{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T22:53:31Z","timestamp":1789167211970,"version":"build-2803163510"},"reference-count":95,"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\/iccv51701.2025.00263","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-12","source":"Crossref","is-referenced-by-count":3,"title":["Gaze-Language Alignment for Zero-Shot Prediction of Visual Search Targets from Human Gaze Scanpaths"],"prefix":"10.1109","author":[{"given":"Sounak","family":"Mondal","sequence":"first","affiliation":[{"name":"Stony Brook University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveen","family":"Sendhilnathan","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Proulx","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Louis Iuzzolino","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Qin","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanya R.","family":"Jonker","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1167\/11.8.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-017-1324-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/ans.18686"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2024.1436564"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3379155.3391314"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2168556.2168569"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1167\/14.3.29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.07.055"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322253"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3655604"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.86"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2302239121"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01073"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02402"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-87715-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00551"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.42.3.692"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-016-1094-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-27361-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3649902.3655654"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.659410"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3138902"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451737"},{"key":"ref32","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/vr.2019.8798327"},{"key":"ref34","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"International conference on machine learning","author":"Lee","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.05.106"},{"key":"ref36","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2017.2647882"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116198"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref41","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1167\/11.9.9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1167\/9.11.8"},{"key":"ref44","article-title":"Visual classification via description from large language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Menon","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00145"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_14"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.08.025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00067"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2945078.2945153"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457528"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_5"},{"key":"ref53","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref54","article-title":"Clip for all things zero-shot sketch-based image retrieval, finegrained or not","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sain","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298700"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.322"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.028"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2006372118"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545628"},{"key":"ref60","author":"Sendhilnathan","year":"2024","journal-title":"Implicit gaze research for xr systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10020068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2535948.2535955"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2876456.2879475"},{"key":"ref64","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref65","first-page":"36","article-title":"Cwcl: Cross-modal transfer with continuously weighted contrastive loss","author":"Sharma Srinivasa","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00111-7_25"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2807520"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00031"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606795"},{"key":"ref70","first-page":"165","article-title":"Facial composite generation with iterative human feedback","volume-title":"Annual Conference on Neural Information Processing Systems","author":"Strohm","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957817"},{"key":"ref73","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref74","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2396031"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1167\/5.1.8"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00219"},{"key":"ref78","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300839"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1167\/jov.20.11.303"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-vision-091718-015048"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3758\/bf03211924"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-011-0153-3"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00804"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01260"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00027"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_4"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00166"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7_8"},{"key":"ref90","author":"Yuan","year":"2021","journal-title":"Florence: A new foundation model for computer vision"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1167\/8.6.380"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1167\/13.3.30"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1167\/13.14.10"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1167\/jov.23.9.5161"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-06217-x"}],"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\/11444428.pdf?arnumber=11444428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:09Z","timestamp":1777531569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00263","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}