{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:25:12Z","timestamp":1786980312007,"version":"build-2736575974"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T00:00:00Z","timestamp":1621296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T00:00:00Z","timestamp":1621296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["108-2221-E-011-116"],"award-info":[{"award-number":["108-2221-E-011-116"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s00530-021-00804-7","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T05:23:44Z","timestamp":1622784224000},"page":"121-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Code generation from a graphical user interface via attention-based encoder\u2013decoder model"],"prefix":"10.1007","volume":"28","author":[{"given":"Wen-Yin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavol","family":"Podstreleny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung-Yao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7735-243X","authenticated-orcid":false,"given":"Kai-Lung","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,18]]},"reference":[{"key":"804_CR1","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. CoRR arXiv:1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"804_CR2","doi-asserted-by":"crossref","unstructured":"Beltramelli, T.: pix2code: Generating code from a graphical user interface screenshot. CoRR arxiv:1705.07962 (2017)","DOI":"10.1145\/3220134.3220135"},{"key":"804_CR3","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A.C., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. CoRR arXiv:1502.03044 (2015)"},{"key":"804_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, Q., Shu, K.: Improving pix2code based bi-directional lstm. 2018 IEEE international conference on automation, electronics and electrical engineering (AUTEEE) p. 220\u2013223 (2018)","DOI":"10.1109\/AUTEEE.2018.8720784"},{"key":"804_CR5","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xue, Z., Yuan, Z.: Automatic graphics program generation using attention-based hierarchical decoder. CoRR arXiv:1810.11536 (2018)","DOI":"10.1007\/978-3-030-20876-9_12"},{"key":"804_CR6","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014)"},{"key":"804_CR7","doi-asserted-by":"crossref","unstructured":"Tang, H.L., Chien, S.C., Cheng, W.H., Chen, Y.Y., Hua, K.L.: Multi-cue pedestrian detection from 3d point cloud data. In: 2017 IEEE international conference on multimedia and expo (ICME), pp. 1279\u20131284. IEEE (2017)","DOI":"10.1109\/ICME.2017.8019455"},{"key":"804_CR8","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.jvcir.2016.03.004","volume":"38","author":"KL Hua","year":"2016","unstructured":"Hua, K.L., Hidayati, S.C., He, F.L., Wei, C.P., Wang, Y.C.F.: Context-aware joint dictionary learning for color image demosaicking. J. Vis. Commun. Image Represent. 38, 230\u2013245 (2016)","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"5","key":"804_CR9","doi-asserted-by":"publisher","first-page":"2408","DOI":"10.1109\/TIP.2018.2803341","volume":"27","author":"DS Tan","year":"2018","unstructured":"Tan, D.S., Chen, W.Y., Hua, K.L.: Deepdemosaicking: adaptive image demosaicking via multiple deep fully convolutional networks. IEEE Trans. Image Process. 27(5), 2408\u20132419 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"804_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2015.12.006","volume":"73","author":"J Sanchez-Riera","year":"2016","unstructured":"Sanchez-Riera, J., Hua, K.L., Hsiao, Y.S., Lim, T., Hidayati, S.C., Cheng, W.H.: A comparative study of data fusion for rgb-d based visual recognition. Pattern Recogn. Lett. 73, 1\u20136 (2016)","journal-title":"Pattern Recogn. Lett."},{"key":"804_CR11","doi-asserted-by":"crossref","unstructured":"Hidayati, S.C., Hua, K.L., Cheng, W.H., Sun, S.W.: What are the fashion trends in new york? In: Proceedings of the 22nd ACM international conference on multimedia, pp. 197\u2013200 (2014)","DOI":"10.1145\/2647868.2656405"},{"key":"804_CR12","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.jnca.2016.12.012","volume":"85","author":"V Sharma","year":"2017","unstructured":"Sharma, V., Srinivasan, K., Chao, H.C., Hua, K.L., Cheng, W.H.: Intelligent deployment of uavs in 5g heterogeneous communication environment for improved coverage. J. Netw. Comput. Appl. 85, 94\u2013105 (2017)","journal-title":"J. Netw. Comput. Appl."},{"key":"804_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., Zitnick, C.L.: Learning a recurrent visual representation for image caption generation. CoRR arXiv:1411.5654 (2014)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"804_CR14","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-rnn) (2015)"},{"key":"804_CR15","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Chua, T.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. CoRR arxiv:1611.05594 (2016)","DOI":"10.1109\/CVPR.2017.667"},{"key":"804_CR16","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via A visual sentinel for image captioning. CoRR arXiv:1612.01887 (2016)","DOI":"10.1109\/CVPR.2017.345"},{"issue":"8","key":"804_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"804_CR18","unstructured":"Ba, L.J., Kiros, J.R., Hinton, G.E.: Layer normalization. CoRR arxiv:1607.06450 (2016)"},{"key":"804_CR19","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., G\u00fcl\u00e7ehre, \u00c7., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"804_CR20","doi-asserted-by":"crossref","unstructured":"Luong, M., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. CoRR arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"804_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"804_CR22","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F.: Imagenet large scale visual recognition challenge. CoRR arXiv:1409.0575 (2014)","DOI":"10.1007\/s11263-015-0816-y"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00804-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00804-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00804-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T02:31:47Z","timestamp":1725157907000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00804-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,18]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["804"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00804-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,18]]},"assertion":[{"value":"9 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}