{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:09:15Z","timestamp":1781107755620,"version":"3.54.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15869-x","type":"journal-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T18:42:29Z","timestamp":1687545749000},"page":"12209-12233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Stacked cross-modal feature consolidation attention networks for image captioning"],"prefix":"10.1007","volume":"83","author":[{"given":"Mozhgan","family":"Pourkeshavarz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shahabedin","family":"Nabavi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7391-508X","authenticated-orcid":false,"given":"Mohsen Ebrahimi","family":"Moghaddam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehrnoush","family":"Shamsfard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,23]]},"reference":[{"key":"15869_CR1","doi-asserted-by":"crossref","unstructured":"Anderson P, Fernando B, Johnson M, Gould S (2016) \u201cSpice: Semantic propositional image caption evaluation.\u201d In: European conference on computer vision, Springer, pp 382\u2013398","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"15869_CR2","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) \u201cBottom-up and top-down attention for image captioning and visual question answering.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"15869_CR3","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) \u201cNeural machine translation by jointly learning to align and translate.\u201d arXiv preprint arXiv:1409.0473"},{"key":"15869_CR4","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24:123\u2013140","journal-title":"Mach Learn"},{"key":"15869_CR5","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.1126\/science.1138071","volume":"315","author":"TJ Buschman","year":"2007","unstructured":"Buschman TJ, Miller EK (2007) Top-down versus bottom-up control of attention in the prefrontal and posterior parietal cortices. Science 315:1860\u20131862","journal-title":"Science"},{"key":"15869_CR6","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua T-S (2017) \u201cSca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5659\u20135667","DOI":"10.1109\/CVPR.2017.667"},{"key":"15869_CR7","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1038\/nrn755","volume":"3","author":"M Corbetta","year":"2002","unstructured":"Corbetta M, Shulman GL (2002) \u201cControl of goal-directed and stimulus-driven attention in the brain\u2019\u2019. Nat Rev Neurosci 3:201\u2013215","journal-title":"Nat Rev Neurosci"},{"key":"15869_CR8","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) \u201cImagenet: A large-scale hierarchical image database.\u201d In: 2009 IEEE conference on computer vision and pattern recognition. Ieee, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15869_CR9","doi-asserted-by":"crossref","unstructured":"Denkowski M, Lavie A (2014) \u201cMeteor universal: Language-specific translation evaluation for any target language.\u201d In: Proceedings of the ninth workshop on statistical machine translation, pp 376\u2013380","DOI":"10.3115\/v1\/W14-3348"},{"key":"15869_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)\u201cFrom captions to visual concepts and back.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1473\u20131482","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"15869_CR11","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TPAMI.2016.2642953","volume":"39","author":"K Fu","year":"2017","unstructured":"Fu K, Jin J, Cui R, Sha F, Zhang C (2017) Aligning where to see and what to tell: Image captioning with region-based attention and scene-specific contexts. IEEE Trans Pattern Anal Mach Intell 39:2321\u20132334","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15869_CR12","doi-asserted-by":"crossref","unstructured":"Gan Z, Gan C, He X, Pu Y, Tran K, Gao J, Carin L, Deng L (2017) \u201cSemantic compositional networks for visual captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5630\u20135639","DOI":"10.1109\/CVPR.2017.127"},{"key":"15869_CR13","doi-asserted-by":"crossref","unstructured":"Gers FA, Schmidhuber J (2000) \u201cRecurrent nets that time and count.\u201d In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, vol. 3. IEEE, pp 189\u2013194","DOI":"10.1109\/IJCNN.2000.861302"},{"key":"15869_CR14","unstructured":"Graves A (2013) \u201cGenerating sequences with recurrent neural networks.\u201d arXiv preprint arXiv:1308.0850"},{"key":"15869_CR15","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2016","unstructured":"Greff K, Srivastava RK, Koutn\u00edk J, Steunebrink BR, Schmidhuber J (2016) Lstm: A search space odyssey. IEEE Trans Neural Netw Learn Syst 28:2222\u20132232","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"15869_CR16","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s11063-018-9807-7","volume":"49","author":"C He","year":"2019","unstructured":"He C, Hu H (2019) Image captioning with text-based visual attention. Neural Process Lett 49:177\u2013185","journal-title":"Neural Process Lett"},{"key":"15869_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) \u201dDeep residual learning for image recognition.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"15869_CR18","doi-asserted-by":"publisher","first-page":"4013","DOI":"10.1109\/TIP.2020.2969330","volume":"29","author":"Y Huang","year":"2020","unstructured":"Huang Y, Chen J, Ouyang W, Wan W, Xue Y (2020) Image captioning with end-to-end attribute detection and subsequent attributes prediction. IEEE Trans Image Process 29:4013\u20134026","journal-title":"IEEE Trans Image Process"},{"key":"15869_CR19","doi-asserted-by":"crossref","unstructured":"Hu X, Gan Z, Wang J, Yang Z, Liu Z, Lu Y et al (2022) \u201cScaling up vision-language pre-training for image captioning.\u201d In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 17980\u201317989","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"15869_CR20","unstructured":"Jaderberg M, Simonyan K, Zisserman A et al (2015) \u201cSpatial transformer networks.\u201d In: Advances in neural information processing systems, pp 2017\u20132025"},{"key":"15869_CR21","doi-asserted-by":"crossref","unstructured":"Jiang W, Ma L, Jiang Y-G, Liu W, Zhang T (2018) \u201cRecurrent fusion network for image captioning.\u201d In: Proceedings of the European conference on computer vision (ECCV), pp 499\u2013515","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"15869_CR22","doi-asserted-by":"crossref","unstructured":"Johnson J, Karpathy A, Fei-Fei L (2016) \u201cDensecap: Fully convolutional localization networks for dense captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.494"},{"key":"15869_CR23","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) \u201cDeep visual-semantic alignments for generating image descriptions.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"15869_CR24","unstructured":"Karpathy A, Joulin A, Fei-Fei LF (2014) \u201cDeep fragment embeddings for bidirectional image sentence mapping.\u201d In: Advances in neural information processing systems, pp 1889\u20131897"},{"key":"15869_CR25","unstructured":"Kingma DP, Ba J (2014) \u201cAdam: A method for stochastic optimization.\u201d arXiv preprint arXiv:1412.6980"},{"key":"15869_CR26","unstructured":"Kiros R, Salakhutdinov R, Zemel RS (2014) \u201cUnifying visual-semantic embeddings with multimodal neural language models.\u201d arXiv preprint arXiv:1411.2539"},{"key":"15869_CR27","unstructured":"Lin C-Y (2004) \u201cRouge: A package for automatic evaluation of summaries.\u201d In: Text summarization branches out, pp 74 81"},{"key":"15869_CR28","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017)\u201cFocal loss for dense object detection.\u201d In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"15869_CR29","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) \u201cMicrosoft coco: Common objects in context.\u201d In: European conference on computer vision, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15869_CR30","doi-asserted-by":"crossref","unstructured":"Li Y, Pan Y, Yao T, Mei T (2022) \u201cComprehending and ordering semantics for image captioning.\u201d In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 17990\u201317999","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"15869_CR31","unstructured":"Liu H, Yang Y, Shen F, Duan L, Shen HT (2016) \u201cRecurrent image captioner: Describing images with spatial-invariant transformation and attention filtering.\u201d arXiv preprint arXiv:1612.04949"},{"key":"15869_CR32","doi-asserted-by":"crossref","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2017) \u201cKnowing when to look: Adaptive attention via a visual sentinel for image captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 375\u2013383","DOI":"10.1109\/CVPR.2017.345"},{"key":"15869_CR33","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2015) \u201cDeep captioning with multimodal recurrent neural networks (m-rnn).\u201d arXiv preprint arXiv:1412.6632"},{"key":"15869_CR34","unstructured":"Mao J, Xu W, Yang Y, Wang J, Yuille AL (2014)\u201cExplain images with multimodal recurrent neural networks.\u201d arXiv preprint arXiv:1410.1090"},{"key":"15869_CR35","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) \u201cBleu: a method for automatic evaluation of machine translation.\u201d In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"15869_CR36","doi-asserted-by":"crossref","unstructured":"Pedersoli M, Lucas T, Schmid C, Verbeek J (2017) \u201dAreas of attention for image captioning.\u201d In: Proceedings of the IEEE international conference on computer vision, pp 1242\u20131250","DOI":"10.1109\/ICCV.2017.140"},{"key":"15869_CR37","doi-asserted-by":"crossref","unstructured":"Qin Y, Du J, Zhang Y, Lu H (2019) \u201cLook back and predict forward in image captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8367\u20138375","DOI":"10.1109\/CVPR.2019.00856"},{"key":"15869_CR38","unstructured":"Ren S, He K, Girshick R, Sun J (2015) \u201cFaster r-cnn: Towards real-time object detection with region proposal networks.\u201d In: Advances in neural information processing systems, pp 91\u201399"},{"key":"15869_CR39","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) \u201cSelfcritical sequence training for image captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7008\u20137024","DOI":"10.1109\/CVPR.2017.131"},{"key":"15869_CR40","doi-asserted-by":"crossref","unstructured":"Shao Z, Han J, Debattista K, Pang Y (2023) \u201cTextual context-aware dense captioning with diverse words.\u201d IEEE Trans Multimedia","DOI":"10.1109\/TMM.2023.3241517"},{"key":"15869_CR41","doi-asserted-by":"crossref","unstructured":"Shao Z, Han J, Marnerides D, Debattista K (2022) \u201cRegion-object relation-aware dense captioning via transformer.\u201d IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2022.3152990"},{"key":"15869_CR42","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"15869_CR43","doi-asserted-by":"crossref","unstructured":"Su Y, Li Y, Xu N, Liu A-A (2019) \u201cHierarchical deep neural network for image captioning.\u201d Neural Process Lett 1\u201311","DOI":"10.1007\/s11063-019-09997-5"},{"key":"15869_CR44","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vis 104:154\u2013171","journal-title":"Int J Comput Vis"},{"key":"15869_CR45","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015)\u201cCider: Consensus-based image description evaluation.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"15869_CR46","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) \u201cShow and tell: A neural image caption generator.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"15869_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075","volume":"98","author":"J Wang","year":"2020","unstructured":"Wang J, Wang W, Wang L, Wang Z, Feng DD, Tan T (2020) Learning visual relationship and context-aware attention for image captioning. Pattern Recogn 98:107075","journal-title":"Pattern Recogn"},{"key":"15869_CR48","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","volume":"1","author":"RJ Williams","year":"1989","unstructured":"Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270\u2013280","journal-title":"Neural Comput"},{"key":"15869_CR49","doi-asserted-by":"crossref","unstructured":"Wu Q, Shen C, Liu L, Dick A, Van Den Hengel A (2016) \u201cWhat value do explicit high-level concepts have in vision to language problems?\u201d. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 203\u2013212","DOI":"10.1109\/CVPR.2016.29"},{"key":"15869_CR50","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) \u201cShow, attend and tell: Neural image caption generation with visual attention.\u201d In: International conference on machine learning, pp 2048\u20132057"},{"key":"15869_CR51","doi-asserted-by":"crossref","unstructured":"Yang X, Tang K, Zhang H, Cai J (2019) \u201cAuto-encoding scene graphs for image captioning.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10 685\u201310 694","DOI":"10.1109\/CVPR.2019.01094"},{"key":"15869_CR52","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2018) \u201cExploring visual relationship for image captioning.\u201d In: Proceedings of the European conference on computer vision (ECCV), pp 684\u2013699","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"15869_CR53","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Qiu Z, Mei T (2017)\u201cBoosting image captioning with attributes.\u201d In: Proceedings of the IEEE international conference on computer vision, pp 4894\u20134902","DOI":"10.1109\/ICCV.2017.524"},{"key":"15869_CR54","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) \u201cImage captioning with semantic attention.\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"15869_CR55","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2:67\u201378","journal-title":"Trans Assoc Comput Linguist"},{"key":"15869_CR56","unstructured":"Zha Z-J, Liu D, Zhang H, Zhang Y, Wu F (2019) \u201cContext-aware visual policy network for fine-grained image captioning.\u201d IEEE Trans Pattern Anal Mach Intell"},{"key":"15869_CR57","doi-asserted-by":"publisher","first-page":"3833","DOI":"10.1007\/s10462-021-10092-2","volume":"55","author":"Z Zohourianshahzadi","year":"2022","unstructured":"Zohourianshahzadi Z, Kalita JK (2022) Neural attention for image captioning: review of outstanding methods. Artif Intell Rev 55:3833\u20133862","journal-title":"Artif Intell Rev"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15869-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15869-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15869-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T09:23:56Z","timestamp":1704878636000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15869-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,23]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15869"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15869-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,23]]},"assertion":[{"value":"2 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}