{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:36Z","timestamp":1777865376084,"version":"3.51.4"},"reference-count":52,"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\/iccv51701.2025.00242","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2512-2522","source":"Crossref","is-referenced-by-count":1,"title":["Visual Intention Grounding for Egocentric Assistants"],"prefix":"10.1109","author":[{"given":"Pengzhan","family":"Sun","sequence":"first","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbin","family":"Xiao","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tze Ho Elden","family":"Tse","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicong","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arjun","family":"Akula","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angela","family":"Yao","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"issue":"2","key":"ref3","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref5","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"2","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"ref8","first-page":"2","article-title":"Chestx-reasoner: Advancing radiology foundation models with reasoning through step-by-step verification","author":"Fan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1197"},{"key":"ref10","first-page":"410","article-title":"A game-theoretic approach to generating spatial descriptions","volume-title":"Proceedings of the 2010 conference on empirical methods in natural language processing","author":"Golland","year":"2010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"issue":"2","key":"ref12","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref13","first-page":"8","article-title":"Open-set image tagging with multi-grained text supervision","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3731715.3733282"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/124"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref28","article-title":"Natural reference to objects in a visual domain","volume-title":"Proceedings of the 6th international natural language generation conference","author":"Mitchell","year":"2010"},{"key":"ref29","first-page":"1174","article-title":"Generating expressions that refer to visible objects","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Mitchell","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"ref32","article-title":"Rio: A benchmark for reasoning intention-oriented objects in open environments","volume":"36","author":"Qu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00779"},{"key":"ref35","first-page":"arXiv-2403","article-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models","author":"Shao","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475472"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1706269.1706296"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1708322.1708334"},{"key":"ref40","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.43"},{"key":"ref43","first-page":"1","article-title":"Egoblind: Towards egocentric visual assistance for the blind people","author":"Xiao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref45","first-page":"3","article-title":"Text-driven affordance learning from egocentric vision","author":"Yoshida","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"2","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref48","first-page":"2","article-title":"Next-chat: An 1 mm for chat, detection and segmentation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","first-page":"3","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","first-page":"19","article-title":"Llava-grounding: Grounded visual chat with large multimodal models","volume-title":"European Conference on Computer Vision","author":"Zhang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00319"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"}],"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\/11445311.pdf?arnumber=11445311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:04Z","timestamp":1777530124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00242","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}