{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:25:55Z","timestamp":1740122755582,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,4,26]],"date-time":"2019-04-26T00:00:00Z","timestamp":1556236800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673402"],"award-info":[{"award-number":["61673402"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s11063-019-10045-5","type":"journal-article","created":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T05:50:20Z","timestamp":1556344220000},"page":"549-564","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Adaptive Syncretic Attention for Constrained Image Captioning"],"prefix":"10.1007","volume":"50","author":[{"given":"Liang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,26]]},"reference":[{"key":"10045_CR1","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2014) Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv:1412.6632"},{"key":"10045_CR2","unstructured":"Kiros R, Salakhutdinov R, Zemel RS (2014) Unifying visual-semantic embeddings with multimodal neural language models. arXiv:1411.2539"},{"key":"10045_CR3","doi-asserted-by":"crossref","unstructured":"Karpathy A, Li FF (2015) Deep visual-semantic alignments for generating image descriptions. In: Computer vision and pattern recognition, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"10045_CR4","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"10045_CR5","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Darrell T, Saenko K (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Computer vision and pattern recognition, p 677","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10045_CR6","doi-asserted-by":"crossref","unstructured":"Fang H, Gupta S, Iandola F, Srivastava RK, Deng L, Doll\u00e1r P, Gao J, He X, Mitchell M, Platt JC et al (2015) From captions to visual concepts and back. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1473\u20131482","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"10045_CR7","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, pp 2048\u20132057"},{"issue":"12","key":"10045_CR8","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TPAMI.2016.2642953","volume":"39","author":"K Fu","year":"2017","unstructured":"Fu K, Jin J, Cui R, Sha F, Zhang C (2017) Aligning where to see and what to tell: image captioning with region-based attention and scene-specific contexts. IEEE Trans Pattern Anal Mach Intell 39(12):2321\u20132334","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10045_CR9","doi-asserted-by":"crossref","unstructured":"Peng KC, Chen T, Sadovnik A, Gallagher A (2015) A mixed bag of emotions: model, predict, and transfer emotion distributions. In: Computer vision and pattern recognition, pp 860\u2013868","DOI":"10.1109\/CVPR.2015.7298687"},{"key":"10045_CR10","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.ins.2015.03.032","volume":"320","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, You J, Chen X, Tao D (2015) Multi-view ensemble manifold regularization for 3D object recognition. Inf Sci 320:395\u2013405","journal-title":"Inf Sci"},{"issue":"6","key":"10045_CR11","first-page":"3742","volume":"62","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Tao D, Wang M (2015) Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. IEEE Trans Ind Electron 62(6):3742\u20133751","journal-title":"IEEE Trans Ind Electron"},{"issue":"7","key":"10045_CR12","doi-asserted-by":"publisher","first-page":"2676","DOI":"10.1109\/TIP.2013.2255302","volume":"22","author":"W Liu","year":"2013","unstructured":"Liu W, Tao D (2013) Multiview Hessian regularization for image annotation. IEEE Trans Image Process 22(7):2676\u20132687","journal-title":"IEEE Trans Image Process"},{"key":"10045_CR13","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.inffus.2017.09.001","volume":"41","author":"W Liu","year":"2018","unstructured":"Liu W, Yang X, Tao D, Cheng J, Tang Y (2018) Multiview dimension reduction via Hessian multiset canonical correlations. Inf Fusion 41:119\u2013128","journal-title":"Inf Fusion"},{"issue":"4","key":"10045_CR14","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TCYB.2014.2336697","volume":"45","author":"J Yu","year":"2015","unstructured":"Yu J, Tao D, Wang M, Rui Y (2015) Learning to rank using user clicks and visual features for image retrieval. IEEE Trans Cybern 45(4):767\u2013779","journal-title":"IEEE Trans Cybern"},{"key":"10045_CR15","doi-asserted-by":"crossref","unstructured":"Chaudhuri K, Kakade SM, Livescu K, Sridharan K (2009) Multi-view clustering via canonical correlation analysis. In: Proceedings of the 26th annual international conference on machine learning. ACM, pp 129\u2013136","DOI":"10.1145\/1553374.1553391"},{"issue":"5","key":"10045_CR16","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1109\/TIP.2014.2311377","volume":"23","author":"J Yu","year":"2014","unstructured":"Yu J, Rui Y, Tao D (2014) Click prediction for web image reranking using multimodal sparse coding. IEEE Trans Image Process 23(5):2019\u20132032","journal-title":"IEEE Trans Image Process"},{"issue":"12","key":"10045_CR17","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659\u20135670","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"10045_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10045_CR19","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2:67\u201378","journal-title":"Trans Assoc Comput Linguist"},{"key":"10045_CR20","unstructured":"Chen X, Fang H, Lin TY, Vedantam R, Gupta S, Doll\u00e1r P, Zitnick CL (2015) Microsoft COCO captions: data collection and evaluation server. arXiv:1504.00325"},{"key":"10045_CR21","first-page":"790","volume":"2","author":"P Kuznetsova","year":"2013","unstructured":"Kuznetsova P, Ordonez V, Berg A, Berg T, Choi Y (2013) Generalizing image captions for image-text parallel corpus. Assoc Comput Linguist (ACL) 2:790\u2013796","journal-title":"Assoc Comput Linguist (ACL)"},{"key":"10045_CR22","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1162\/tacl_a_00188","volume":"2","author":"P Kuznetsova","year":"2014","unstructured":"Kuznetsova P, Ordonez V, Berg TL, Choi Y (2014) Treetalk: composition and compression of trees for image descriptions. TACL 2:351\u2013362","journal-title":"TACL"},{"issue":"12","key":"10045_CR23","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni G, Premraj V, Ordonez V, Dhar S, Li S, Choi Y, Berg AC, Berg TL (2013) Babytalk: understanding and generating simple image descriptions. IEEE Trans Pattern Anal Mach Intell 35(12):2891\u20132903","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10045_CR24","unstructured":"Yang Y, Teo CL, Daum\u00e9\u00a0III H, Aloimonos Y (2011) Corpus-guided sentence generation of natural images. In: Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics, pp 444\u2013454"},{"key":"10045_CR25","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"10045_CR26","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv:1409.0473"},{"key":"10045_CR27","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. In: International conference on machine learning, pp 595\u2013603"},{"key":"10045_CR28","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.503"},{"key":"10045_CR29","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-critical sequence training for image captioning. In: IEEE conference on computer vision and pattern recognition, pp 1179\u20131195","DOI":"10.1109\/CVPR.2017.131"},{"key":"10045_CR30","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10045_CR31","unstructured":"Tan M, Santos CD, Xiang B, Zhou B (2015) Lstm-based deep learning models for non-factoid answer selection. arXiv:1511.04108"},{"key":"10045_CR32","doi-asserted-by":"crossref","unstructured":"Wang B, Liu K, Zhao J (2016) Inner attention based recurrent neural networks for answer selection. In: Proceedings of the 54th annual meeting of the association for computational linguistics, vol 1, pp 1288\u20131297","DOI":"10.18653\/v1\/P16-1122"},{"key":"10045_CR33","doi-asserted-by":"crossref","unstructured":"Wang D, Nyberg E (2015) A long short-term memory model for answer sentence selection in question answering. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing, vol 2, pp 707\u2013712","DOI":"10.3115\/v1\/P15-2116"},{"key":"10045_CR34","unstructured":"LeCun Y, Bottou L, Orr G, Muller K (1998) Efficient backprop in neural networks: tricks of the trade. In: Orr G, M\u00fcller K (eds) Lecture notes in computer science, vol 1524(98), p 111"},{"key":"10045_CR35","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, ACL \u201902. Association for Computational Linguistics, Stroudsburg, pp 311\u2013318"},{"key":"10045_CR36","unstructured":"Banerjee S, Lavie A (2005) Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, pp 65\u201372"},{"key":"10045_CR37","unstructured":"Lin C-Y (2004) Rouge: a package for automatic evaluation of summaries. In: Marie-Francine Moens SS (ed) Text summarization branches out: proceedings of the ACL-04 workshop. Association for Computational Linguistics, Barcelona, pp 74\u201381"},{"key":"10045_CR38","doi-asserted-by":"crossref","unstructured":"Vedantam R, Zitnick CL, Parikh D (2015) Cider: consensus-based image description evaluation. In: Computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10045_CR39","doi-asserted-by":"crossref","unstructured":"Lavie A, Agarwal A (2007) Meteor: an automatic metric for MT evaluation with high levels of correlation with human judgments. In: Proceedings of the second workshop on statistical machine translation. Association for Computational Linguistics, pp 228\u2013231","DOI":"10.3115\/1626355.1626389"},{"key":"10045_CR40","doi-asserted-by":"crossref","unstructured":"Jia X, Gavves E, Fernando B, Tuytelaars T (2015) Guiding the long-short term memory model for image caption generation. In: Proceedings of the IEEE international conference on computer vision, pp 2407\u20132415","DOI":"10.1109\/ICCV.2015.277"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10045-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-019-10045-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10045-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,8]],"date-time":"2020-12-08T06:12:57Z","timestamp":1607407977000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-019-10045-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,26]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["10045"],"URL":"https:\/\/doi.org\/10.1007\/s11063-019-10045-5","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2019,4,26]]},"assertion":[{"value":"26 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}