{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T15:34:10Z","timestamp":1762011250875,"version":"build-2065373602"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"45-46","license":[{"start":{"date-parts":[[2019,3,27]],"date-time":"2019-03-27T00:00:00Z","timestamp":1553644800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,3,27]],"date-time":"2019-03-27T00:00:00Z","timestamp":1553644800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s11042-019-7441-7","type":"journal-article","created":{"date-parts":[[2019,3,27]],"date-time":"2019-03-27T17:52:34Z","timestamp":1553709154000},"page":"33333-33348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Cross-domain personalized image captioning"],"prefix":"10.1007","volume":"79","author":[{"given":"Cuirong","family":"Long","sequence":"first","affiliation":[]},{"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,3,27]]},"reference":[{"unstructured":"Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M (2014) Domain-adversarial neural networks. Eprint Arxiv","key":"7441_CR1"},{"doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2017) Bottom-up and top-down attention for image captioning and visual question answering","key":"7441_CR2","DOI":"10.1109\/CVPR.2018.00636"},{"unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. Computer Science","key":"7441_CR3"},{"unstructured":"Bengio S, Vinyals O, Jaitly N, Shazeer N (2015) Scheduled sampling for sequence prediction with recurrent neural networks, pp 1171\u20131179","key":"7441_CR4"},{"doi-asserted-by":"crossref","unstructured":"Chen TH, Liao YH, Chuang CY, Hsu WT, Fu J, Sun M (2017) Show, adapt and tell: Adversarial training of cross-domain image captioner. In: IEEE international conference on computer vision, pp 521\u2013530","key":"7441_CR5","DOI":"10.1109\/ICCV.2017.64"},{"issue":"10","key":"7441_CR6","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume":"21","author":"A Farhadi","year":"2010","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. Lect Notes Comput Sci 21(10):15\u201329","journal-title":"Lect Notes Comput Sci"},{"issue":"1","key":"7441_CR7","first-page":"2096","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(1):2096\u20132030","journal-title":"J Mach Learn Res"},{"key":"7441_CR8","first-page":"315","volume":"15","author":"X Glorot","year":"2012","unstructured":"Glorot X, Bordes A, Bengio Y (2012) Deep sparse rectifier neural networks. Jmlr W Cp 15:315\u2013323","journal-title":"Jmlr W Cp"},{"issue":"11","key":"7441_CR9","doi-asserted-by":"publisher","first-page":"3137","DOI":"10.1109\/TMM.2018.2823900","volume":"20","author":"YG Jiang","year":"2018","unstructured":"Jiang YG, Wu Z, Tang J, Li Z, Xue X, Chang SF (2018) Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification. IEEE Trans Multimed (TMM) 20(11):3137\u20133147","journal-title":"IEEE Trans Multimed (TMM)"},{"issue":"2","key":"7441_CR10","first-page":"50:1","volume":"14","author":"YG Jiang","year":"2018","unstructured":"Jiang YG, Li M, Wang X, Liu W, Hua XS (2018) DeepProduct: Mobile Product Search with Portable Deep Features. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM) 14(2):50:1\u201350:18","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)"},{"issue":"4","key":"7441_CR11","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy A, Fei-Fei L (2017) Deep visual-semantic alignments for generating image descriptions. IEEE Trans Pattern Anal Mach Intell 39(4):664\u2013676","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. Eprint Arxiv","key":"7441_CR12","DOI":"10.3115\/v1\/D14-1181"},{"unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Computer Science","key":"7441_CR13"},{"doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Lawrence Zitnick C (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, pp 740\u2013755","key":"7441_CR14","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Lin WH, Chen KT, Chiang HY, Hsu W (2018) Netizen-style commenting on fashion photos: dataset and diversity measures","key":"7441_CR15","DOI":"10.1145\/3184558.3186354"},{"doi-asserted-by":"crossref","unstructured":"Liu X, Qian X, Lu D, Hou X, Wang L (2014) Personalized tag recommendation for flickr users. In: IEEE international conference on multimedia and expo","key":"7441_CR16","DOI":"10.1109\/ICME.2014.6890126"},{"unstructured":"Long M, Wang J (2015) Learning transferable features with deep adaptation networks. arXiv:1502.02791","key":"7441_CR17"},{"doi-asserted-by":"crossref","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2016) Knowing when to look: adaptive attention via a visual sentinel for image captioning, pp 3242\u20133250","key":"7441_CR18","DOI":"10.1109\/CVPR.2017.345"},{"doi-asserted-by":"crossref","unstructured":"Mathews A, Xie L, He X (2016) Senticap: generating image descriptions with sentiments. In: Thirtieth AAAI conference on artificial intelligence, pp 3574\u20133580","key":"7441_CR19","DOI":"10.1609\/aaai.v30i1.10475"},{"issue":"2","key":"7441_CR20","first-page":"311","volume":"30","author":"K Papineni","year":"2002","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Ibm research report bleu: a method for automatic evaluation of machine translation. Acl Proc Ann Meet Assoc Comput Linguist 30(2):311\u2013318","journal-title":"Acl Proc Ann Meet Assoc Comput Linguist"},{"doi-asserted-by":"crossref","unstructured":"Park CC, Kim B, Kim G (2017) Attend to you: personalized image captioning with context sequence memory networks, pp 6432\u20136440","key":"7441_CR21","DOI":"10.1109\/CVPR.2017.681"},{"doi-asserted-by":"crossref","unstructured":"Plummer BA, Wang L, Cervantes CM, Caicedo JC (2015) Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: IEEE international conference on computer vision, pp 2641\u20132649","key":"7441_CR22","DOI":"10.1109\/ICCV.2015.303"},{"issue":"111","key":"7441_CR23","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.neucom.2012.12.021","volume":"111","author":"X Qian","year":"2013","unstructured":"Qian X, Liu X, Zheng C, Youtian DU, Hou X (2013) Tagging photos using users\u2019 vocabularies. Neurocomputing 111(111):144\u2013153","journal-title":"Neurocomputing"},{"doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015) Cider: consensus-based image description evaluation. In: Computer vision and pattern recognition, pp 4566\u20134575","key":"7441_CR24","DOI":"10.1109\/CVPR.2015.7299087"},{"doi-asserted-by":"crossref","unstructured":"Venugopalan S, Hendricks LA, Rohrbach M, Mooney R, Darrell T, Saenko K (2017) Captioning images with diverse objects. In: IEEE conference on computer vision and pattern recognition, pp 1170\u20131178","key":"7441_CR25","DOI":"10.1109\/CVPR.2017.130"},{"doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2014) Show and tell: a neural image caption generator, pp 3156\u20133164","key":"7441_CR26","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"2","key":"7441_CR27","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"},{"unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville AC, Salakhutdinov R, Zemel RS, Bengio Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of the international conference on machine learning, ICML 2015, pp 2048\u20132057","key":"7441_CR28"},{"key":"7441_CR29","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/978-3-642-20161-5_34","volume":"6611","author":"WX Zhao","year":"2011","unstructured":"Zhao WX, Jiang J, Weng J, He J, Ee PL, Yan H, Li X (2011) Comparing twitter and traditional media using topic models. Lect Notes Comput Sci 6611:338\u2013349","journal-title":"Lect Notes Comput Sci"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-7441-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-7441-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-7441-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T13:11:36Z","timestamp":1663161096000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-7441-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,27]]},"references-count":29,"journal-issue":{"issue":"45-46","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["7441"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-7441-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2019,3,27]]},"assertion":[{"value":"31 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}