{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T10:29:36Z","timestamp":1762338576948,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756742"},{"type":"electronic","value":"9789819756759"}],"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\/978-981-97-5675-9_36","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T01:10:40Z","timestamp":1722474640000},"page":"423-434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Cross-modal Recipe Retrieval with Hierarchical Transformers and Pretrained Food Image Encoder"],"prefix":"10.1007","author":[{"given":"Hanyan","family":"Qin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiankun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"issue":"12","key":"36_CR1","doi-asserted-by":"publisher","first-page":"3266","DOI":"10.1109\/TMM.2018.2831627","volume":"20","author":"E Aguilar","year":"2018","unstructured":"Aguilar, E., et al.: Grab, pay, and eat: semantic food detection for smart restaurants. IEEE Trans. Multim. 20(12), 3266\u20133275 (2018)","journal-title":"IEEE Trans. Multim."},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Bossard, L., et al.: Food-101\u2013mining discriminative components with random forests. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, 6\u201312 September 2014, Proceedings, Part VI 13, pp. 446\u2013461. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Carvalho, M., et al.: Cross-modal retrieval in the cooking context: learning semantic text-image embeddings. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 35\u201344 (2018)","DOI":"10.1145\/3209978.3210036"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: Mcen: bridging cross-modal gap between cooking recipes and dish images with latent variable model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14570\u201314580 (2020)","DOI":"10.1109\/CVPR42600.2020.01458"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Guerrero, R., et al.: Cross-modal retrieval and synthesis (X-MRS): closing the modality gap in shared subspace learning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3192\u20133201 (2021)","DOI":"10.1145\/3474085.3475465"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Guo, M., et al.: Effective parallel corpus mining using bilingual sentence embeddings. arXiv preprint arXiv:1807.11906 (2018)","DOI":"10.18653\/v1\/W18-6317"},{"key":"36_CR7","unstructured":"Kaur, P., et al.: Foodx-251: a dataset for fine-grained food classification. arXiv preprint arXiv:1907.06167 (2019)"},{"issue":"5","key":"36_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3329168","volume":"52","author":"W Min","year":"2019","unstructured":"Min, W., et al.: A survey on food computing. ACM Comput. Surv. 52(5), 1\u201336 (2019)","journal-title":"ACM Comput. Surv."},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Min, W., et al.: Large scale visual food recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9932\u20139949 (2023)","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Okamoto, K., Yanai, K.: UEC-FoodPIX complete: a large-scale food image segmentation dataset. In: Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, 10\u201315 January 2021, Proceedings, Part V, pp. 647\u2013659. Springer (2021)","DOI":"10.1007\/978-3-030-68821-9_51"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Salvador, A., et al.: Inverse cooking: recipe generation from food images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10453\u201310462 (2019)","DOI":"10.1109\/CVPR.2019.01070"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Salvador, A., et al.: Learning cross-modal embeddings for cooking recipes and food images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3020\u20133028 (2017)","DOI":"10.1109\/CVPR.2017.327"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Salvador, A., et al.: Revamping cross-modal recipe retrieval with hierarchical transformers and self-supervised learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15475\u201315484 (2021)","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Learning cross-modal embeddings with adversarial networks for cooking recipes and food images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11572\u201311581 (2019)","DOI":"10.1109\/CVPR.2019.01184"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Structure-aware generation network for recipe generation from images. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, 23\u201328 August 2020, Proceedings, Part XXVII 16, pp. 359\u2013374. Springer (2020)","DOI":"10.1007\/978-3-030-58583-9_22"},{"key":"36_CR16","doi-asserted-by":"publisher","unstructured":"Yang, J., et al.: Transformer-based cross-modal recipe embeddings with large batch training. In: International Conference on Multimedia Modeling, pp. 471\u2013482 Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27818-1_39","DOI":"10.1007\/978-3-031-27818-1_39"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Zhen, L., et al.: Deep supervised cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10394\u201310403 (2019)","DOI":"10.1109\/CVPR.2019.01064"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Zhu, B., et al.: R2gan: cross-modal recipe retrieval with generative adversarial network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11477\u201311486 (2019)","DOI":"10.1109\/CVPR.2019.01174"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Zhu, B., Ngo, C.-W.: CookGAN: causality based text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5519\u20135527 (2020)","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"36_CR20","unstructured":"Zhu, L., et al.: Cross-modal retrieval: a systematic review of methods and future directions. arXiv preprint arXiv:2308.14263 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5675-9_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T01:20:59Z","timestamp":1722475259000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5675-9_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756742","9789819756759"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5675-9_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}