{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T05:33:21Z","timestamp":1736573601488,"version":"3.32.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,20]]},"DOI":"10.1109\/icbase63199.2024.10762462","type":"proceedings-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:45:22Z","timestamp":1732646722000},"page":"860-865","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Representation Learning by Hybrid Transformer with Multi-level Fusion"],"prefix":"10.1109","author":[{"given":"Yi","family":"Wu","sequence":"first","affiliation":[{"name":"State Grid Quzhou Power Supply Company Power Dispatch Control Center,QuZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongquan","family":"Xu","sequence":"additional","affiliation":[{"name":"State Grid Quzhou Power Supply Company Power Dispatch Control Center,QuZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Grid Quzhou Power Supply Company Power Dispatch Control Center,QuZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Self-chained image-language model for video localization and question answering","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv:2305.06988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00806"},{"key":"ref4","first-page":"8632","article-title":"On uni-modal feature learning in supervised multi-modal learning","volume-title":"International Conference on Machine Learning, ICML 2023","volume":"202","author":"Du"},{"key":"ref5","article-title":"Improving multimodal accuracy through modality pre-training and attention","volume":"abs\/2011.06102","author":"Ismail","year":"2020","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3101421"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref8","article-title":"Provable dynamic fusion for low-quality multimodal data","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2306.02050"},{"key":"ref9","article-title":"Read, look or listen? what\u2019s needed for solving a multimodal dataset","volume":"abs\/2307.04532","author":"Madvil","year":"2023","journal-title":"CoRR"},{"key":"ref10","article-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2403.00425"},{"key":"ref11","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2402.11411"},{"key":"ref12","article-title":"Multimodal clinical trial outcome prediction with large language models","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv:2402.06512"},{"key":"ref13","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv:2310.00754"},{"key":"ref14","article-title":"How many unicorns are in this image? a safety evaluation benchmark for vision llms","author":"Tu","year":"2023","journal-title":"arXiv preprint arXiv:2311.16101"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.25"},{"key":"ref16","article-title":"On uni-modal feature learning in supervised multi-modal learning","author":"Du","year":"2023","journal-title":"arXiv preprint arXiv:2305.01233"},{"key":"ref17","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably)","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref20","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv preprint arXiv:1908.03557"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref22","article-title":"Vilbert: Pretraining taskagnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icsmc.2005.1571679"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref30","first-page":"51985204","article-title":"Efficient large-scale multimodal classification","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18) and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI18)","author":"Kiela"}],"event":{"name":"2024 5th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)","start":{"date-parts":[[2024,9,20]]},"location":"Wenzhou, China","end":{"date-parts":[[2024,9,22]]}},"container-title":["2024 5th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10761118\/10761986\/10762462.pdf?arnumber=10762462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T19:50:22Z","timestamp":1736538622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10762462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,20]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icbase63199.2024.10762462","relation":{},"subject":[],"published":{"date-parts":[[2024,9,20]]}}}