{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T20:16:10Z","timestamp":1779308170861,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T00:00:00Z","timestamp":1660262400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T00:00:00Z","timestamp":1660262400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["Grant No. 2016YFB0800602"],"award-info":[{"award-number":["Grant No. 2016YFB0800602"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant Nos. 61573067"],"award-info":[{"award-number":["Grant Nos. 61573067"]}],"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":["61771071"],"award-info":[{"award-number":["61771071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s10489-022-04010-4","type":"journal-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T06:03:27Z","timestamp":1660284207000},"page":"9731-9743","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Incorporating retrieval-based method for feature enhanced image captioning"],"prefix":"10.1007","volume":"53","author":[{"given":"Shanshan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9949-8731","authenticated-orcid":false,"given":"Lixiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haipeng","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,12]]},"reference":[{"key":"4010_CR1","doi-asserted-by":"crossref","unstructured":"Das A, Kottur S, Gupta K, Singh A, Yadav D, Moura JM, Parikh D, Batra D (2017) Visual dialog. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 326\u2013335","DOI":"10.1109\/CVPR.2017.121"},{"key":"4010_CR2","doi-asserted-by":"crossref","unstructured":"Chen H, Ding G, Liu X, Lin Z, Liu J, Han J (2020) Imram: iterative matching with recurrent attention memory for cross-modal image-text retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12655\u2013 12663","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"4010_CR3","doi-asserted-by":"crossref","unstructured":"Hou C, Li Z, Wu J (2021) Unsupervised hash retrieval based on multiple similarity matrices and text self-attention mechanism. Appl Intell:1\u201316","DOI":"10.1007\/s10489-021-02804-6"},{"key":"4010_CR4","doi-asserted-by":"crossref","unstructured":"Wang Z, Liu X, Li H, Sheng L, Yan J, Wang X, Shao J (2019) Camp: cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5764\u20135773","DOI":"10.1109\/ICCV.2019.00586"},{"key":"4010_CR5","doi-asserted-by":"crossref","unstructured":"Wang L, Bai Z, Zhang Y, Lu H (2020) Show, recall, and tell: image captioning with recall mechanism. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 12176\u201312183","DOI":"10.1609\/aaai.v34i07.6898"},{"key":"4010_CR6","doi-asserted-by":"crossref","unstructured":"Mun J, Cho M, Han B (2017) Text-guided attention model for image captioning. In: Proceedings of the AAAI conference on artificial intelligence, vol 31","DOI":"10.1609\/aaai.v31i1.11237"},{"key":"4010_CR7","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1162\/tacl_a_00188","volume":"2","author":"P Kuznetsova","year":"2014","unstructured":"Kuznetsova P, Ordonez V, Berg TL, Choi Y (2014) Treetalk: composition and compression of trees for image descriptions. Trans Assoc Comput Linguist 2:351\u2013362","journal-title":"Trans Assoc Comput Linguist"},{"key":"4010_CR8","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Hodosh M, Hockenmaier J, Lazebnik S (2014) Improving image-sentence embeddings using large weakly annotated photo collections. In: European conference on computer vision. Springer, pp 529\u2013545","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"4010_CR9","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":"4","key":"4010_CR10","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2017) Show and tell: Lessons learned from the 2015 mscoco image captioning challenge. IEEE Trans Pattern Anal Mach Intell 39(4):652\u2013663","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4010_CR11","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":"4010_CR12","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":"4010_CR13","doi-asserted-by":"crossref","unstructured":"Bhunia AK, Perla SRK, Mukherjee P, Das A, Roy PP (2019) Texture synthesis guided deep hashing for texture image retrieval. In: 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 609\u2013618","DOI":"10.1109\/WACV.2019.00070"},{"issue":"2","key":"4010_CR14","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/s10044-019-00827-x","volume":"23","author":"AK Bhunia","year":"2020","unstructured":"Bhunia AK, Bhattacharyya A, Banerjee P, Roy PP, Murala S (2020) A novel feature descriptor for image retrieval by combining modified color histogram and diagonally symmetric co-occurrence texture pattern. Pattern Anal Applic 23(2):703\u2013723","journal-title":"Pattern Anal Applic"},{"key":"4010_CR15","first-page":"1143","volume":"24","author":"V Ordonez","year":"2011","unstructured":"Ordonez V, Kulkarni G, Berg T (2011) Im2text: describing images using 1 million captioned photographs. Adv Neural Inf Process Syst 24:1143\u20131151","journal-title":"Adv Neural Inf Process Syst"},{"key":"4010_CR16","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Intell Res 47:853\u2013899","journal-title":"J Artif Intell Res"},{"key":"4010_CR17","doi-asserted-by":"crossref","unstructured":"Agrawal P, Yadav R, Yadav V, De K, Pratim Roy P (2020) Caption-based region extraction in images. In: Proceedings of 3rd international conference on computer vision and image processing. Springer, pp 27\u201338","DOI":"10.1007\/978-981-32-9291-8_3"},{"key":"4010_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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 375\u2013383","DOI":"10.1109\/CVPR.2017.345"},{"key":"4010_CR19","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":"4010_CR20","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua T. -S. (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 5659\u20135667","DOI":"10.1109\/CVPR.2017.667"},{"key":"4010_CR21","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"},{"issue":"1","key":"4010_CR22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L-J, Shamma DA et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vision 123(1):32\u201373","journal-title":"Int J Comput Vision"},{"key":"4010_CR23","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 7008\u20137024","DOI":"10.1109\/CVPR.2017.131"},{"issue":"2","key":"4010_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439734","volume":"17","author":"H Wei","year":"2021","unstructured":"Wei H, Li Z, Huang F, Zhang C, Ma H, Shi Z (2021) Integrating scene semantic knowledge into image captioning. ACM Trans Multimed Comput Communi Appl (TOMM) 17(2):1\u201322","journal-title":"ACM Trans Multimed Comput Communi Appl (TOMM)"},{"key":"4010_CR25","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2018) Exploring visual relationship for image captioning. In: Proceedings of the European conference on computer vision (ECCV), pp 684\u2013699","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"4010_CR26","doi-asserted-by":"crossref","unstructured":"Yang X, Tang K, Zhang H, Cai J (2019) Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10685\u201310694","DOI":"10.1109\/CVPR.2019.01094"},{"issue":"5","key":"4010_CR27","doi-asserted-by":"publisher","first-page":"739","DOI":"10.3390\/app8050739","volume":"8","author":"X Zhu","year":"2018","unstructured":"Zhu X, Li L, Liu J, Peng H, Niu X (2018) Captioning transformer with stacked attention modules. Appl Sci 8(5):739","journal-title":"Appl Sci"},{"key":"4010_CR28","doi-asserted-by":"crossref","unstructured":"Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10578\u201310587","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"4010_CR29","doi-asserted-by":"crossref","unstructured":"Liu J, Wang K, Xu C, Zhao Z, Xu R, Shen Y, Yang M (2020) Interactive dual generative adversarial networks for image captioning. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 11588\u201311595","DOI":"10.1609\/aaai.v34i07.6826"},{"key":"4010_CR30","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1109\/TIP.2020.3042086","volume":"30","author":"W Zhao","year":"2020","unstructured":"Zhao W, Wu X, Luo J (2020) Cross-domain image captioning via cross-modal retrieval and model adaptation. IEEE Trans Image Process 30:1180\u20131192","journal-title":"IEEE Trans Image Process"},{"key":"4010_CR31","doi-asserted-by":"publisher","first-page":"9627","DOI":"10.1109\/TIP.2020.3028651","volume":"29","author":"M Yang","year":"2020","unstructured":"Yang M, Liu J, Shen Y, Zhao Z, Chen X, Wu Q, Li C (2020) An ensemble of generation-and retrieval-based image captioning with dual generator generative adversarial network. IEEE Trans Image Process 29:9627\u20139640","journal-title":"IEEE Trans Image Process"},{"key":"4010_CR32","doi-asserted-by":"crossref","unstructured":"Lin T-Y, 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. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"4010_CR33","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"4010_CR34","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"},{"key":"4010_CR35","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":"4010_CR36","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. Springer, pp 382\u2013398","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"4010_CR37","doi-asserted-by":"crossref","unstructured":"Luo R, Price B, Cohen S, Shakhnarovich G (2018) Discriminability objective for training descriptive captions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6964\u20136974","DOI":"10.1109\/CVPR.2018.00728"},{"key":"4010_CR38","doi-asserted-by":"crossref","unstructured":"Huang L, Wang W, Chen J, Wei X-Y (2019) Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4634\u20134643","DOI":"10.1109\/ICCV.2019.00473"},{"key":"4010_CR39","doi-asserted-by":"crossref","unstructured":"Li G, Zhu L, Liu P, Yang Y (2019) Entangled transformer for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8928\u20138937","DOI":"10.1109\/ICCV.2019.00902"},{"key":"4010_CR40","doi-asserted-by":"crossref","unstructured":"Wang J, Xu W, Wang Q, Chan AB (2020) Compare and reweight: distinctive image captioning using similar images sets. In: European conference on computer vision. Springer, pp 370\u2013386","DOI":"10.1007\/978-3-030-58452-8_22"},{"key":"4010_CR41","doi-asserted-by":"crossref","unstructured":"Nie W, Li J, Xu N, Liu A-A, Li X, Zhang Y (2021) Triangle-reward reinforcement learning: a visual-linguistic semantic alignment for image captioning. In: Proceedings of the 29th ACM international conference on multimedia, pp 4510\u20134518","DOI":"10.1145\/3474085.3475604"},{"key":"4010_CR42","doi-asserted-by":"crossref","unstructured":"Guo L, Liu J, Tang J, Li J, Luo W, Lu H (2019) Aligning linguistic words and visual semantic units for image captioning. In: Proceedings of the 27th ACM international conference on multimedia, pp 765\u2013773","DOI":"10.1145\/3343031.3350943"},{"key":"4010_CR43","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":"4010_CR44","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2019) Hierarchy parsing for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2621\u20132629","DOI":"10.1109\/ICCV.2019.00271"},{"key":"4010_CR45","doi-asserted-by":"crossref","unstructured":"Liu F, Ren X, Liu Y, Lei K, Sun X (2019) Exploring and distilling cross-modal information for image captioning. In: IJCAI","DOI":"10.24963\/ijcai.2019\/708"},{"key":"4010_CR46","unstructured":"Liu W, Chen S, Guo L, Zhu X, Liu J (2021) Cptr: full transformer network for image captioning. arXiv:2101.10804"},{"key":"4010_CR47","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":"4010_CR48","doi-asserted-by":"crossref","unstructured":"Zhou L, Kalantidis Y, Chen X, Corso JJ, Rohrbach M (2019) Grounded video description. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6578\u20136587","DOI":"10.1109\/CVPR.2019.00674"},{"key":"4010_CR49","doi-asserted-by":"crossref","unstructured":"Gao L, Fan K, Song J, Liu X, Xu X, Shen HT (2019) Deliberate attention networks for image captioning. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8320\u2013 8327","DOI":"10.1609\/aaai.v33i01.33018320"},{"key":"4010_CR50","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.neucom.2020.06.112","volume":"413","author":"W Cai","year":"2020","unstructured":"Cai W, Liu Q (2020) Image captioning with semantic-enhanced features and extremely hard negative examples. Neurocomputing 413:31\u201340","journal-title":"Neurocomputing"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04010-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04010-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04010-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T09:30:32Z","timestamp":1682847032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04010-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,12]]},"references-count":50,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["4010"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04010-4","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,12]]},"assertion":[{"value":"15 July 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}