{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:13:01Z","timestamp":1776103981530,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T00:00:00Z","timestamp":1506297600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Natural Science Foundation of China (CN)","award":["61375054"],"award-info":[{"award-number":["61375054"]}]},{"name":"Natural Science Foundation of Guangdong Province (CN)","award":["2014A030313745"],"award-info":[{"award-number":["2014A030313745"]}]},{"name":"Basic Scientific Research Program of Shenzhen City","award":["JCYJ20160331184440545"],"award-info":[{"award-number":["JCYJ20160331184440545"]}]},{"name":"Cross Fund of Graduate School at Shenzhen, Tsinghua University","award":["JC20140001"],"award-info":[{"award-number":["JC20140001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1007\/s11042-017-5236-2","type":"journal-article","created":{"date-parts":[[2017,9,25]],"date-time":"2017-09-25T02:00:48Z","timestamp":1506304848000},"page":"18583-18599","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Weakly-supervised image captioning based on rich contextual information"],"prefix":"10.1007","volume":"77","author":[{"given":"Hai-Tao","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7248-8389","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ningning","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun Kumar","family":"Sangaiah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,25]]},"reference":[{"key":"5236_CR1","unstructured":"Abadi M, Agarwal A, Barham P et al (2016) Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467"},{"key":"5236_CR2","unstructured":"Aker A, Gaizauskas R (2010) Generating image descriptions using dependency relational patterns. Proceedings of the 48th annual meeting of the association for computational linguistics. Association for Computational Linguistics, pp 1250\u20131258"},{"key":"5236_CR3","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473"},{"key":"5236_CR4","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C et al (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. In EMNLP","DOI":"10.3115\/v1\/D14-1179"},{"key":"5236_CR5","doi-asserted-by":"crossref","unstructured":"Elliott D, Keller F (2013) Image description using visual dependency representations. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing pp 1292\u20131302","DOI":"10.18653\/v1\/D13-1128"},{"key":"5236_CR6","doi-asserted-by":"crossref","unstructured":"Farhadi A, Hejrati M, Sadeghi M et al (2010) Every picture tells a story: Generating sentences from images. Computer vision\u2013ECCV pp 15\u201329","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"5236_CR7","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"5236_CR8","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Hodosh M, et al (2014) Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections. ECCV (4), pp 529\u2013545","DOI":"10.1007\/978-3-319-10593-2_35"},{"issue":"9","key":"5236_CR9","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S et al (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5236_CR10","doi-asserted-by":"crossref","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":"5236_CR11","unstructured":"Karpathy A, Joulin A, Li FFF (2014) Deep fragment embeddings for bidirectional image sentence mapping. Advances in Neural Information Processing Systems pp 1889\u20131897"},{"key":"5236_CR12","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. Proceedings of the 31st International Conference on Machine Learning (ICML-14). pp 595\u2013603"},{"key":"5236_CR13","unstructured":"Kiros R, Salakhutdinov R, Zemel RS (2014) Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539"},{"issue":"12","key":"5236_CR14","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni G, Premraj V, Ordonez V et al (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":"5236_CR15","unstructured":"Kuznetsova P, Ordonez V, Berg AC et al (2012) Collective generation of natural image descriptions. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1. Association for Computational Linguistics, pp 359\u2013368"},{"issue":"10","key":"5236_CR16","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 et al (2014) TREETALK: Composition and Compression of Trees for Image Descriptions. TACL 2(10):351\u2013362","journal-title":"TACL"},{"key":"5236_CR17","unstructured":"Li S, Kulkarni G, Berg TL et al (2011) Composing simple image descriptions using web-scale n-grams. Proceedings of the Fifteenth Conference on Computational Natural Language Learning. Association for Computational Linguistics, pp 220\u2013228"},{"key":"5236_CR18","doi-asserted-by":"crossref","unstructured":"Lin T Y, Maire M, Belongie S et al (2014) Microsoft coco: Common objects in context. arXiv preprint arXiv:1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5236_CR19","unstructured":"Mao J, Xu W, Yang Y et al (2014) Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv preprint arXiv:1412.6632"},{"key":"5236_CR20","unstructured":"Mitchell M, Han X, Dodge J et al (2012) Midge: Generating image descriptions from computer vision detections. Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, pp 747\u2013756"},{"key":"5236_CR21","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2text: Describing images using 1 million captioned photographs. In: Advances in Neural Information Processing Systems, pp 1143\u20131151"},{"key":"5236_CR22","unstructured":"Papineni K, Roukos S, Ward T et al (2002) BLEU: a method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, pp 311\u2013318"},{"issue":"6","key":"5236_CR23","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R et al (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":"5236_CR24","unstructured":"Russakovsky O, Deng J, Su H et al (2014) Imagenet large scale visual recognition challenge. arXiv preprint arXiv:1409.0575"},{"key":"5236_CR25","doi-asserted-by":"crossref","unstructured":"Shi J, Wu J, Paul A et al (2014) Change Detection in Synthetic Aperture Radar Images Based on Fuzzy Active Contour Models and Genetic Algorithms. Mathematical Problems in Engineering, 2014","DOI":"10.1155\/2014\/870936"},{"key":"5236_CR26","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 et al (2014) Grounded compositional semantics for finding and describing images with sentences. Transactions of the Association for Computational Linguistics 2:207\u2013218","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"5236_CR27","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. Advances in neural information processing systems, pp 3104\u20133112"},{"key":"5236_CR28","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S et al (2015) Show and tell: A neural image caption generator. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"10","key":"5236_CR29","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1016\/j.image.2010.10.003","volume":"25","author":"J Wu","year":"2010","unstructured":"Wu J, Paul A, Xing Y et al (2010) Morphological dilation image coding with context weights prediction. Signal Process Image Commun 25(10):717\u2013728","journal-title":"Signal Process Image Commun"},{"key":"5236_CR30","unstructured":"Xu K, Ba J, Kiros R et al (2015) Show, attend and tell: Neural image caption generation with visual attention. International Conference on Machine Learning, pp 2048\u20132057"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-5236-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-5236-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-5236-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T21:50:51Z","timestamp":1750888251000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-5236-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,25]]},"references-count":30,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["5236"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-5236-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,25]]}}}