{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T14:57:56Z","timestamp":1785164276344,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T00:00:00Z","timestamp":1685059200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T00:00:00Z","timestamp":1685059200000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-023-01870-6","type":"journal-article","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T15:02:29Z","timestamp":1685113349000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Multimodal Recipe Recommendation System Using Deep Learning and Rule-Based Approach"],"prefix":"10.1007","volume":"4","author":[{"given":"Abdullah Faiz Ur Rahman","family":"Khilji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Utkarsh","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pintu","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adnan","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pankaj","family":"Dadure","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riyanka","family":"Manna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3834-5154","authenticated-orcid":false,"given":"Partha","family":"Pakray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,26]]},"reference":[{"issue":"4","key":"1870_CR1","doi-asserted-by":"publisher","first-page":"5761","DOI":"10.3233\/JIFS189415","volume":"40","author":"JAA Alzubi","year":"2021","unstructured":"Alzubi JAA, Jain R, Nagrath P, Satapathy S, Taneja S, Gupta P. Deep image captioning using an ensemble of CNN and LSTM based deep neural networks. J Intell Fuzzy Syst. 2021;40(4):5761\u20139. https:\/\/doi.org\/10.3233\/JIFS189415.","journal-title":"J Intell Fuzzy Syst."},{"key":"1870_CR2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T. Enriching word vectors with subword information. Trans Assoc Comput Linguist. 2017;5:135\u201346.","journal-title":"Trans Assoc Comput Linguist"},{"key":"1870_CR3","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer vision\u2014ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard L, Guillaumin M, Van Gool L. Food-101\u2014mining discriminative components with random forests. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T, editors. Computer vision\u2014ECCV 2014. Cham: Springer International Publishing; 2014. p. 446\u201361."},{"key":"1870_CR4","doi-asserted-by":"crossref","unstructured":"Chen X, Lawrence Zitnick C. Mind\u2019s eye: a recurrent visual representation for image caption generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p. 2422\u201331, 2015.","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"1870_CR5","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.patrec.2020.03.003","volume":"133","author":"J Choi","year":"2020","unstructured":"Choi J, Lee SW. Improving fasttext with inverse document frequency of subwords. Pattern Recogn Lett. 2020;133:165\u201372.","journal-title":"Pattern Recogn Lett"},{"key":"1870_CR6","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. 2018."},{"issue":"6","key":"1870_CR7","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1007\/s12559-018-9581-x","volume":"11","author":"G Ding","year":"2019","unstructured":"Ding G, Chen M, Zhao S, Chen H, Han J, Liu Q. Neural image caption generation with weighted training and reference. Cogn Comput. 2019;11(6):763\u201377.","journal-title":"Cogn Comput"},{"key":"1870_CR8","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T. Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p. 2625\u201334, 2015.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1870_CR9","unstructured":"Elliott D, Keller F. Image description using visual dependency representations. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, p. 1292\u2013302, 2013."},{"key":"1870_CR10","doi-asserted-by":"crossref","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D. Every picture tells a story: generating sentences from images. In: European Conference on Computer Vision, p. 15\u201329. Springer; 2010.","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"1870_CR11","doi-asserted-by":"crossref","unstructured":"Forbes P, Zhu M. Content-boosted matrix factorization for recommender systems: experiments with recipe recommendation. In: Proceedings of the fifth ACM conference on Recommender systems, p. 261\u20134, 2011.","DOI":"10.1145\/2043932.2043979"},{"key":"1870_CR12","doi-asserted-by":"crossref","unstructured":"Freyne J, Berkovsky S. Intelligent food planning: personalized recipe recommendation. In: Proceedings of the 15th International Conference on Intelligent User Interfaces, p. 321\u201324, 2010.","DOI":"10.1145\/1719970.1720021"},{"key":"1870_CR13","doi-asserted-by":"crossref","unstructured":"Geleijnse G, Nachtigall P, van Kaam P, Wijgergangs L. A personalized recipe advice system to promote healthful choices. In: Proceedings of the 16th International Conference on Intelligent User Interfaces, p. 437\u20138, 2011.","DOI":"10.1145\/1943403.1943487"},{"key":"1870_CR14","doi-asserted-by":"crossref","unstructured":"He S, Liao W, Tavakoli HR, Yang M, Rosenhahn B, Pugeault N. Image captioning through image transformer. In: Proceedings of the Asian Conference on Computer Vision, 2020.","DOI":"10.1007\/978-3-030-69538-5_10"},{"key":"1870_CR15","doi-asserted-by":"crossref","unstructured":"Huang Z, Thint M, Qin Z. Question classification using head words and their hypernyms. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, p. 927\u201336. Honolulu: Association for Computational Linguistics; 2008. https:\/\/www.aclweb.org\/anthology\/D08-1097","DOI":"10.3115\/1613715.1613835"},{"key":"1870_CR16","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1613\/jair.5660","volume":"60","author":"D Inclezan","year":"2017","unstructured":"Inclezan D, Pradanos LI. A critical view on smart cities and AI. J Artif Intell Res. 2017;60:681\u20136.","journal-title":"J Artif Intell Res"},{"key":"1870_CR17","doi-asserted-by":"crossref","unstructured":"Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen H, Wang Y. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4).","DOI":"10.1136\/svn-2017-000101"},{"key":"1870_CR18","doi-asserted-by":"crossref","unstructured":"Joulin A, Grave E, Bojanowski P, Mikolov T. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759. 2016.","DOI":"10.18653\/v1\/E17-2068"},{"key":"1870_CR19","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, p. 3128\u201337, 2015.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1870_CR20","doi-asserted-by":"crossref","unstructured":"Khilji AFUR, Manna R, Laskar SR, Pakray P, Das D, Bandyopadhyay S, Gelbukh A. Question classification and answer extraction for developing a cooking QA system. Computaci\u00f3n y Sistemas. 2020;24(2).","DOI":"10.13053\/cys-24-2-3445"},{"key":"1870_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-020-05236-5","author":"AFUR Khilji","year":"2021","unstructured":"Khilji AFUR, Manna R, Laskar SR, Pakray P, Das D, Bandyopadhyay S, Gelbukh A. Cookingqa: answering questions and recommending recipes based on ingredients. Arab J Sci Eng. 2021. https:\/\/doi.org\/10.1007\/s13369-020-05236-5.","journal-title":"Arab J Sci Eng"},{"key":"1870_CR22","doi-asserted-by":"crossref","unstructured":"Kim D, Park C, Oh J, Lee S, Yu H. Convolutional matrix factorization for document context-aware recommendation. In: Proceedings of the 10th ACM Conference on Recommender Systems, p. 233\u201340, 2016.","DOI":"10.1145\/2959100.2959165"},{"key":"1870_CR23","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. 2017."},{"key":"1870_CR24","unstructured":"Kuznetsova P, Ordonez V, Berg A, Berg T, Choi Y. Collective generation of natural image descriptions. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, (Volume 1: Long Papers), p. 359\u201368, 2012."},{"key":"1870_CR25","unstructured":"Li S, Kulkarni G, Berg T, Berg A, Choi Y. Composing simple image descriptions using web-scale n-grams. In: Proceedings of the Fifteenth Conference on Computational Natural Language Learning, p. 220\u20138, 2011."},{"key":"1870_CR26","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A. Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv preprint arXiv:1412.6632. 2014."},{"issue":"1","key":"1870_CR27","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1109\/TPAMI.2019.2927476","volume":"43","author":"J Mar\u00edn","year":"2021","unstructured":"Mar\u00edn J, Biswas A, Ofli F, Hynes N, Salvador A, Aytar Y, Weber I, Torralba A. Recipe1m+: a dataset for learning cross-modal embeddings for cooking recipes and food images. IEEE Trans Pattern Anal Mach Intell. 2021;43(1):187\u2013203. https:\/\/doi.org\/10.1109\/TPAMI.2019.2927476.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1870_CR28","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer, A. Automatic differentiation in pytorch. 2017."},{"key":"1870_CR29","doi-asserted-by":"crossref","unstructured":"Prager Dragomir E, Brown Anni Coden VS. The use of predictive annotation for question answering in trec8. In: Proceedings of the Eighth Text Retrieval Conferences 500-264, p. 165\u201372, 1999.","DOI":"10.6028\/NIST.SP.500-246.ibm-chong"},{"key":"1870_CR30","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.","DOI":"10.1109\/CVPR.2019.01070"},{"key":"1870_CR31","doi-asserted-by":"crossref","unstructured":"Salvador A, Hynes N, Aytar Y, Marin J, Ofli F, Weber I, Torralba A. Learning cross-modal embeddings for cooking recipes and food images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p. 3020\u201328, 2017.","DOI":"10.1109\/CVPR.2017.327"},{"key":"1870_CR32","doi-asserted-by":"crossref","unstructured":"Shi H, Li P, Wang B, Wang Z. Image captioning based on deep reinforcement learning. In: Proceedings of the 10th International Conference on Internet Multimedia Computing and Service, p. 1\u20135, 2018.","DOI":"10.1145\/3240876.3240900"},{"key":"1870_CR33","doi-asserted-by":"crossref","unstructured":"Shidochi Y, Takahashi T, Ide I, Murase, H. Finding replaceable materials in cooking recipe texts considering characteristic cooking actions. In: Proceedings of the ACM Multimedia 2009 Workshop on Multimedia for Cooking and Eating Activities, p. 9\u201314, 2009.","DOI":"10.1145\/1630995.1630998"},{"key":"1870_CR34","doi-asserted-by":"crossref","unstructured":"Silva Coheur A, Mendes AW. The use of predictive annotation for question answering in trec8. From symbolic to sub-symbolic information in question classification. 2011;35:137\u2013154.","DOI":"10.1007\/s10462-010-9188-4"},{"issue":"3","key":"1870_CR35","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1145\/1096737.1096739","volume":"12","author":"M Svensson","year":"2005","unstructured":"Svensson M, H\u00f6\u00f6k K, C\u00f6ster R. Designing and evaluating kalas: a social navigation system for food recipes. ACM Trans Comput-Hum Interact (TOCHI). 2005;12(3):374\u2013400.","journal-title":"ACM Trans Comput-Hum Interact (TOCHI)"},{"key":"1870_CR36","unstructured":"Ueda M, Takahata M, Nakajima S. User\u2019s food preference extraction for personalized cooking recipe recommendation. In: Workshop of ISWC, p. 98\u2013105, 2011."},{"key":"1870_CR37","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, p. 3156\u201364, 2015.","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1870_CR38","doi-asserted-by":"crossref","unstructured":"Wang H, Sahoo D, Liu C, Lim EP, Hoi SCH. 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 (CVPR), 2019.","DOI":"10.1109\/CVPR.2019.01184"},{"issue":"2","key":"1870_CR39","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/MIM.2020.9062691","volume":"23","author":"WL Woo","year":"2020","unstructured":"Woo WL. Future trends in I&M: human\u2013machine co-creation in the rise of AI. IEEE Instrum Meas Mag. 2020;23(2):71\u20133.","journal-title":"IEEE Instrum Meas Mag"},{"key":"1870_CR40","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y. Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, p. 2048\u201357. PMLR; 2015."},{"key":"1870_CR41","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T. Exploring visual relationship for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), p. 684\u201399, 2018.","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"1870_CR42","unstructured":"Zhang Q, Hu R, Mac Namee B, Delany SJ. Back to the future: knowledge light case base cookery. In: ECCBR Workshops, p. 239\u201348, 2008."},{"key":"1870_CR43","doi-asserted-by":"crossref","unstructured":"Zheng L, Noroozi V, Yu PS. Joint deep modeling of users and items using reviews for recommendation. In: Proceedings of the tenth ACM International Conference on Web Search and Data Mining, p. 425\u201334, 2017.","DOI":"10.1145\/3018661.3018665"},{"key":"1870_CR44","doi-asserted-by":"crossref","unstructured":"Zou X, Lin C, Zhang Y, Zhao Q. To be an artist: automatic generation on food image aesthetic captioning. In: 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), p. 779\u201386. IEEE; 2020.","DOI":"10.1109\/ICTAI50040.2020.00124"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-01870-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-023-01870-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-01870-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T05:28:51Z","timestamp":1729488531000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-023-01870-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,26]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["1870"],"URL":"https:\/\/doi.org\/10.1007\/s42979-023-01870-6","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,26]]},"assertion":[{"value":"6 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"421"}}