{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:19:14Z","timestamp":1761895154491,"version":"build-2065373602"},"reference-count":23,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icme59968.2025.11210173","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":["Causal Intervention with Active Learning for Large Vision-Language Models in Egocentric Contexts"],"prefix":"10.1109","author":[{"given":"Wenxin","family":"Meng","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenshen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Salesforce AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Meituan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Peng","sequence":"additional","affiliation":[{"name":"Meituan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","year":"2024","author":"Liu","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"ICLR","author":"Zhu","key":"ref3"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306738"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680948"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3554559"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02490"},{"key":"ref12","article-title":"Causal inference in statistics: A primer. 2016","author":"Pearl","year":"2016","journal-title":"Internet resource"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.334"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref16"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref17"},{"journal-title":"mplug-owl: Modularization empowers large language models with multimodality","year":"2023","author":"Ye","key":"ref18"},{"article-title":"Pandagpt: One model to instruction-follow them all","year":"2023","author":"Su","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref22"},{"article-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref23"}],"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\/11210173.pdf?arnumber=11210173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:44:36Z","timestamp":1761889476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210173","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}