{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T05:04:16Z","timestamp":1664168656799},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T00:00:00Z","timestamp":1652400000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T00:00:00Z","timestamp":1652400000000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s00530-022-00933-7","type":"journal-article","created":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T08:03:59Z","timestamp":1652429039000},"page":"1767-1777","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Double-scale similarity with rich features for cross-modal retrieval"],"prefix":"10.1007","volume":"28","author":[{"given":"Kaiqiang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hufei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dexin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,13]]},"reference":[{"key":"933_CR1","first-page":"5797","volume-title":"Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned","author":"E Voita","year":"2019","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned, pp. 5797\u20135808. Association for Computational Linguistics, Stroudsburg (2019)"},{"key":"933_CR2","unstructured":"Staudemeyer, R.\u00a0C. & Morris, E.\u00a0R.: Understanding lstm: A tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586 (2019)"},{"key":"933_CR3","first-page":"2088","volume-title":"Learning fragment self-attention embeddings for image-text matching","author":"Y Wu","year":"2019","unstructured":"Wu, Y., Wang, S., Song, G., Huang, Q.: Learning fragment self-attention embeddings for image-text matching, pp. 2088\u20132096. ACM, New York (2019)"},{"issue":"1","key":"933_CR4","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1002\/asi.24373","volume":"72","author":"W Li","year":"2021","unstructured":"Li, W., et al.: Cross-modal retrieval with dual multi-angle self-attention. J. Assoc. Inf. Sci. Technol. 72(1), 46\u201365 (2021)","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"933_CR5","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1109\/TPAMI.2019.2927476","volume":"43","author":"J Marin","year":"2021","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, 187\u2013203 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"933_CR6","first-page":"35","volume-title":"Cross-modal retrieval in the cooking context: Learning semantic text-image embeddings","author":"M Carvalho","year":"2018","unstructured":"Carvalho, M., et al.: Cross-modal retrieval in the cooking context: Learning semantic text-image embeddings, pp. 35\u201344. ACM, London (2018)"},{"key":"933_CR7","unstructured":"Thompson, B.: Canonical correlation analysis. American psychological association 6(2), (2000)"},{"key":"933_CR8","volume-title":"Kernel canonical correlation analysis","author":"T Melzer","year":"2001","unstructured":"Melzer, T., Reiter, M., Bischof, H.: Kernel canonical correlation analysis. John Wiley, New Jersey (2001)"},{"key":"933_CR9","unstructured":"Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: International conference on machine learning, pp. 1247\u20131255 (2013)"},{"key":"933_CR10","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: CAMP: Cross-modal adaptive message passing for text-image retrieval. In: IEEE, pp. 5763\u20135772 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"933_CR11","doi-asserted-by":"crossref","unstructured":"Park, G., Han, C., Yoon, W., Kim, D.: MHSAN: Multi-head self-attention network for visual semantic embedding. In: IEEE, pp. 1507\u20131515 (2020)","DOI":"10.1109\/WACV45572.2020.9093548"},{"key":"933_CR12","doi-asserted-by":"crossref","unstructured":"Zhen, L., Hu, P., Wang, X., Peng, D.: Deep supervised cross-modal retrieval. In: Computer Vision Foundation\/IEEE, pp. 10394\u201310403 (2019)","DOI":"10.1109\/CVPR.2019.01064"},{"key":"933_CR13","unstructured":"Khojasteh, H.\u00a0A., Ansari, E., Razzaghi, P., Karimi, A.: Deep multimodal image-text embeddings for automatic cross-media retrieval. arXiv preprint arXiv:2002.10016 (2020)"},{"key":"933_CR14","doi-asserted-by":"publisher","first-page":"2354","DOI":"10.1109\/TMM.2019.2957948","volume":"22","author":"X Fu","year":"2020","unstructured":"Fu, X., Zhao, Y., Wei, Y., Zhao, Y., Wei, S.: Rich features embedding for cross-modal retrieval: A simple baseline. IEEE Trans. Multimed. 22, 2354\u20132365 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"933_CR15","first-page":"1461","volume-title":"Multi-head attention with diversity for learning grounded multilingual multimodal representations","author":"P Huang","year":"2019","unstructured":"Huang, P., Chang, X., Hauptmann, A.G.: Multi-head attention with diversity for learning grounded multilingual multimodal representations, pp. 1461\u20131467. Association for Computational Linguistics, Stroudsburg (2019)"},{"key":"933_CR16","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/TPAMI.2015.2435740","volume":"38","author":"M Kan","year":"2016","unstructured":"Kan, M., Shan, S., Zhang, H., Lao, S., Chen, X.: Multi-view discriminant analysis. IEEE Trans. Pattern Anal. Mach. Intell. 38, 188\u2013194 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"933_CR17","first-page":"707","volume-title":"Deep cross-modal projection learning for image-text matching","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching, pp. 707\u2013723. Springer, Berlin (2018)"},{"key":"933_CR18","doi-asserted-by":"publisher","first-page":"21847","DOI":"10.1109\/ACCESS.2020.2969808","volume":"8","author":"Z Li","year":"2020","unstructured":"Li, Z., Ling, F., Zhang, C., Ma, H.: Combining global and local similarity for cross-media retrieval. IEEE Access 8, 21847\u201321856 (2020)","journal-title":"IEEE Access"},{"key":"933_CR19","first-page":"770","volume-title":"Deep residual learning for image recognition","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, pp. 770\u2013778. IEEE Computer Society, Washington (2016)"},{"key":"933_CR20","first-page":"248","volume-title":"Imagenet:A large-scale hierarchical image database","author":"J Deng","year":"2009","unstructured":"Deng, J., et al.: Imagenet:A large-scale hierarchical image database, pp. 248\u2013255. IEEE Computer Society, Washington (2009)"},{"key":"933_CR21","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.\u00a0D.: Glove: Global vectors for word representation. In: ACL, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"933_CR22","doi-asserted-by":"crossref","unstructured":"Cho, K., et\u00a0al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: ACL, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"933_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"933_CR24","unstructured":"Van Der\u00a0Westhuizen, J., Lasenby, J.: The unreasonable effectiveness of the forget gate. arXiv preprint arXiv:1804.04849 (2018)"},{"key":"933_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C. , Wang, L.: Learning semantic concepts and order for image and sentence matching. In: Computer Vision Foundation\/IEEE Computer Society, pp. 6163\u20136171 (2018)","DOI":"10.1109\/CVPR.2018.00645"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00933-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-022-00933-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00933-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T12:28:44Z","timestamp":1664108924000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-022-00933-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,13]]},"references-count":25,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["933"],"URL":"https:\/\/doi.org\/10.1007\/s00530-022-00933-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,13]]},"assertion":[{"value":"7 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2022","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 certify that there is no conflict of interest with any individual\/organization for the present work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}