CR4","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":"14_CR5","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":"14_CR6","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"14_CR8","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. arXiv:2104.00650 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"14_CR9","unstructured":"Chen, D., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL (2011)"},{"key":"14_CR10","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":"14_CR11","doi-asserted-by":"crossref","unstructured":"Chum, O., Mikulik, A., Perdoch, M., Matas, J.: Total recall II: query expansion revisited. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995601"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automatic query expansion with a generative feature model for object retrieval. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Chung, J., Wuu, C., Yang, H., Tai, Y.-W., Tang, C.-K.: Haa500: human-centric atomic action dataset with curated videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01321"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. In: PAMI (2021)","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"14_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"14_CR16","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":"14_CR17","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: CLIP2Video: mastering video-text retrieval via image CLIP. arXiv:2106.11097 (2021)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Fernando, B., Tuytelaars, T.: Mining multiple queries for image retrieval: on-the-fly learning of an object-specific mid-level representation. In: CVPR (2013)","DOI":"10.1109\/ICCV.2013.316"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Nagrani, A., Sun, C., Alahari, K., Schmid, C.: Masking modalities for cross-modal video retrieval. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00217"},{"key":"14_CR20","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":"14_CR21","unstructured":"Gao, Z., Liu, J., Chen, S., Chang, D., Zhang, H., Yuan, J.: CLIP2TV: an empirical study on transformer-based methods for video-text retrieval. arXiv:2111.05610 (2021)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Gordo, A., Almazan, J., Revaud, J., Larlus, D.: End-to-end learning of deep visual representations for image retrieval. IJCV (2017)","DOI":"10.1007\/s11263-017-1016-8"},{"key":"14_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-030-58604-1_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Gordo","year":"2020","unstructured":"Gordo, A., Radenovic, F., Berg, T.: Attention-based query expansion learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 172\u2013188. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_11"},{"key":"14_CR24","unstructured":"Goyal, P., et al.: Self-supervised pretraining of visual features in the wild. arXiv:2103.01988 (2021)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Huang, S., Hang, H.M.: Multi-query image retrieval using CNN and SIFT features. In: APSIPA ASC (2017)","DOI":"10.1109\/APSIPA.2017.8282180"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Imani, A., Vakili, A., Montazer, A., Shakery, A.: Deep neural networks for query expansion using word embeddings. In: ECIR (2019)","DOI":"10.1007\/978-3-030-15719-7_26"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos Niebles, J.: Dense-captioning events in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T.L., Bansal, M., Liu, J.: Less is more: clipBERT for video-and-language learning via sparse sampling. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"14_CR30","unstructured":"Li, G., He, F., Feng, Z.: A CLIP-Enhanced method for video-language understanding. arXiv:2110.07137 (2021)"},{"key":"14_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Liu, T., Lin, Y., Du, B.: Unsupervised person re-identification with stochastic training strategy. TIP (2022)","DOI":"10.1109\/TIP.2022.3181811"},{"key":"14_CR33","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":"14_CR34","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv:1608.03983 (2016)"},{"key":"14_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv:1711.05101 (2017)"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Luo, H., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: CLIP4clip: an empirical study of CLIP for end to end video clip retrieval. arXiv:2104.08860 (2021)","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"14_CR37","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learning a text-video embedding from incomplete and heterogeneous data. arXiv:1804.02516 (2018)"},{"key":"14_CR38","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"14_CR39","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":"14_CR40","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. arXiv:2010.02824 (2020)"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. TPAMI (2018)","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"14_CR42","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv:2103.00020 (2021)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"14_CR45","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"14_CR46","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Vural, C., Akbacak, E.: Deep multi query image retrieval. SPIC (2020)","DOI":"10.1016\/j.image.2020.115970"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2VLAD: global-local sequence alignment for text-video retrieval. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: VATEX: a large-scale, high-quality multilingual dataset for video-and-language research. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lin, X., Wu, L., Zhang, W.: Effective multi-query expansions: robust landmark retrieval. In: ACMMM (2015)","DOI":"10.1145\/2733373.2806233"},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lin, X., Wu, L., Zhang, W.: Effective multi-query expansions: collaborative deep networks for robust landmark retrieval. TIP (2017)","DOI":"10.1109\/TIP.2017.2655449"},{"key":"14_CR53","unstructured":"Wu, Y., Jiang, L., Yang, Y.: Switchable novel object captioner. TPAMI (2022)"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"14_CR55","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"14_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/978-3-030-01234-2_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Yu","year":"2018","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 487\u2013503. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_29"},{"key":"14_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-030-01261-8_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhang","year":"2018","unstructured":"Zhang, B., Hu, H., Sha, F.: Cross-modal and hierarchical modeling of video and text. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 385\u2013401. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_23"},{"key":"14_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1007\/978-3-319-46466-4_52","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Zheng","year":"2016","unstructured":"Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 868\u2013884. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_52"},{"key":"14_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: ActBERT: learning global-local video-text representations. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00877"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19781-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:33:38Z","timestamp":1710261218000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19781-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197802","9783031197819"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19781-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}