{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:39:00Z","timestamp":1776688740261,"version":"3.51.2"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032184795","type":"print"},{"value":"9783032184801","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-18480-1_50","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T11:47:34Z","timestamp":1776685654000},"page":"494-504","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AsCap-GPT2: A Data-Efficient Assamese Image Captioning Framework with\u00a0Pretrained GPT-2"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1159-3118","authenticated-orcid":false,"given":"Pankaj","family":"Choudhury","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0635-938X","authenticated-orcid":false,"given":"Prabhanjan","family":"Jadhav","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2885-0026","authenticated-orcid":false,"given":"Prithwijit","family":"Guha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5869-1057","authenticated-orcid":false,"given":"Sukumar","family":"Nandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"50_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"50_CR2","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.: A survey on automatic image caption generation. Neurocomputing 311, 291\u2013304 (2018)","journal-title":"Neurocomputing"},{"key":"50_CR3","unstructured":"Chandramouli, C., General, R.: Census of India. Rural Urban Distribution of Population, Provisional Population Total. New Delhi: Office of the Registrar General and Census Commissioner, India (2011)"},{"key":"50_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Guo, H., Yi, K., Li, B., Elhoseiny, M.: VisualGPT: data-efficient adaptation of pretrained language models for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18030\u201318040 (2022)","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"50_CR5","unstructured":"Choudhury, P., Guha, P., Nandi, S.: Image caption synthesis for low resource assamese language using Bi-LSTM with bilinear attention. In: Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pp. 743\u2013752 (2023)"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Choudhury, P., Guha, P., Nandi, S.: Impact of language-specific training on image caption synthesis: a case study on low-resource assamese language. Int. J. Asian Lang. Process. (2024)","DOI":"10.1142\/S2717554524500048"},{"key":"50_CR7","doi-asserted-by":"crossref","unstructured":"Choudhury, P., Guha, P., Nandi, S.: Exploring semantic attributes for image caption synthesis in low-resource assamese language. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 24(4) (2025)","DOI":"10.1145\/3717612"},{"key":"50_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"50_CR9","doi-asserted-by":"publisher","unstructured":"Doddapaneni, S., et al.: Towards leaving no Indic language behind: building monolingual corpora, benchmark and models for Indic languages. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12402\u201312426. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.693, https:\/\/aclanthology.org\/2023.acl-long.693\/","DOI":"10.18653\/v1\/2023.acl-long.693"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., Lu, H.: Normalized and geometry-aware self-attention network for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10327\u201310336 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"50_CR11","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"50_CR13","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"50_CR14","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"50_CR15","doi-asserted-by":"crossref","unstructured":"Luo, Z., Hu, Z., Xi, Y., Zhang, R., Ma, J.: I-tuning: tuning frozen language models with image for lightweight image captioning. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096424"},{"issue":"10","key":"50_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3622936","volume":"22","author":"SK Mishra","year":"2023","unstructured":"Mishra, S.K., Chakraborty, S., Saha, S., Bhattacharyya, P.: GAGPT-2: a geometric attention-based GPT-2 framework for image captioning in Hindi. ACM Trans. Asian Low-Resource Lang. Inf. Process. 22(10), 1\u201316 (2023)","journal-title":"ACM Trans. Asian Low-Resource Lang. Inf. Process."},{"key":"50_CR17","unstructured":"Nath, P., Adhikary, P.K., Dadure, P., Pakray, P., Manna, R., Bandyopadhyay, S.: Image caption generation for low-resource assamese language. In: Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022), pp. 263\u2013272 (2022)"},{"key":"50_CR18","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"issue":"8","key":"50_CR19","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"50_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"50_CR21","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"50_CR22","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"50_CR23","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-18480-1_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T11:47:44Z","timestamp":1776685664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-18480-1_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032184795","9783032184801"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-18480-1_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PReMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Machine Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delhi","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"premi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/premi25-git-dev-ashirbad97s-projects.vercel.app\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}