{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:46:00Z","timestamp":1778082360653,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031560651","type":"print"},{"value":"9783031560668","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-56066-8_15","type":"book-chapter","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T15:05:28Z","timestamp":1710428728000},"page":"161-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Does the\u00a0Performance of\u00a0Text-to-Image Retrieval Models Generalize Beyond Captions-as-a-Query?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1130-8065","authenticated-orcid":false,"given":"Juan Manuel","family":"Rodriguez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nima","family":"Tavassoli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eliezer","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gil","family":"Lederman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dima","family":"Sivov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7922-5998","authenticated-orcid":false,"given":"Matteo","family":"Lissandrini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8256-2258","authenticated-orcid":false,"given":"Davide","family":"Mottin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,15]]},"reference":[{"key":"15_CR1","unstructured":"ACM (2020). Artifact review and badging - current. https:\/\/www.acm.org\/publications\/policies\/artifact-review-and-badging-current"},{"issue":"4","key":"15_CR2","first-page":"823","volume":"47","author":"H Aguinis","year":"2021","unstructured":"Aguinis, H., Villamor, I., Ramani, R.S.: MTurk research: review and recommendations. J. Manag. 47(4), 823\u2013837 (2021)","journal-title":"J. Manag."},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Alemu, Y., Koh, J.B., Ikram, M., Kim, D.K.: Image retrieval in multimedia databases: a survey. In: 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 681\u2013689 (2009)","DOI":"10.1109\/IIH-MSP.2009.159"},{"key":"15_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/978-3-030-99739-7_30","volume-title":"Advances in Information Retrieval","author":"E Bassani","year":"2022","unstructured":"Bassani, E.: ranx: a blazing-fast Python library for\u00a0ranking evaluation and\u00a0comparison. In: Hagen, M., et al. (eds.) ECIR 2022. LNCS, vol. 13186, pp. 259\u2013264. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-99739-7_30"},{"key":"15_CR5","unstructured":"Blattmann, A., Rombach, R., Oktay, K., M\u00fcller, J., Ommer, B.: Retrieval-augmented diffusion models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 15309\u201315324 (2022)"},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-642-15393-8_43","volume-title":"Knowledge-Based and Intelligent Information and Engineering Systems","author":"C Bouras","year":"2010","unstructured":"Bouras, C., Tsogkas, V.: W-kmeans: clustering news articles using WordNet. In: Setchi, R., Jordanov, I., Howlett, R.J., Jain, L.C. (eds.) KES 2010. LNCS (LNAI), vol. 6278, pp. 379\u2013388. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15393-8_43"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Cao, M., Li, S., Li, J., Nie, L., Zhang, M.: Image-text retrieval: a survey on recent research and development. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-2022, pp. 5410\u20135417 (7 2022). Survey Track","DOI":"10.24963\/ijcai.2022\/759"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3558\u20133568, June 2021","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Jia, J.: Jigsaw clustering for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11526\u201311535, June 2021","DOI":"10.1109\/CVPR46437.2021.01136"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1218\u20131226 (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"15_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-031-28241-6_5","volume-title":"Advances in Information Retrieval","author":"M Hendriksen","year":"2023","unstructured":"Hendriksen, M., Vakulenko, S., Kuiper, E., de Rijke, M.: Scene-centric vs. object-centric image-text cross-modal retrieval: a reproducibility study. In: Kamps, J., et al. (eds.) ECIR 2023. LNCS, vol. 13982, pp. 68\u201385. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-28241-6_5"},{"key":"15_CR12","unstructured":"Honnibal, M., Montani, I., Van Landeghem, S., Boyd, A.: spaCy: Industrial-strength Natural Language Processing in Python, January 2022"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Kacprzak, E., Koesten, L.M., Ib\u00e1\u00f1ez, L.D., Simperl, E., Tennison, J.: A query log analysis of dataset search. In: Web Engineering, pp. 429\u2013436 (2017)","DOI":"10.1007\/978-3-319-60131-1_29"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Kalkowski, S., Schulze, C., Dengel, A., Borth, D.: Real-time analysis and visualization of the YFCC100m dataset. In: Workshop on Community-Organized Multimodal Mining: Opportunities for Novel Solutions, pp. 25\u201330, New York, NY, USA (2015)","DOI":"10.1145\/2814815.2814820"},{"key":"15_CR16","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"15_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"KH Lee","year":"2018","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"15_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"15_CR19","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 12888\u201312900 (2022)"},{"key":"15_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"15_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"15_CR22","doi-asserted-by":"publisher","unstructured":"Luo, C., et al.: Query attribute recommendation at Amazon search. In: Proceedings of the 16th ACM Conference on Recommender Systems, RecSys 2022, pp. 506\u2013508 (2022). https:\/\/doi.org\/10.1145\/3523227.3547395","DOI":"10.1145\/3523227.3547395"},{"issue":"11","key":"15_CR23","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"15_CR24","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2Text: describing images using 1 million captioned photographs. In: Advances in Neural Information Processing Systems, vol. 24. Curran Associates, Inc. (2011)"},{"key":"15_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning. PMLR, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, November 2019","DOI":"10.18653\/v1\/D19-1410"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695, June 2022","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR28","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs (2021)"},{"key":"15_CR29","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: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"15_CR30","unstructured":"Wang, B.: Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX, May 2021. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, R., Yao, Z., Shan, S., Chen, X.: Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2020)","DOI":"10.1109\/WACV45572.2020.9093614"},{"issue":"12","key":"15_CR32","doi-asserted-by":"publisher","first-page":"10718","DOI":"10.1609\/aaai.v35i12.17281","volume":"35","author":"S Yoon","year":"2021","unstructured":"Yoon, S., et al.: Image-to-image retrieval by learning similarity between scene graphs. AAAI 35(12), 10718\u201310726 (2021)","journal-title":"AAAI"},{"key":"15_CR33","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Yu, T., Fei, H., Li, P.: U-BERT for fast and scalable text-image retrieval. In: Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval, pp. 193\u2013203 (2022)","DOI":"10.1145\/3539813.3545148"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, K., Mao, Z., Wang, Q., Zhang, Y.: Negative-aware attention framework for image-text matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15661\u201315670 (2022)","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Song, Y., Jin, Q.: Progressive learning for image retrieval with hybrid-modality queries. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1012\u20131021 (2022)","DOI":"10.1145\/3477495.3532047"}],"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\/978-3-031-56066-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T00:06:49Z","timestamp":1710461209000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56066-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560651","9783031560668"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56066-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 March 2024","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2024.org\/","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":"578","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":"110","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":"69","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":"19% - 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":"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":"31 (Tracks: Workshop, Tutorial, Industry, Doctoral Consortium)","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)"}}]}}