{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:50:56Z","timestamp":1773791456972,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"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":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342816","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"972-977","source":"Crossref","is-referenced-by-count":0,"title":["FIQ: Fundamental Question Generation with the Integration of Question Embeddings for Video Question Answering"],"prefix":"10.1109","author":[{"given":"Juyoung","family":"Oh","sequence":"first","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}]},{"given":"Ho-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01782"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2395752"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29954"},{"key":"ref4","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Li"},{"key":"ref5","first-page":"9864","article-title":"Text-infused attention and foreground-aware modeling for zero-shot temporal action detection","volume":"37","author":"Lee","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref7","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"Akbari","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref10","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_11"},{"key":"ref12","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/72.557671"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/5326.760572"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref17","first-page":"13448","article-title":"GraphAdapter: Tuning vision-language models with dual knowledge graph","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01282"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.227"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.902945"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001490000022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.287"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.142"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.8"},{"issue":"140","key":"ref27","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref28","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Radford"},{"key":"ref31","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Int. Conf. Learn. Represent. (ICLR)","volume":"1","author":"Hu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.450"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342816.pdf?arnumber=11342816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:17:13Z","timestamp":1773778633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342816","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}