{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:24:50Z","timestamp":1760171090380,"version":"3.41.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s13735-018-0158-y","type":"journal-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T14:47:51Z","timestamp":1532011671000},"page":"147-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Improvement of image description using bidirectional LSTM"],"prefix":"10.1007","volume":"7","author":[{"given":"Vahid","family":"Chahkandi","sequence":"first","affiliation":[]},{"given":"Mohammad Javad","family":"Fadaeieslam","sequence":"additional","affiliation":[]},{"given":"Farzin","family":"Yaghmaee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"158_CR1","doi-asserted-by":"crossref","unstructured":"Coyne B, Sproat R (2001) Wordseye: an automatic text-to-scene conversion system. In: SIGGRAPH\u201901","DOI":"10.1145\/383259.383316"},{"key":"158_CR2","doi-asserted-by":"crossref","unstructured":"Das P, Xu C, Doell RF, Corso JJ (2013) A thousand frames in just a few words: lingual description of videos through latent topic and sparse object stitching. In: CVPR","DOI":"10.1109\/CVPR.2013.340"},{"key":"158_CR3","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy N, Malkarnenkar G, Mooney RJ, Saenko K, Guadarrama S (2013) Generating natural-language video descriptions using text-mined knowledge. In: AAAI, vol 1","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"158_CR4","unstructured":"Karpathy A, Joulin A, Li F-F (2014) Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in neural information processing systems"},{"key":"158_CR5","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems"},{"key":"158_CR6","unstructured":"Wang C, Yang H, Bartz C, Meinel C (2016) Image captioning with deep bidirectional LSTMs. In: Proceedings of the 2016 ACM on multimedia conference. ACM, Oct 2016, pp 988\u2013997"},{"key":"158_CR7","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1613\/jair.4900","volume":"55","author":"R Bernardi","year":"2016","unstructured":"Bernardi R, Cakici R, Elliott D, Erdem A, Erdem E, Cinbis NI, Keller F, Muscat A, Plank B (2016) Automatic description generation from images: a survey of models, datasets, and evaluation measures. J Artif Intell Res (JAIR) 55:409\u2013442","journal-title":"J Artif Intell Res (JAIR)"},{"key":"158_CR8","unstructured":"Mitchell M, Han X, Dodge J, Mensch A, Goyal A, Berg A, Yamaguchi K, Berg T, Stratos K, Daum\u00e9 H III (2012) Midge: generating image descriptions from computer vision detections. In: Proceedings of the 13th conference of the European chapter of the association for computational linguistics. Association for computational linguistics"},{"key":"158_CR9","doi-asserted-by":"crossref","unstructured":"Kuznetsova P, Ordonez V, Berg TL, Choi Y (2014) TREETALK: composition and compression of trees for image descriptions. In: Conference on empirical methods in natural language processing","DOI":"10.1162\/tacl_a_00188"},{"key":"158_CR10","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2015) Deep captioning with multimodal recurrent neural networks (m-RNN). In: International conference on learning representations"},{"key":"158_CR11","doi-asserted-by":"crossref","unstructured":"Elliott D, Keller F (2013) Image description using visual dependency representations. In: Proceedings of the 2013 conference on empirical methods in natural language processing","DOI":"10.18653\/v1\/D13-1128"},{"issue":"12","key":"158_CR12","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":"158_CR13","unstructured":"Li S, Kulkarni G, Berg TL, Berg AC, Choi Y (2011) Composing simple image descriptions using web-scale n-grams. In: Proceedings of the fifteenth conference on computational natural language learning. Association for computational linguistics"},{"key":"158_CR14","unstructured":"Yang Y, Teo CL, Daum\u00e9 H III 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"},{"key":"158_CR15","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2text: describing images using 1 million captioned photographs. In: Advances in neural information processing systems"},{"key":"158_CR16","unstructured":"Kuznetsova P, Ordonez V, Berg AC, Berg TL, Choi Y (2012) Collective generation of natural image descriptions. In: Proceedings of the 50th annual meeting of the association for computational linguistics: long papers, vol 1. Association for computational linguistics"},{"issue":"1\u20132","key":"158_CR17","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s11263-013-0695-z","volume":"108","author":"G Patterson","year":"2014","unstructured":"Patterson G, Xu C, Su H, Hays J (2014) The sun attribute database: beyond categories for deeper scene understanding. Int J Comput Vis 108(1\u20132):59\u201381","journal-title":"Int J Comput Vis"},{"key":"158_CR18","unstructured":"Gupta A, Verma Y, Jawahar CV (2012) Choosing linguistics over vision to describe images. In: AAAI"},{"key":"158_CR19","doi-asserted-by":"crossref","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences for images. In: ECCV","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"158_CR20","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Intell Res 47:853\u2013899","journal-title":"J Artif Intell Res"},{"key":"158_CR21","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher R, Karpathy A, Le QV, Manning CD, Ng AY (2014) Grounded compositional semantics for finding and describing images with sentences. Trans Assoc Comput Linguist 2:207\u2013218","journal-title":"Trans Assoc Comput Linguist"},{"key":"158_CR22","doi-asserted-by":"crossref","unstructured":"Karpathy A, Li F-F (2015) Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"158_CR23","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"158_CR24","unstructured":"Xu K, Ba J, Kiros R, Courville A, Salakhutdinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: ICML"},{"key":"158_CR25","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: CVPR, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"158_CR26","doi-asserted-by":"crossref","unstructured":"Chen X, Zitnick CL (2015) Mind\u2019s eye: a recurrent visual representation for image caption generation. In: CVPR, pp 2422\u20132431","DOI":"10.1109\/CVPR.2015.7298856"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13735-018-0158-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-018-0158-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-018-0158-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T22:12:27Z","timestamp":1751753547000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13735-018-0158-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["158"],"URL":"https:\/\/doi.org\/10.1007\/s13735-018-0158-y","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"type":"print","value":"2192-6611"},{"type":"electronic","value":"2192-662X"}],"subject":[],"published":{"date-parts":[[2018,7,19]]},"assertion":[{"value":"11 December 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}