{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T00:47:39Z","timestamp":1770511659705,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T00:00:00Z","timestamp":1585180800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T00:00:00Z","timestamp":1585180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61751209"],"award-info":[{"award-number":["61751209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11042-020-08832-7","type":"journal-article","created":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T18:04:20Z","timestamp":1585245860000},"page":"16267-16282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Tell and guess: cooperative learning for natural image caption generation with hierarchical refined attention"],"prefix":"10.1007","volume":"80","author":[{"given":"Wenqiao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajie","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,26]]},"reference":[{"issue":"11","key":"8832_CR1","doi-asserted-by":"publisher","first-page":"1949","DOI":"10.1109\/TMM.2015.2477680","volume":"17","author":"AH Abdulnabi","year":"2015","unstructured":"Abdulnabi AH, Wang G, Lu J, Jia K (2015) Multi-task cnn model for attribute prediction. IEEE Transactions on Multimedia 17(11):1949\u20131959","journal-title":"IEEE Transactions on Multimedia"},{"key":"8832_CR2","doi-asserted-by":"crossref","unstructured":"Alahmadi R, Park CH, Hahn J (2019) Sequence-to-sequence image caption generator Eleventh international conference on machine vision (ICMV 2018), vol. 11041, p. 110410c. International society for optics and photonics","DOI":"10.1117\/12.2523174"},{"key":"8832_CR3","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8832_CR4","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"},{"issue":"3","key":"8832_CR5","doi-asserted-by":"publisher","first-page":"2959","DOI":"10.1007\/s11042-017-4593-1","volume":"77","author":"YS Chang","year":"2018","unstructured":"Chang YS (2018) Fine-grained attention for image caption generation. Multimedia Tools and Applications 77(3):2959\u20132971","journal-title":"Multimedia Tools and Applications"},{"key":"8832_CR6","doi-asserted-by":"crossref","unstructured":"Chao YW, Vijayanarasimhan S, Seybold B, Ross DA, Deng J, Sukthankar R (2018) Rethinking the faster r-cnn architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130\u20131139","DOI":"10.1109\/CVPR.2018.00124"},{"key":"8832_CR7","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 preprint. arXiv:1504.00325"},{"key":"8832_CR8","doi-asserted-by":"crossref","unstructured":"Chen H, Ding G, Lin Z, Zhao S, Han J (2018) Show, observe and tell: Attribute-driven attention model for image captioning. In: IJCAI, pp. 606\u2013612","DOI":"10.24963\/ijcai.2018\/84"},{"key":"8832_CR9","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint. arXiv:1412.3555"},{"key":"8832_CR10","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":"8832_CR11","doi-asserted-by":"crossref","unstructured":"Gao J, Ge R, Chen K, Nevatia R (2018) Motion-appearance co-memory networks for video question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6576\u20136585","DOI":"10.1109\/CVPR.2018.00688"},{"key":"8832_CR12","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"},{"issue":"8","key":"8832_CR13","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 (1997) Long short-term memory. Neural computation 9(8):1735\u20131780","journal-title":"Neural computation"},{"key":"8832_CR14","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint . arXiv:1502.03167"},{"key":"8832_CR15","unstructured":"Jacobsen JH, Oyallon E, Mallat S, Smeulders AW (2017) Hierarchical attribute cnns. In: ICML Workshop on principled approaches to deep learning"},{"key":"8832_CR16","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1016\/j.neucom.2017.07.014","volume":"272","author":"P Kinghorn","year":"2018","unstructured":"Kinghorn P, Zhang L, Shao L (2018) A region-based image caption generator with refined descriptions. Neurocomputing 272:416\u2013424","journal-title":"Neurocomputing"},{"issue":"11","key":"8832_CR17","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P, et al. (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"8832_CR18","doi-asserted-by":"crossref","unstructured":"Li L, Tang S, Deng L, Zhang Y, Tian Q (2017) Image caption with global-local attention. In: Thirty-first AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11236"},{"key":"8832_CR19","doi-asserted-by":"crossref","unstructured":"Li Q, Fu J, Yu D, Mei T, Luo J (2018) Tell-and-answer: Towards explainable visual question answering using attributes and captions. arXiv preprint. arXiv:1801.09041","DOI":"10.18653\/v1\/D18-1164"},{"key":"8832_CR20","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"8832_CR21","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, pp. 311\u2013318. Association for Computational Linguistics","DOI":"10.3115\/1073083.1073135"},{"key":"8832_CR22","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"8832_CR23","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp. 91\u201399"},{"key":"8832_CR24","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint . arXiv:1409.1556"},{"key":"8832_CR25","unstructured":"Smith JR, Saint-Amand H, Plamada M, Koehn P, Callison-Burch C, Lopez A (2013) Dirt cheap web-scale parallel text from the common crawl. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 1374\u20131383"},{"key":"8832_CR26","unstructured":"Sutskever I, Hinton GE, Krizhevsky A (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, pp. 1097\u20131105"},{"key":"8832_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8832_CR28","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015) Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"8832_CR29","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"},{"issue":"2","key":"8832_CR30","doi-asserted-by":"publisher","first-page":"646","DOI":"10.3390\/s18020646","volume":"18","author":"L Wang","year":"2018","unstructured":"Wang L, Chu X, Zhang W, Wei Y, Sun W, Wu C (2018) Social image captioning: Exploring visual attention and user attention. Sensors 18(2):646","journal-title":"Sensors"},{"issue":"10","key":"8832_CR31","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2018","unstructured":"Wang P, Wu Q, Shen C, Dick A, van den Hengel A (2018) Fvqa: Fact-based visual question answering. IEEE transactions on pattern analysis and machine intelligence 40(10):2413\u20132427","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"8832_CR32","doi-asserted-by":"crossref","unstructured":"Wang W, Ding Y, Tian C (2018) A novel semantic attribute-based feature for image caption generation. In: 2018 IEEE International conference on acoustics, speech and signal processing (ICASSP), pp. 3081\u20133085. IEEE","DOI":"10.1109\/ICASSP.2018.8461507"},{"issue":"6","key":"8832_CR33","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2018","unstructured":"Wu Q, Shen C, Wang P, Dick A, van den Hengel A (2018) Image captioning and visual question answering based on attributes and external knowledge. IEEE transactions on pattern analysis and machine intelligence 40(6):1367\u20131381","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"8832_CR34","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov 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"},{"key":"8832_CR35","doi-asserted-by":"crossref","unstructured":"Yang Z, He X, Gao J, Deng L, Smola A (2016) Stacked attention networks for image question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 21\u201329","DOI":"10.1109\/CVPR.2016.10"},{"key":"8832_CR36","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Qiu Z, Mei T (2017) Boosting image captioning with attributes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4894\u20134902","DOI":"10.1109\/ICCV.2017.524"},{"key":"8832_CR37","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"8832_CR38","doi-asserted-by":"crossref","unstructured":"Yu H, Cheng S, Ni B, Wang M, Zhang J, Yang X (2018) Fine-grained video captioning for sports narrative. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6006\u20136015","DOI":"10.1109\/CVPR.2018.00629"},{"key":"8832_CR39","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision, pp. 818\u2013833. Springer","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"8832_CR40","first-page":"718","volume":"5","author":"ML Zhang","year":"2005","unstructured":"Zhang ML, Zhou ZH (2005) A k-nearest neighbor based algorithm for multi-label classification. GrC 5:718\u2013721","journal-title":"GrC"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08832-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-08832-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08832-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T20:36:08Z","timestamp":1666211768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-08832-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,26]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["8832"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-08832-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,26]]},"assertion":[{"value":"4 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}