{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:04:36Z","timestamp":1749182676501,"version":"3.41.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031789397","type":"print"},{"value":"9783031789403","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78940-3_47","type":"book-chapter","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T06:07:12Z","timestamp":1749103632000},"page":"445-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Self-attention Training in Transformers for Image Captioning Using ViT and BERT"],"prefix":"10.1007","author":[{"given":"Madduri","family":"Deepika","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N.","family":"Purushotham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ch.","family":"Sarada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Modem Sai","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jyothirmai","family":"Digumarthi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gottimukkula Sravan","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"47_CR1","doi-asserted-by":"crossref","unstructured":"Sargar, O., Kinger, S.: Image captioning methods and metrics. In: 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), pp. 522\u2013526. IEEE (2021)","DOI":"10.1109\/ESCI50559.2021.9396839"},{"issue":"6","key":"47_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. (CsUR) 51(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CsUR)"},{"key":"47_CR3","doi-asserted-by":"crossref","unstructured":"Wang, C., Yang, H., Bartz, C., Meinel, C.: Image captioning with deep bidirectional LSTMs. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 988\u2013997 (2016)","DOI":"10.1145\/2964284.2964299"},{"key":"47_CR4","doi-asserted-by":"crossref","unstructured":"Sharma, H., Agrahari, M., Singh, S.K., Firoj, M., Mishra, R.K.: Image captioning: a comprehensive survey. In: 2020 International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC), pp. 325\u2013328. IEEE (2020)","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"47_CR5","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"47_CR6","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4894\u20134902 (2017)","DOI":"10.1109\/ICCV.2017.524"},{"key":"47_CR7","doi-asserted-by":"crossref","unstructured":"Chohan, M., Khan, A., Mahar, M.S., Hassan, S., Ghafoor, A., Khan, M.: Image captioning using deep learning: a systematic. Image 11(5) (2020)","DOI":"10.14569\/IJACSA.2020.0110537"},{"issue":"5","key":"47_CR8","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, J.K.: Neural attention for image captioning: review of outstanding methods. Artif. Intell. Rev. 55(5), 3833\u20133862 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"47_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101699","volume":"53","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Xiao, B., Bouferguene, A., Al-Hussein, M., Li, H.: Vision-based method for semantic information extraction in construction by integrating deep learning object detection and image captioning. Adv. Eng. Inform. 53, 101699 (2022)","journal-title":"Adv. Eng. Inform."},{"key":"47_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, G., Cai, J., Chen, T.: An empirical study of language cnn for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1222\u20131231 (2017)","DOI":"10.1109\/ICCV.2017.138"},{"key":"47_CR11","doi-asserted-by":"publisher","unstructured":"Periannasamy, S.M., et al.: Analysis of artificial intelligence enabled intelligent sixth generation (6G) wireless communication networks. In: 2022 IEEE International Conference on Data Science and Information System (ICDSIS), Hassan, India, pp. 1\u20138 (2022). https:\/\/doi.org\/10.1109\/ICDSIS55133.2022.9915945","DOI":"10.1109\/ICDSIS55133.2022.9915945"},{"key":"47_CR12","doi-asserted-by":"publisher","unstructured":"Gothane, S.: Content summarization: journey toward word clouds. In: Kumar, A., Ghinea, G., Merugu, S., Hashimoto, T. (eds.) Proceedings of the International Conference on Cognitive and Intelligent Computing. Cognitive Science and Technology. Springer, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-19-2350-0_46","DOI":"10.1007\/978-981-19-2350-0_46"},{"key":"47_CR13","doi-asserted-by":"crossref","unstructured":"Simi Margarat, G., et al.: Early diagnosis of tuberculosis using deep learning approach for iot based healthcare applications. Comput. Intell. Neurosci. 2022 (2022)","DOI":"10.1155\/2022\/3357508"},{"issue":"1","key":"47_CR14","doi-asserted-by":"publisher","first-page":"2598465","DOI":"10.1155\/2022\/2598465","volume":"2022","author":"C Monga","year":"2022","unstructured":"Monga, C., et al.: Secure techniques for channel encryption in wireless body area network without the certificate. Wirel. Commun. Mobile Comput. 2022(1), 2598465 (2022)","journal-title":"Wirel. Commun. Mobile Comput."},{"key":"47_CR15","doi-asserted-by":"publisher","unstructured":"Patel, P., Sivaiah, B., Patel, R.: Approaches for finding optimal number of clusters using k-means and agglomerative hierarchical clustering techniques. In: 2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP), Hyderabad, India, pp. 1\u20136 (2022). https:\/\/doi.org\/10.1109\/ICICCSP53532.2022.9862439","DOI":"10.1109\/ICICCSP53532.2022.9862439"},{"key":"47_CR16","doi-asserted-by":"publisher","unstructured":"Madala, S., Suvarna Vani, K., Jalapally, P., Srujan Raju, K., Somasekhar, G.: Framework for diabetic retinopathy classification. In: Satapathy, S.C., Bhateja, V., Favorskaya, M.N., Adilakshmi, T. (eds.) Smart Intelligent Computing and Applications, Volume 2: Proceedings of Fifth International Conference on Smart Computing and Informatics (SCI 2021), pp. 593\u2013601. Springer Nature Singapore, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-16-9705-0_58","DOI":"10.1007\/978-981-16-9705-0_58"},{"key":"47_CR17","doi-asserted-by":"publisher","unstructured":"Kolli, C.S., Raghunath, M.P., Meenakshi, S., Maheswari, K., Britto, C.F., Kushwaha, S.: Efficient development of supervised learning algorithm for kidney stone prediction. In: 2022 International Conference on Inventive Computation Technologies (ICICT), Nepal, pp. 1373\u20131379 (2022). https:\/\/doi.org\/10.1109\/ICICT54344.2022.9850573","DOI":"10.1109\/ICICT54344.2022.9850573"},{"key":"47_CR18","doi-asserted-by":"publisher","unstructured":"Sathishkumar, A., Majji, S., Radhika Patnala, T., Rao Karanam, S., Kumar, A., Malyadri, M.: Experimentation methodology of orthogonal frequency division multiplexing signals process using radio over fiber (RoF) system. In: 2022 International Virtual Conference on Power Engineering Computing and Control: Developments in Electric Vehicles and Energy Sector for Sustainable Future (PECCON), Chennai, India, pp. 01\u201305 (2022). https:\/\/doi.org\/10.1109\/PECCON55017.2022.9850996","DOI":"10.1109\/PECCON55017.2022.9850996"},{"key":"47_CR19","doi-asserted-by":"publisher","unstructured":"Avanija, J., Madhavi, K.R., Sunitha, G., Sangapu, S.C., Raju, S.: Facial expression recognition using convolutional neural network. In: 2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR), Hyderabad, India, pp. 1\u20137 (2022). https:\/\/doi.org\/10.1109\/ICAITPR51569.2022.9844221","DOI":"10.1109\/ICAITPR51569.2022.9844221"},{"key":"47_CR20","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/978-981-19-1559-8_37","volume-title":"Data Engineering and Intelligent Computing: Proceedings of 5th ICICC 2021, Volume 1","author":"L Tiwari","year":"2022","unstructured":"Tiwari, L., Awasthi, V., Patra, R.K., Miri, R., Raja, H., Bhaskar, N.: Lung cancer detection using deep convolutional neural networks. In: Bhateja, V., Wee, L.K., Lin, J.C.-W., Satapathy, S.C., Rajesh, T.M. (eds.) Data Engineering and Intelligent Computing: Proceedings of 5th ICICC 2021, Volume 1, pp. 373\u2013385. Springer Nature Singapore, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-19-1559-8_37"},{"key":"47_CR21","doi-asserted-by":"crossref","unstructured":"Elbedwehy, S., Medhat, T., Hamza, T., Alrahmawy, M.F.: Efficient image captioning based on vision transformer models. Comput. Mater. Continua 73(1) (2022)","DOI":"10.32604\/cmc.2022.029313"},{"issue":"17","key":"47_CR22","doi-asserted-by":"publisher","first-page":"5978","DOI":"10.3390\/app10175978","volume":"10","author":"V Atliha","year":"2020","unstructured":"Atliha, V., \u0160e\u0161ok, D.: Text augmentation using BERT for image captioning. Appl. Sci. 10(17), 5978 (2020)","journal-title":"Appl. Sci."},{"key":"47_CR23","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-030-68780-9_32","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10\u201315, 2021, Proceedings, Part VI","author":"M Kalimuthu","year":"2021","unstructured":"Kalimuthu, M., Mogadala, A., Mosbach, M., Klakow, D.: Fusion models for improved image captioning. In: Del Bimbo, A., et al. (eds.) Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10\u201315, 2021, Proceedings, Part VI, pp. 381\u2013395. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68780-9_32"},{"key":"47_CR24","doi-asserted-by":"crossref","unstructured":"Ragab, M., Addas, A.: Low complexity encoder with multilabel classification and image captioning model. Comput. Mater. Continua 72(3) (2022)","DOI":"10.32604\/cmc.2022.026602"},{"key":"47_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118669","volume":"212","author":"A Salaberria","year":"2023","unstructured":"Salaberria, A., Azkune, G., de Lacalle, O.L., Soroa, A., Agirre, E.: Image captioning for effective use of language models in knowledge-based visual question answering. Expert Syst. Appl. 212, 118669 (2023)","journal-title":"Expert Syst. Appl."},{"key":"47_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104404","volume":"121","author":"G Sunitha","year":"2022","unstructured":"Sunitha, G., Geetha, K., Neelakandan, S., Pundir, A.K.S., Hemalatha, S., Kumar, V.: Intelligent deep learning based ethnicity recognition and classification using facial images. Image Vis. Comput. 121, 104404 (2022)","journal-title":"Image Vis. Comput."},{"issue":"7","key":"47_CR27","first-page":"1708","volume":"12","author":"MD Deepa","year":"2021","unstructured":"Deepa, M.D.: Bidirectional encoder representations from transformers (BERT) language model for sentiment analysis task. Turk. J. Comput. Math. Educ. (TURCOMAT) 12(7), 1708\u20131721 (2021)","journal-title":"Turk. J. Comput. Math. Educ. (TURCOMAT)"}],"container-title":["Lecture Notes in Networks and Systems","Bio-Inspired Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78940-3_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T06:07:19Z","timestamp":1749103639000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78940-3_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031789397","9783031789403"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78940-3_47","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"6 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IBICA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovations in Bio-Inspired Computing and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kochi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ibica2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mirlabs.net\/ibica23\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}