{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:26:45Z","timestamp":1758274005628,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"17-18","license":[{"start":{"date-parts":[[2020,1,6]],"date-time":"2020-01-06T00:00:00Z","timestamp":1578268800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,6]],"date-time":"2020-01-06T00:00:00Z","timestamp":1578268800000},"content-version":"vor","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":["61806213"],"award-info":[{"award-number":["61806213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s11042-019-08567-0","type":"journal-article","created":{"date-parts":[[2020,1,6]],"date-time":"2020-01-06T12:02:43Z","timestamp":1578312163000},"page":"11531-11549","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["GateCap: Gated spatial and semantic attention model for image captioning"],"prefix":"10.1007","volume":"79","author":[{"given":"Shiwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,6]]},"reference":[{"key":"8567_CR1","doi-asserted-by":"crossref","unstructured":"Anderson P, Fernando B, Johnson M, Gould S (2016) Spice: Semantic propositional image caption evaluation. In: European conference on computer vision, pp 382\u2013398","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"8567_CR2","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: IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8567_CR3","unstructured":"Banerjee S, Lavie A (2005) METEOR: An automatic metric for mt evaluation with improved correlation with human judgments. In: The acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, pp 65\u201372"},{"key":"8567_CR4","unstructured":"Bird S, Klein E, Loper E (2009) Natural language processing with Python: analyzing text with the natural language toolkit. \u201d O\u2019Reilly Media, Inc.\u201d"},{"key":"8567_CR5","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua TS (2017) SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning. In: IEEE conference on computer vision and pattern recognition, pp 6298\u20136306","DOI":"10.1109\/CVPR.2017.667"},{"key":"8567_CR6","doi-asserted-by":"crossref","unstructured":"Cheng Z, Bai F, Xu Y, Zheng G, Pu S, Zhou S (2017) Focusing attention: Towards accurate text recognition in natural images. In: IEEE International Conference on Computer Vision, pp 5076\u20135084","DOI":"10.1109\/ICCV.2017.543"},{"issue":"23","key":"8567_CR7","doi-asserted-by":"publisher","first-page":"31,159","DOI":"10.1007\/s11042-018-6228-6","volume":"77","author":"F Fang","year":"2018","unstructured":"Fang F, Wang H, Chen Y, Tang P (2018) Looking deeper and transferring attention for image captioning. Multimed Tools Appl 77(23):31,159\u201331,175","journal-title":"Multimed Tools Appl"},{"key":"8567_CR8","doi-asserted-by":"crossref","unstructured":"Gan Z, Gan C, He X, Pu Y, Tran K, Gao J, Carin L, Deng L (2017) Semantic compositional networks for visual captioning. In: IEEE conference on computer vision and pattern recognition, pp 5630\u20135639","DOI":"10.1109\/CVPR.2017.127"},{"key":"8567_CR9","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8567_CR10","doi-asserted-by":"crossref","unstructured":"Jiang W, Ma L, Jiang YG, Liu W, Zhang T (2018) Recurrent fusion network for image captioning. In: European conference on computer vision, pp 499\u2013515","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"8567_CR11","unstructured":"Jin J, Fu K, Cui R, Sha F, Zhang C (2015) Aligning where to see and what to tell: image caption with region-based attention and scene factorization. arXiv:150606272"},{"key":"8567_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: IEEE conference on computer vision and pattern recognition, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"8567_CR13","unstructured":"Kingma D P, Ba J (2014) Adam: A method for stochastic optimization"},{"key":"8567_CR14","doi-asserted-by":"crossref","unstructured":"Li L, Tang S, Deng L, Zhang Y, Tian Q (2017) Image caption with global-local attention. In: 31st AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11236"},{"key":"8567_CR15","unstructured":"Lin CY (2004) Rouge: A package for automatic evaluation of summaries. Text Summarization Branches Out"},{"key":"8567_CR16","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8567_CR17","doi-asserted-by":"crossref","unstructured":"Liu C, Sun F, Wang C, Wang F, Yuille A (2017) MAT: A multimodal attentive translator for image captioning","DOI":"10.24963\/ijcai.2017\/563"},{"key":"8567_CR18","doi-asserted-by":"crossref","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2017) Knowing when to look: Adaptive attention via a visual sentinel for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 3242\u20133250","DOI":"10.1109\/CVPR.2017.345"},{"key":"8567_CR19","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2014) Deep captioning with multimodal recurrent neural networks (m-rnn)"},{"key":"8567_CR20","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation. In: The 40th annual meeting on association for computational linguistics, pp 311\u2013318"},{"key":"8567_CR21","doi-asserted-by":"crossref","unstructured":"Pedersoli M, Lucas T, Schmid C, Verbeek J (2017) Areas of attention for image captioning. In: IEEE international conference on computer vision, pp 1242\u20131250","DOI":"10.1109\/ICCV.2017.140"},{"key":"8567_CR22","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":"8567_CR23","doi-asserted-by":"crossref","unstructured":"Ren Z, Wang X, Zhang N, Lv X, Li LJ (2017) Deep reinforcement learning-based image captioning with embedding reward. In: IEEE conference on computer vision and pattern recognition, pp 290\u2013298","DOI":"10.1109\/CVPR.2017.128"},{"key":"8567_CR24","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":"8567_CR25","unstructured":"Selvaraju RR, Das A, Vedantam R, Cogswell M, Parikh D, Batra D (2016) Grad-cam: Why did you say that?. arXiv:161107450"},{"key":"8567_CR26","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015) Cider: Consensus-based image description evaluation. In: IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"8567_CR27","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: A neural image caption generator. In: IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"8567_CR28","doi-asserted-by":"crossref","unstructured":"Wu Q, Shen C, Liu L, Dick A, van den Hengel A (2016) What value do explicit high level concepts have in vision to language problems? In: IEEE conference on computer vision and pattern recognition, pp 203\u2013212","DOI":"10.1109\/CVPR.2016.29"},{"key":"8567_CR29","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":"8567_CR30","unstructured":"Yang Z, Yuan Y, Wu Y, Cohen WW, Salakhutdinov RR (2016) Review networks for caption generation. In: Advances in neural information processing systems, pp 2361\u20132369"},{"key":"8567_CR31","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2017) Incorporating copying mechanism in image captioning for learning novel objects. In: IEEE conference on computer vision and pattern recognition, pp 5263\u20135271","DOI":"10.1109\/CVPR.2017.559"},{"key":"8567_CR32","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Qiu Z, Mei T (2017) Boosting image captioning with attributes. In: IEEE International Conference on Computer Vision, pp 22\u201329","DOI":"10.1109\/ICCV.2017.524"},{"key":"8567_CR33","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: IEEE conference on computer vision and pattern recognition, pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"8567_CR34","doi-asserted-by":"crossref","unstructured":"Yu Y, Ko H, Choi J, Kim G (2017) End-to-end concept word detection for video captioning, retrieval, and question answering. In: IEEE conference on computer vision and pattern recognition, pp 3165\u20133173","DOI":"10.1109\/CVPR.2017.347"},{"key":"8567_CR35","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: IEEE conference on computer vision and pattern recognition, pp 2921\u20132929","DOI":"10.1109\/CVPR.2016.319"},{"key":"8567_CR36","unstructured":"Zhou L, Xu C, Koch P, Corso JJ (2016) Image caption generation with text-conditional semantic attention. arXiv:160604621.2"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08567-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08567-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08567-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T02:25:03Z","timestamp":1665368703000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08567-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,6]]},"references-count":36,"journal-issue":{"issue":"17-18","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["8567"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08567-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,1,6]]},"assertion":[{"value":"31 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}