{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:48:36Z","timestamp":1756309716787,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031278174"},{"type":"electronic","value":"9783031278181"}],"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\/978-3-031-27818-1_39","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"471-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Transformer-Based Cross-Modal Recipe Embeddings with\u00a0Large Batch Training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2103-6825","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1355-4128","authenticated-orcid":false,"given":"Junwen","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0431-183X","authenticated-orcid":false,"given":"Keiji","family":"Yanai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Carvalho, M., Cad\u00e8ne, R., Picard, D., Soulier, L., Thome, N., Cord, M.: Cross-modal retrieval in the cooking context: learning semantic text-image embeddings. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 35\u201344 (2018)","DOI":"10.1145\/3209978.3210036"},{"key":"39_CR2","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of International Conference on Machine Learning (2020)"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"39_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"39_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Fu, H., Wu, R., Liu, C., Sun, J.: MCEN: bridging cross-modal gap between cooking recipes and dish images with latent variable model. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01458"},{"issue":"11","key":"39_CR7","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"IJ Goodfellow","year":"2020","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"issue":"5\u20136","key":"39_CR8","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5\u20136), 602\u2013610 (2005)","journal-title":"Neural Netw."},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Guerrero, R., Xuan, H.P., Vladimir, P.: Cross-modal retrieval and synthesis (X-MRS): closing the modality gap in shared representation learning. In: Proceedings of ACM International Conference Multimedia (2021)","DOI":"10.1145\/3474085.3475465"},{"key":"39_CR10","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767\u20135777 (2017)"},{"key":"39_CR11","doi-asserted-by":"publisher","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","volume":"7","author":"W Guo","year":"2019","unstructured":"Guo, W., Wang, J., Wang, S.: Deep multimodal representation learning: a survey. IEEE Access 7, 63373\u201363394 (2019)","journal-title":"IEEE Access"},{"key":"39_CR12","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"key":"39_CR13","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6629\u20136640 (2017)"},{"key":"39_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representation (2015)"},{"key":"39_CR15","doi-asserted-by":"publisher","unstructured":"Li, J., Sun, J., Xu, X., Yu, W., Shen, F.: Cross-modal image-recipe retrieval via intra- and inter-modality hybrid fusion. In: Proceedings of ACM International Conference on Multimedia Retrieval, pp. 173\u2013182 (2021). https:\/\/doi.org\/10.1145\/3460426.3463618","DOI":"10.1145\/3460426.3463618"},{"issue":"1","key":"39_CR16","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1109\/TPAMI.2019.2927476","volume":"43","author":"J Marin","year":"2019","unstructured":"Marin, J., et al.: Recipe1m+: a dataset for learning cross-modal embeddings for cooking recipes and food images. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 187\u2013203 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Pham, H.X., Guerrero, R., Pavlovic, V., Li, J.: CHEF: cross-modal hierarchical embeddings for food domain retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2423\u20132430 (2021)","DOI":"10.1609\/aaai.v35i3.16343"},{"key":"39_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of International Conference on Machine Learning, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Salvador, A., Gundogdu, E., Bazzani, L., Donoser, M.: Revamping cross-modal recipe retrieval with hierarchical transformers and self-supervised learning. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Salvador, A., et al.: Learning cross-modal embeddings for cooking recipes and food images. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.327"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Sugiyama, Y., Yanai, K.: Cross-modal recipe embeddings by disentangling recipe contents and dish styles. In: Proceedings of ACM International Conference Multimedia (2021)","DOI":"10.1145\/3474085.3475422"},{"key":"39_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Wang, H., Sahoo, D., Liu, C., Lim, E., Hoi, S.C.: Learning cross-modal embeddings with adversarial networks for cooking recipes and food images. In: Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 11572\u201311581 (2019)","DOI":"10.1109\/CVPR.2019.01184"},{"key":"39_CR25","unstructured":"Wang, H., et al.: Cross-modal food retrieval: learning a joint embedding of food images and recipes with semantic consistency and attention mechanism. arXiv:2003.03955 (2020)"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Zan, Z., Li, L., Liu, J., Zhou, D.: Sentence-based and noise-robust cross-modal retrieval on cooking recipes and food images. In: Proceedings of the International Conference on Multimedia Retrieval, p. 117\u2013125 (2020)","DOI":"10.1145\/3372278.3390681"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, B., Ngo, C.W., Chen, J., Hao, Y.: R2GAN: cross-modal recipe retrieval with generative adversarial network. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01174"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27818-1_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:30:53Z","timestamp":1680172253000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","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":"86","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":"32% - 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)"}}]}}