{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:19:58Z","timestamp":1778080798421,"version":"3.51.4"},"reference-count":56,"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\/iccv51701.2025.00122","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1228-1238","source":"Crossref","is-referenced-by-count":1,"title":["Acknowledging Focus Ambiguity in Visual Questions"],"prefix":"10.1109","author":[{"given":"Chongyan","family":"Chen","sequence":"first","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Yun","family":"Tseng","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoheng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anush","family":"Venkatesh","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danna","family":"Gurari","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","first-page":"5","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00437"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01405"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_15"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","first-page":"5","article-title":"Chatbot arena: An open platform for evaluating 11 ms by human preference","author":"Chiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1156"},{"key":"ref12","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00298"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref17","first-page":"2","article-title":"Abg-coqa: Clarifying ambiguity in conversational question answering","volume-title":"3rd Conference on Automated Knowledge Base Construction","author":"Guo","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025781"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1065-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1065-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-020-00195-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref25","first-page":"3","article-title":"Long-form answers to visual questions from blind and low vision people","author":"Huh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.271"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.63"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref30","first-page":"3","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","first-page":"3","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.70"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/a16030135"},{"key":"ref35","first-page":"3","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.804"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.466"},{"key":"ref39","article-title":"Gpt-4o system card","year":"2024","journal-title":"OpenAI"},{"key":"ref40","first-page":"2","article-title":"Rephrase, augment, reason: Visual grounding of questions for vision-language models","volume-title":"arXiv preprint","author":"Prasad","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01098"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref46","first-page":"2","article-title":"Why did the chicken cross the road? rephrasing and analyzing ambiguous questions in vqa","author":"Stengel-Eskin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_33"},{"key":"ref48","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0060"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00132"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref52","first-page":"2","article-title":"Described object detection: Liberating object detection with flexible expressions","volume":"36","author":"Xie","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v6i1.13341"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"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\/11446311.pdf?arnumber=11446311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:15Z","timestamp":1777612515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00122","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}