{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:41:41Z","timestamp":1781174501270,"version":"3.54.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s11042-022-12042-8","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T21:02:45Z","timestamp":1644872565000},"page":"10051-10069","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Assamese news image caption generation using attention mechanism"],"prefix":"10.1007","volume":"81","author":[{"given":"Ringki","family":"Das","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thoudam Doren","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,14]]},"reference":[{"key":"12042_CR1","doi-asserted-by":"crossref","unstructured":"Amritkar C, Jabade V (2018) Image caption generation using deep learning technique. In: 2018 Fourth international conference on computing communication control and automation (ICCUBEA), IEEE, pp 1\u20134","DOI":"10.1109\/ICCUBEA.2018.8697360"},{"key":"12042_CR2","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In Proc international conference on learning representations arXiv:1409.0473"},{"key":"12042_CR3","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.neucom.2018.05.080","volume":"311","author":"S Bai","year":"2018","unstructured":"Bai S, An S (2018) A survey on automatic image caption generation. Neurocomputing 311:291\u2013304. Elsevier","journal-title":"Neurocomputing"},{"key":"12042_CR4","unstructured":"Batra V, He Y, Vogiatzis G (2018) Neural caption generation for news images. In: Proceedings of the Eleventh international conference on language resources and evaluation (LREC 2018)"},{"key":"12042_CR5","unstructured":"Chen X, Fang H, Lin T-Y, Vedantam R, Gupta S, Doll\u00e1r P, Lawrence ZC (2015) Microsoft coco captions: Data collection and evaluation server. arXiv:1504.00325"},{"key":"12042_CR6","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":"12042_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.13053\/cys-23-3-3269","volume":"23","author":"R Dhir","year":"2019","unstructured":"Dhir R, Mishra SK, Saha S, Bhattacharyya P (2019) A deep attention based framework for image caption generation in hindi language. Computaci\u00f3n y Sistemas 23:3","journal-title":"Computaci\u00f3n y Sistemas"},{"key":"12042_CR8","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) From captions to visual concepts and back. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1473\u20131482","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"12042_CR9","unstructured":"Feng Y, Lapata M (2010) How many words is a picture worth? automatic caption generation for news images. In: Proceedings of the 48th annual meeting of the Association for Computational Linguistics, pp 1239\u20131249"},{"issue":"4","key":"12042_CR10","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1109\/TPAMI.2012.118","volume":"35","author":"Y Feng","year":"2012","unstructured":"Feng Y, Lapata M (2012) Automatic caption generation for news images. IEEE Transactions on Pattern Analysis and Machine Intelligence 35 (4):797\u2013812. IEEE","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"12042_CR11","doi-asserted-by":"crossref","unstructured":"Gorokhovatskyi O, Peredrii O (2018) Shallow convolutional neural networks for pattern recognition problems. In: 2018 IEEE Second international conference on data stream mining & processing (DSMP), IEEE, pp 459\u2013463","DOI":"10.1109\/DSMP.2018.8478540"},{"key":"12042_CR12","unstructured":"Haripriya B, Srushti GM, Haseeb S, Prakash MM Image Captioning using Deep Learning"},{"issue":"02","key":"12042_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1142\/S0218488598000094","volume":"6","author":"S Hochreiter","year":"1998","unstructured":"Hochreiter S (1998) The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 6(02):107\u2013116","journal-title":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems"},{"issue":"8","key":"12042_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"12042_CR15","unstructured":"Holzinger A, Saranti A, Mueller H (2021) KANDINSKY Patterns\u2013An experimental exploration environment for Pattern Analysis and Machine Intelligence. arXiv:2103.00519"},{"key":"12042_CR16","doi-asserted-by":"crossref","unstructured":"Kamal AH, Jishan Md, Mansoor N et al (2020) TextMage: The Automated Bangla Caption Generator Based On Deep Learning. arXiv:2010.08066","DOI":"10.1109\/DASA51403.2020.9317108"},{"key":"12042_CR17","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":"11","key":"12042_CR18","first-page":"7","volume":"100","author":"AK Kohakade","year":"2014","unstructured":"Kohakade AK, Emmanuel M (2014) Content based caption generation for images embedded in news articles. Int J Comput Appl 100(11):7\u201315","journal-title":"Int J Comput Appl"},{"issue":"4","key":"12042_CR19","first-page":"2183","volume":"56","author":"X Lu","year":"2017","unstructured":"Lu X, Wang B, Zheng X, Li X (2017) . Exploring models and data for remote sensing image caption generation 56(4):2183\u20132195. IEEE","journal-title":"Exploring models and data for remote sensing image caption generation"},{"key":"12042_CR20","doi-asserted-by":"crossref","unstructured":"Lu D, Whitehead S, Huang L, Ji H, Chang S-F (2018) Entity-aware image caption generation. arXiv:1804.07889","DOI":"10.18653\/v1\/D18-1435"},{"key":"12042_CR21","doi-asserted-by":"crossref","unstructured":"Luong M-T, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. arXiv:1508.04025","DOI":"10.18653\/v1\/D15-1166"},{"key":"12042_CR22","unstructured":"Mansimov E, Parisotto E, Ba JL, Salakhutdinov R (2015) Generating images from captions with attention. arXiv:1511.02793"},{"key":"12042_CR23","doi-asserted-by":"publisher","unstructured":"Meetei LS, Singh TD, Bandyopadhyay S (2019) Extraction and identification of manipuri and mizo texts from scene and document images. In: Deka B, Maji P, Mitra S, Bhattacharyya DK, Bora PK, Pal SK (eds) PReMI 2019. LNCS. https:\/\/doi.org\/10.1007\/978-3-030-34869-4_44, vol 11941. Springer, Cham, pp 405\u2013414","DOI":"10.1007\/978-3-030-34869-4_44"},{"key":"12042_CR24","doi-asserted-by":"crossref","unstructured":"Meetei LS, Singh TD, Bandyopadhyay S (2019) WAT2019: English-Hindi translation on Hindi visual genome dataset. In: Proceedings of the 6th workshop on asian translation, pp 181\u2013188","DOI":"10.18653\/v1\/D19-5224"},{"key":"12042_CR25","doi-asserted-by":"crossref","unstructured":"Miyazaki T, Shimizu N (2016) Cross-lingual image caption generation. In: Proceedings of the 54th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp 1780\u20131790","DOI":"10.18653\/v1\/P16-1168"},{"key":"12042_CR26","unstructured":"O\u2019Shea K, Nash R (2015) An introduction to convolutional neural networks. arXiv:1511.08458"},{"key":"12042_CR27","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 of the Association for Computational Linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"12042_CR28","unstructured":"Peng H, Li N (2016) Generating chinese captions for flickr30k images"},{"key":"12042_CR29","unstructured":"Prajapati K, Wadekar S, Bobhate B, Mhatre A Auto-Caption Generation for News Images"},{"key":"12042_CR30","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1016\/j.procs.2019.06.100","volume":"154","author":"M Rahman","year":"2019","unstructured":"Rahman M, Mohammed N, Mansoor N, Momen S (2019) Chittron: An automatic bangla image captioning system. Procedia Comput Sci 154:636\u2013642. Elsevier","journal-title":"Procedia Comput Sci"},{"key":"12042_CR31","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky A (2020) Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physica D: Nonlinear Phenomena 404:132306. Elsevier","journal-title":"Physica D: Nonlinear Phenomena"},{"key":"12042_CR32","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"12042_CR33","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"12042_CR34","doi-asserted-by":"publisher","unstructured":"Singh A, Meetei LS, Singh TD, Bandyopadhyay S (2021) Generation and evaluation of hindi image captions of visual genome. In: Maji AK, Saha G, Das S, Basu S, Tavares JMRS (eds) Proceedings of the international conference on computing and communication systems. Lecture Notes in Networks and Systems. https:\/\/doi.org\/10.1007\/978-981-33-4084-8_7, vol 170. Springer, Singapore","DOI":"10.1007\/978-981-33-4084-8_7"},{"key":"12042_CR35","unstructured":"Soh M (2016) Learning CNN-LSTM architectures for image caption generation. Dept Comput Sci, Stanford Univ., Stanford, CA, USA, Tech. Rep"},{"key":"12042_CR36","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":"12042_CR37","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: A neural image caption generator, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"12042_CR38","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":"12042_CR39","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"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12042-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12042-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12042-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T17:37:10Z","timestamp":1648057030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12042-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,14]]},"references-count":39,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["12042"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12042-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,14]]},"assertion":[{"value":"6 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}