{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T13:21:25Z","timestamp":1778592085630,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2019,11,14]],"date-time":"2019-11-14T00:00:00Z","timestamp":1573689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,11,14]],"date-time":"2019-11-14T00:00:00Z","timestamp":1573689600000},"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1435222"],"award-info":[{"award-number":["U1435222"]}],"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":[[2020,1]]},"DOI":"10.1007\/s11042-019-08209-5","type":"journal-article","created":{"date-parts":[[2019,11,14]],"date-time":"2019-11-14T20:01:38Z","timestamp":1573761698000},"page":"2013-2030","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Object-aware semantics of attention 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":"Guohua","family":"Dong","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":[[2019,11,14]]},"reference":[{"key":"8209_CR1","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","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8209_CR2","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv:14090473"},{"key":"8209_CR3","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":"8","key":"8209_CR4","doi-asserted-by":"publisher","first-page":"3911","DOI":"10.1109\/TIP.2017.2708506","volume":"26","author":"X Chang","year":"2017","unstructured":"Chang X, Ma Z, Lin M, Yang Y, Hauptmann A G (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans Image Process 26(8):3911\u20133920","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"8209_CR5","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TPAMI.2016.2608901","volume":"39","author":"X Chang","year":"2017","unstructured":"Chang X, Yu Y L, Yang Y, Xing E P (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39 (8):1617\u20131632","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"8209_CR6","doi-asserted-by":"publisher","first-page":"2959","DOI":"10.1007\/s11042-017-4593-1","volume":"77","author":"Yan-Shuo Chang","year":"2017","unstructured":"Chang Y S (2018) Fine-grained attention for image caption generation. Multimedia Tools and Applications pp 2959\u20132971","journal-title":"Multimedia Tools and Applications"},{"key":"8209_CR7","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6298\u20136306","DOI":"10.1109\/CVPR.2017.667"},{"key":"8209_CR8","doi-asserted-by":"crossref","unstructured":"Chen X, Lawrence Zitnick C (2015) Mind\u2019s eye: A recurrent visual representation for image caption generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2422\u20132431","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"8209_CR9","unstructured":"Cheng Z, Ding Y, He X, Zhu L, Song X, Kankanhalli MS (2018) A3NCF: An adaptive aspect attention model for rating prediction. In: IJCAI, pp 3748\u20133754"},{"key":"8209_CR10","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:14061078","DOI":"10.3115\/v1\/D14-1179"},{"key":"8209_CR11","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"8209_CR12","unstructured":"Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN (2017) Convolutional sequence to sequence learning. arXiv:170503122"},{"key":"8209_CR13","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"8209_CR14","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2016","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38:142\u2013158","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8209_CR15","unstructured":"Gkioxari G, Girshick R, Doll\u00e1r P, He K (2017) Detecting and recognizing human-object interactions. arXiv:170407333"},{"issue":"2","key":"8209_CR16","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1145\/3295822","volume":"37","author":"Y Guo","year":"2019","unstructured":"Guo Y, Cheng Z, Nie L, Wang Y, Ma J, Kankanhalli M (2019) Attentive long short-term preference modeling for personalized product search. ACM Trans Inf Syst 37(2):19","journal-title":"ACM Trans Inf Syst"},{"key":"8209_CR17","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"},{"key":"8209_CR18","unstructured":"Hu H, Gu J, Zhang Z, Dai J, Wei Y (2017) Relation networks for object detection. arXiv:171111575"},{"key":"8209_CR19","doi-asserted-by":"crossref","unstructured":"Jia X, Gavves E, Fernando B, Tuytelaars T (2015) Guiding long-short term memory for image caption generation. arXiv:150904942","DOI":"10.1109\/ICCV.2015.277"},{"key":"8209_CR20","doi-asserted-by":"crossref","unstructured":"Johnson J, Karpathy A, Fei-Fei L (2016) Densecap: Fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4565\u20134574","DOI":"10.1109\/CVPR.2016.494"},{"key":"8209_CR21","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"10","key":"8209_CR22","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1109\/TKDE.2017.2728531","volume":"29","author":"Z Li","year":"2017","unstructured":"Li Z, Nie F, Chang X, Yang Y (2017) Beyond trace ratio: weighted harmonic mean of trace ratios for multiclass discriminant analysis. IEEE Trans Knowl Data Eng 29(10):2100\u20132110","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"8209_CR23","unstructured":"Lin CY (2004) Rouge: A package for automatic evaluation of summaries. Text Summarization Branches Out"},{"key":"8209_CR24","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":"8209_CR25","doi-asserted-by":"crossref","unstructured":"Liu A, Xu N, Zhang H, Nie W, Su Y, Zhang Y (2018) Multi-level policy and reward reinforcement learning for image captioning. In: IJCAI, pp 821\u2013827","DOI":"10.24963\/ijcai.2018\/114"},{"key":"8209_CR26","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.cviu.2017.04.013","volume":"163","author":"AA Liu","year":"2017","unstructured":"Liu A A, Xu N, Wong Y, Li J, Su Y T, Kankanhalli M (2017) Hierarchical & multimodal video captioning: Discovering and transferring multimodal knowledge for vision to language. Comput Vis Image Underst 163:113\u2013125","journal-title":"Comput Vis Image Underst"},{"key":"8209_CR27","doi-asserted-by":"crossref","unstructured":"Liu C, Sun F, Wang C, Wang F, Yuille A (2017) MAT: A multimodal attentive translator for image captioning. arXiv:170205658","DOI":"10.24963\/ijcai.2017\/563"},{"key":"8209_CR28","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3242\u20133250","DOI":"10.1109\/CVPR.2017.345"},{"key":"8209_CR29","doi-asserted-by":"crossref","unstructured":"Lu J, Yang J, Batra D, Parikh D (2018) Neural Baby Talk. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7219\u20137228","DOI":"10.1109\/CVPR.2018.00754"},{"key":"8209_CR30","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2014) Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv:14126632"},{"key":"8209_CR31","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"},{"key":"8209_CR32","unstructured":"Pedersoli M, Lucas T, Schmid C, Verbeek J (2016) Areas of attention for image captioning. arXiv:161201033"},{"key":"8209_CR33","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":"8209_CR34","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-critical sequence training for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1179\u20131195","DOI":"10.1109\/CVPR.2017.131"},{"key":"8209_CR35","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104\u20133112"},{"key":"8209_CR36","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"8209_CR37","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":"8209_CR38","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"},{"key":"8209_CR39","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 203\u2013212","DOI":"10.1109\/CVPR.2016.29"},{"key":"8209_CR40","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":"8209_CR41","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":"8209_CR42","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5263\u20135271","DOI":"10.1109\/CVPR.2017.559"},{"key":"8209_CR43","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 22\u201329","DOI":"10.1109\/ICCV.2017.524"},{"key":"8209_CR44","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":"8209_CR45","doi-asserted-by":"crossref","unstructured":"Zhou L, Xu C, Koch P, Corso J J (2017) Watch what you just said: Image captioning with text-conditional attention. In: Proceedings of the on Thematic Workshops of ACM Multimedia, vol 2017, pp 305\u2013313","DOI":"10.1145\/3126686.3126717"},{"key":"8209_CR46","doi-asserted-by":"crossref","unstructured":"Zhu Z, Xue Z, Yuan Z (2018) Topic-guided attention for image captioning. arXiv:180703514","DOI":"10.1109\/ICIP.2018.8451083"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08209-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08209-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08209-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:32:23Z","timestamp":1605227543000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08209-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,14]]},"references-count":46,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["8209"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08209-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,14]]},"assertion":[{"value":"31 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}