{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:05:08Z","timestamp":1773414308625,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585822","type":"print"},{"value":"9783030585839","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58583-9_22","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"359-374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Structure-Aware Generation Network for Recipe Generation from Images"],"prefix":"10.1007","author":[{"given":"Hao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven C. H.","family":"Hoi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyan","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"22_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"22_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Britz, D., Goldie, A., Luong, M.T., Le, Q.: Massive exploration of neural machine translation architectures. arXiv preprint arXiv:1703.03906 (2017)","DOI":"10.18653\/v1\/D17-1151"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chandu, K.R., Nyberg, E., Black, A.: Storyboarding of recipes: Grounded contextual generation (2019)","DOI":"10.18653\/v1\/P19-1606"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., He, X., Pu, S., Chang, S.F.: Counterfactual critic multi-agent training for scene graph generation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4613\u20134623 (2019)","DOI":"10.1109\/ICCV.2019.00471"},{"key":"22_CR6","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"22_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"22_CR9","unstructured":"Golland, D., Liang, P., Klein, D.: A game-theoretic approach to generating spatial descriptions. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 410\u2013419. Association for Computational Linguistics (2010)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Zhao, H., Yang, X., Wang, G.: Unpaired image captioning via scene graph alignments. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10323\u201310332 (2019)","DOI":"10.1109\/ICCV.2019.01042"},{"key":"22_CR11","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"22_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. (CSUR) 51(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Jia, Y., Ye, Y., Feng, Y., Lai, Y., Yan, R., Zhao, D.: Modeling discourse cohesion for discourse parsing via memory network. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 438\u2013443 (2018)","DOI":"10.18653\/v1\/P18-2070"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"22_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"22_CR16","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, July 2004"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Lin, X., Joty, S., Jwalapuram, P., Bari, S.: A unified linear-time framework for sentence-level discourse parsing. arXiv preprint arXiv:1905.05682 (2019)","DOI":"10.18653\/v1\/P19-1410"},{"key":"22_CR18","unstructured":"Logeswaran, L., Lee, H.: An efficient framework for learning sentence representations. arXiv preprint arXiv:1803.02893 (2018)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Luo, R., Price, B., Cohen, S., Shakhnarovich, G.: Discriminability objective for training descriptive captions. arXiv preprint arXiv:1803.04376 (2018)","DOI":"10.1109\/CVPR.2018.00728"},{"issue":"5","key":"22_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3329168","volume":"52","author":"W Min","year":"2019","unstructured":"Min, W., Jiang, S., Liu, L., Rui, Y., Jain, R.: A survey on food computing. ACM Comput. Surv. (CSUR) 52(5), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Salvador, A., Drozdzal, M., Giro-i Nieto, X., Romero, A.: Inverse cooking: recipe generation from food images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10453\u201310462 (2019)","DOI":"10.1109\/CVPR.2019.01070"},{"key":"22_CR24","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":"22_CR25","unstructured":"Shen, Y., Lin, Z., Huang, C.W., Courville, A.: Neural language modeling by jointly learning syntax and lexicon. arXiv preprint arXiv:1711.02013 (2017)"},{"key":"22_CR26","unstructured":"Shen, Y., Tan, S., Sordoni, A., Courville, A.: Ordered neurons: integrating tree structures into recurrent neural networks. arXiv preprint arXiv:1810.09536 (2018)"},{"key":"22_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"22_CR28","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Sahoo, D., Liu, C., Lim, E.P., Hoi, S.C.: Learning cross-modal embeddings with adversarial networks for cooking recipes and food images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11572\u201311581 (2019)","DOI":"10.1109\/CVPR.2019.01184"},{"key":"22_CR31","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 preprint arXiv:2003.03955 (2020)"},{"key":"22_CR32","unstructured":"You, J., Ying, R., Ren, X., Hamilton, W.L., Leskovec, J.: GraphRNN: generating realistic graphs with deep auto-regressive models. arXiv preprint arXiv:1802.08773 (2018)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12342"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58583-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:09:11Z","timestamp":1731888551000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58583-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585822","9783030585839"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58583-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 November 2020","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":"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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}