{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:11:40Z","timestamp":1778080300434,"version":"3.51.4"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"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":[[2024,7,8]]},"DOI":"10.23919\/fusion59988.2024.10706514","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T17:19:50Z","timestamp":1728667190000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["QCaption: Video Captioning and Q&A through Fusion of Large Multimodal Models"],"prefix":"10.23919","author":[{"given":"Jiale","family":"Wang","sequence":"first","affiliation":[{"name":"Q Team, Home Team Science and Technology Agency,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gee Wah","family":"Ng","sequence":"additional","affiliation":[{"name":"Q Team, Home Team Science and Technology Agency,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lee Onn","family":"Mak","sequence":"additional","affiliation":[{"name":"Q Team, Home Team Science and Technology Agency,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Randall","family":"Cher","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Department of Computer Science and Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding Hei Ryan","family":"Ng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Department of Computer Science and Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davis","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Department of Computer Science and Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","author":"Chowdhery","year":"2022","journal-title":"Palm: Scaling language modeling with pathways"},{"key":"ref3","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021","journal-title":"Proceedings of Machine Learning Research"},{"key":"ref5","volume-title":"OpenAI. Gpt-4 technical report","year":"2023"},{"key":"ref6","author":"Team","year":"2023","journal-title":"Gemini: A family of highly capable multimodal models"},{"key":"ref7","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3522295"},{"key":"ref9","author":"Peng","year":"2023","journal-title":"Instruction tuning with gpt-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.prime.2023.100372"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iemtronics52119.2021.9422600"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/I2CT51068.2021.9417907"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv1tjrvk1.47"},{"key":"ref19","author":"Shen","year":"2023","journal-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face"},{"key":"ref20","author":"Ye","year":"2023","journal-title":"mplug-owl: Modularization empowers large language models with multimodality"},{"key":"ref21","author":"Peng","year":"2023","journal-title":"Kosmos-2: Grounding multimodal large language models to the world"},{"key":"ref22","author":"Li","year":"2023","journal-title":"Deep model fusion: A survey"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s23052381"},{"key":"ref24","author":"Jain","year":"2021","journal-title":"Github-keplerlab\/katna: Tool for automating common video key-frame extraction, video compression and image auto-crop\/image-resize tasks"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"}],"event":{"name":"2024 27th International Conference on Information Fusion (FUSION)","location":"Venice, Italy","start":{"date-parts":[[2024,7,8]]},"end":{"date-parts":[[2024,7,11]]}},"container-title":["2024 27th International Conference on Information Fusion (FUSION)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10706250\/10706251\/10706514.pdf?arnumber=10706514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T08:51:35Z","timestamp":1747731095000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":29,"URL":"https:\/\/doi.org\/10.23919\/fusion59988.2024.10706514","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}