{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:15:38Z","timestamp":1754151338978,"version":"3.41.2"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board (SERB) Mathematical Research Impact Centric Support","doi-asserted-by":"publisher","award":["MTR\/2021\/000604"],"award-info":[{"award-number":["MTR\/2021\/000604"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3582655","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T13:35:03Z","timestamp":1750772103000},"page":"122071-122087","source":"Crossref","is-referenced-by-count":0,"title":["News Image Captioning via Separate Attention on Entity Categories"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9608-7101","authenticated-orcid":false,"given":"Sonali","family":"Ajankar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2801-0687","authenticated-orcid":false,"given":"Tanima","family":"Dutta","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. ICML","volume":"3","author":"Xu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3282444"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3423790"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3018752"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.542"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547883"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413576"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2721945"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.419"},{"key":"ref18","article-title":"Wikipedia2Vec: An efficient toolkit for learning and visualizing the embeddings of words and entities from Wikipedia","author":"Yamada","year":"2018","journal-title":"arXiv:1812.06280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3332098"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3128178"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611768"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref27","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref29","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2999568"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067607"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3164787"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref37","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref39","article-title":"Scaling instruction-finetuned language models","author":"Won Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref40","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref42","first-page":"1","article-title":"Exploring diverse in-context configurations for image captioning","volume-title":"Proc. Adv. NIPS","author":"Xu"},{"key":"ref43","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref44","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref46","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. conf. Mach. Learn.","author":"Touvron"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. conf. Mach. Learn.","author":"Radford"},{"key":"ref50","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. conf. Mach. Learn.","author":"Li"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref53","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref54","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. conf. Mach. Learn.","author":"Jia"},{"key":"ref55","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","author":"Yuksekgonul","year":"2022","journal-title":"arXiv:2210.01936"},{"key":"ref56","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.176"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013321"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3093650"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301279"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108429"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.450"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.67"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.818"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.162"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3426655"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref72","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Adv. NeurIPS","volume":"26","author":"Mikolov"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref74","first-page":"1","article-title":"SpaCy: Industrial-strength natural language processing in Python","author":"Honnibal","year":"2020"},{"key":"ref75","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref79","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text summarization Branches Out","author":"Lin"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref81","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-336156-1.50061-6"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2501"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/mmul.2024.3363429"},{"key":"ref86","first-page":"1","article-title":"A simple but tough-to-beat baseline for sentence embeddings","volume-title":"Proc. Conf. Learn. Represent.","author":"Arora"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11048780.pdf?arnumber=11048780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:46:58Z","timestamp":1752860818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11048780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3582655","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}