{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T00:51:30Z","timestamp":1746233490746,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030997359"},{"type":"electronic","value":"9783030997366"}],"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\/978-3-030-99736-6_36","type":"book-chapter","created":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T23:02:47Z","timestamp":1649113367000},"page":"535-551","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Do Lessons from\u00a0Metric Learning Generalize to\u00a0Image-Caption Retrieval?"],"prefix":"10.1007","author":[{"given":"Maurits","family":"Bleeker","sequence":"first","affiliation":[]},{"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,5]]},"reference":[{"key":"36_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-030-58545-7_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Brown","year":"2020","unstructured":"Brown, A., Xie, W., Kalogeiton, V., Zisserman, A.: Smooth-AP: smoothing the path towards large-scale image retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 677\u2013694. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_39"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Bruch, S., Wang, X., Bendersky, M., Najork, M.: An analysis of the softmax cross entropy loss for learning-to-rank with binary relevance. In: International Conference on Theory of Information Retrieval (ICTIR), pp. 75\u201378. ACM (2019)","DOI":"10.1145\/3341981.3344221"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Bruch, S., Zoghi, M., Bendersky, M., Najork, M.: Revisiting approximate metric optimization in the age of deep neural networks. In: SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 1241\u20131244. ACM (2019)","DOI":"10.1145\/3331184.3331347"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Liu, X., Lin, Z., Liu, J., Han, J.: IMRAM: iterative matching with recurrent attention memory for cross-modal image-text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12655\u201312663 (2020)","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"36_CR5","unstructured":"Chen, T., Li, L.: Intriguing properties of contrastive losses. arXiv preprint arXiv:2011.02803 (2020)"},{"key":"36_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-030-58601-0_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Chen","year":"2020","unstructured":"Chen, T., Deng, J., Luo, J.: Adaptive offline quintuplet loss for image-text matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 549\u2013565. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_33"},{"key":"36_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, PMLR, pp. 1597\u20131607 (2020)"},{"key":"36_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/978-3-030-72240-1_21","volume-title":"Advances in Information Retrieval","author":"X Chen","year":"2021","unstructured":"Chen, X., He, B., Hui, K., Sun, L., Sun, Y.: Simplified TinyBERT: knowledge distillation for document retrieval. In: Hiemstra, D., Moens, M.-F., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds.) ECIR 2021. LNCS, vol. 12657, pp. 241\u2013248. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72240-1_21"},{"key":"36_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"YC Chen","year":"2020","unstructured":"Chen, Y.C., et al.: UNITER: UNiversal Image-TExt Representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. arXiv preprint arXiv:2101.01368 (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"36_CR12","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Formal, T., Piwowarski, B., Clinchant, S.: SPLADE: sparse lexical and expansion model for first stage ranking. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2288\u20132292 (2021)","DOI":"10.1145\/3404835.3463098"},{"key":"36_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-030-72240-1_26","volume-title":"Advances in Information Retrieval","author":"L Gao","year":"2021","unstructured":"Gao, L., Dai, Z., Callan, J.: Rethink training of BERT rerankers in multi-stage retrieval pipeline. In: Hiemstra, D., Moens, M.-F., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds.) ECIR 2021. LNCS, vol. 12657, pp. 280\u2013286. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72240-1_26"},{"key":"36_CR15","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 (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR16","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. arXiv preprint arXiv:2102.05918 (2021)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 39\u201348 (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"36_CR20","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. arXiv preprint arXiv:2102.03334 (2021)"},{"key":"36_CR21","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"36_CR22","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"36_CR25","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":"36_CR26","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":"TY 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":"36_CR27","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265 (2019)"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Lu, X., Zhao, T., Lee, K.: VisualSparta: an embarrassingly simple approach to large-scale text-to-image search with weighted bag-of-words. arXiv preprint arXiv:2101.00265 (2021)","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Esuli, A., Falchi, F., Gennaro, C., Marchand-Maillet, S.: Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. arXiv preprint arXiv:2008.05231 (2020)","DOI":"10.1145\/3451390"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Messina, N., Falchi, F., Esuli, A., Amato, G.: Transformer reasoning network for image-text matching and retrieval. In: International Conference on Pattern Recognition (ICPR), pp. 5222\u20135229. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413172"},{"key":"36_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/978-3-030-58595-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Musgrave","year":"2020","unstructured":"Musgrave, K., Belongie, S., Lim, S.-N.: A metric learning reality check. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 681\u2013699. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_41"},{"key":"36_CR32","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Oosterhuis, H., de Rijke, M.: Differentiable unbiased online learning to rank. In: International Conference on Information and Knowledge Management (CIKM), pp. 1293\u20131302. ACM (2018)","DOI":"10.1145\/3269206.3271686"},{"key":"36_CR34","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"36_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"36_CR36","unstructured":"Varamesh, A., Diba, A., Tuytelaars, T., Van Gool, L.: Self-supervised ranking for representation learning. arXiv preprint arXiv:2010.07258 (2020)"},{"key":"36_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"36_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/978-3-030-45439-5_45","volume-title":"Advances in Information Retrieval","author":"G Verma","year":"2020","unstructured":"Verma, G., Vinay, V., Bansal, S., Oberoi, S., Sharma, M., Gupta, P.: Using image captions and multitask learning for recommending query reformulations. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12035, pp. 681\u2013696. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45439-5_45"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, C., Golbandi, N., Bendersky, M., Najork, M.: The LambdaLoss framework for ranking metric optimization. In: Conference on Information and Knowledge Management (CIKM), pp. 1313\u20131322. ACM (2018)","DOI":"10.1145\/3269206.3271784"},{"key":"36_CR40","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":"36_CR41","doi-asserted-by":"crossref","unstructured":"Zeng, D., Yu, Y., Oyama, K.: Deep triplet neural networks with cluster-CCA for audio-visual cross-modal retrieval. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 16(3), 1\u201323 (2020)","DOI":"10.1145\/3387164"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 1503\u20131512. Association for Computing Machinery (2021)","DOI":"10.1145\/3404835.3462880"},{"key":"36_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"}],"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\/978-3-030-99736-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T13:02:30Z","timestamp":1710248550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-99736-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030997359","9783030997366"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-99736-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"5 April 2022","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":"Stavanger","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","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":"10 April 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2022.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":"395","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":"35","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":"29","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":"9% - 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":"4-6","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":"Additionally, there are other papers: 11 reproducibility, 12 doctoral, 13 CLEF Labs, 5 workshops and 4 tutorials.","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)"}}]}}