{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:23:00Z","timestamp":1761895380242,"version":"build-2065373602"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210080","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["VidCtx: Context-aware Video Question Answering with Image Models"],"prefix":"10.1109","author":[{"given":"Andreas","family":"Goulas","sequence":"first","affiliation":[{"name":"CERTH-ITI & Queen Mary University of London,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasileios","family":"Mezaris","sequence":"additional","affiliation":[{"name":"CERTH-ITI,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Patras","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.18653\/v1\/2024.acl-long.679"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"year":"2024","author":"Zhang","article-title":"Video instruction tuning with synthetic data","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR52733.2024.02095"},{"year":"2024","author":"Wang","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref8","article-title":"Self-chained image-language model for video localization and question answering","volume":"36","author":"Yu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/cvpr52734.2025.00311"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/978-3-031-72989-8_4"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.18653\/v1\/2025.findings-acl.294"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.18653\/v1\/2024.findings-acl.555"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.18653\/v1\/2024.acl-long.818"},{"key":"ref15","first-page":"31210","article-title":"Large language models can be easily distracted by irrelevant context","volume-title":"Int. Conf. on Machine Learning","author":"Shi"},{"key":"ref16","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.18653\/v1\/2023.findings-emnlp.734"},{"key":"ref18","first-page":"5168","article-title":"Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICME57554.2024.10688334"},{"volume-title":"Forty-first International Conference on Machine Learning","author":"Fei","article-title":"Video-of-thought: Step-by-step video reasoning from perception to cognition","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"ref22","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR52733.2024.01367"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR46437.2021.00965"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICCV51070.2023.01099"},{"year":"2024","author":"Wu","article-title":"Star: A benchmark for situated reasoning in real-world videos","key":"ref27"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICCV51070.2023.01428"},{"year":"2022","author":"Wang","article-title":"Internvideo: General video foundation models via generative and discriminative learning","key":"ref29"},{"year":"2024","author":"Liu","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","key":"ref30"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210080.pdf?arnumber=11210080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:48:54Z","timestamp":1761889734000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210080","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}