{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:55:08Z","timestamp":1777888508638,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00151","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1537-1547","source":"Crossref","is-referenced-by-count":0,"title":["VAGUE: Visual Contexts Clarify Ambiguous Expressions"],"prefix":"10.1109","author":[{"given":"Heejeong","family":"Nam","sequence":"first","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwoo","family":"Ahn","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keummin","family":"Ka","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwan","family":"Chung","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjae","family":"Yu","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Text is not all you need: Multimodal prompting helps 11 ms understand humor","author":"Baluja","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","author":"Betker","journal-title":"Improving image generation with better captions"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3233\/faia240573"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.481"},{"key":"ref5","article-title":"Through the theory of mind\u2019s eye: Reading minds with multimodal video large language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/opmi_a_00160"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29748"},{"key":"ref9","article-title":"Boss: A benchmark for human belief prediction in object-context scenarios","author":"Duan","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0595"},{"key":"ref12","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.89"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.56"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.851"},{"key":"ref18","author":"Khanam","year":"2024","journal-title":"Yolov11: An overview of the key architectural enhancements"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.411"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26526"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.flp-1.20"},{"key":"ref22","first-page":"87874","article-title":"What matters when building vision-language mod-els?","volume":"37","author":"Lauren\u00e7on","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","author":"Li","year":"2024","journal-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models"},{"key":"ref25","author":"Li","year":"2025","journal-title":"Inference optimal vlms need fewer visual tokens and more parameters"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.601"},{"key":"ref28","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","year":"2024","journal-title":"Microsoft. Phi-3 technical report: A highly capable language model locally on your phone"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.761"},{"key":"ref31","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3565959"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X00076512"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.780"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32142"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.719"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.figlang-1.4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.170"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01842"},{"key":"ref42","year":"2025","journal-title":"OpenGVLab Team. Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models"},{"key":"ref43","year":"2025","journal-title":"Qwen Team. Qwen2.5-vl technical report"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref45","volume-title":"Social-iq 2.0 challenge: Benchmarking multimodal social understanding","author":"Wilf","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref47","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zeng","year":"2023"},{"key":"ref48","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444089.pdf?arnumber=11444089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:46:19Z","timestamp":1777610779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00151","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}