{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T16:12:09Z","timestamp":1762445529094,"version":"3.40.2"},"reference-count":52,"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\/100018276","name":"Indian Institute of Technology Patna and Credit Rating Information Services of India Limited","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018276","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.2025.3551124","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T17:44:46Z","timestamp":1741887886000},"page":"48367-48379","source":"Crossref","is-referenced-by-count":1,"title":["Presenting an Order-Aware Multimodal Fusion Framework for Financial Advisory Summarization With an Exclusive Video Dataset"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3429-306X","authenticated-orcid":false,"given":"Sarmistha","family":"Das","sequence":"first","affiliation":[{"name":"CSE Department, IIT Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samrat","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Ramakrishna Mission Vivekananda Educational and Research Institute, Belur, West Bengal, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhisek","family":"Tiwari","sequence":"additional","affiliation":[{"name":"CSE Department, IIT Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R. E. Zera Marveen","family":"Lynghoi","sequence":"additional","affiliation":[{"name":"CSE Department, IIT Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5494-9391","authenticated-orcid":false,"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[{"name":"CSE Department, IIT Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zak","family":"Murad","sequence":"additional","affiliation":[{"name":"CRISIL Ltd., Mumbai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alka","family":"Maurya","sequence":"additional","affiliation":[{"name":"CRISIL Ltd., Mumbai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.2018.1440766"},{"key":"ref2","first-page":"656","article-title":"Teaching and learning with audiovisual media: Empirical analysis of the effectiveness of podcasts in financial literacy","volume-title":"Josef Ne\u0161leha. Eur. Financial Syst. Proc. 16th Int. Sci. Conf.","author":"Zureck"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119227205"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1891\/JFCP-18-00049"},{"key":"ref5","first-page":"21","article-title":"Towards human-centered summarization: A case study on financial news","volume-title":"Proc. 1st Workshop Bridging Hum.\u2013Comput. Interact. Natural Lang. Process.","author":"Passali"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/joitmc7030165"},{"key":"ref7","first-page":"1","article-title":"An exploration of automatic text summarization of financial reports","volume-title":"Proc. 3rd Workshop Financial Technol. Natural Lang. Process.","author":"Abdaljalil"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.643"},{"key":"ref9","article-title":"BloombergGPT: A large language model for finance","author":"Wu","year":"2023","journal-title":"arXiv:2303.17564"},{"key":"ref10","article-title":"FinGPT: Democratizing Internet-scale data for financial large language models","author":"Liu","year":"2023","journal-title":"arXiv:2307.10485"},{"key":"ref11","article-title":"PIXIU: A large language model, instruction data and evaluation benchmark for finance","author":"Xie","year":"2023","journal-title":"arXiv:2306.05443"},{"key":"ref12","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3502289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.05.034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103517"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.conctc.2018.08.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587324"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref20","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.69"},{"key":"ref22","article-title":"FinBERT: A pretrained language model for financial communications","author":"Yang","year":"2020","journal-title":"arXiv:2006.08097"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1993077.1993078"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref25","article-title":"ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"2021","journal-title":"arXiv:2107.02137"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412879"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413752"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1448"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref31","first-page":"2528","article-title":"Multimodal attention for fusion of audio and spatiotemporal features for video description","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Hori"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref34","first-page":"3843","article-title":"Solving quantitative reasoning problems with language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lewkowycz"},{"key":"ref35","article-title":"Least-to-Most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv:2205.10625"},{"key":"ref36","first-page":"24824","article-title":"Chain-of-Thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5220\/0006922101420153"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380128"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10192028"},{"key":"ref40","first-page":"133","article-title":"Wealth guide: A sophisticated language model solution for financial trading decisions","volume-title":"Proc. 8th Financial Technol. Natural Lang. Process., 1st Agent AI Scenario Planning","author":"Das"},{"key":"ref41","first-page":"1459","article-title":"Opensmile: The Munich versatile and fast open-source audio feature extractor","volume-title":"Proc. 18th ACM Int. Conf. Multimedia","author":"Eyben"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445347"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"},{"key":"ref45","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019","journal-title":"arXiv:1910.13461"},{"key":"ref46","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"arXiv:1508.07909"},{"issue":"1","key":"ref47","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.411"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"ref50","article-title":"Hierarchical3D adapters for long video-to-text summarization","author":"Papalampidi","year":"2022","journal-title":"arXiv:2210.04829"},{"key":"ref51","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10925332.pdf?arnumber=10925332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:43:33Z","timestamp":1742841813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10925332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3551124","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}