{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:21:19Z","timestamp":1761895279668,"version":"build-2065373602"},"reference-count":28,"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"}]},{"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"}]},{"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"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","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\/icme59968.2025.11209977","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":["Mitigating Hallucination in Large Video-Language Models with Injected Semantics"],"prefix":"10.1109","author":[{"given":"Bimei","family":"Wang","sequence":"first","affiliation":[{"name":"Jinan University,College of Cyber Security,China"}]},{"given":"Fan","family":"Wen","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science & Engineering,China"}]},{"given":"Jisheng","family":"Dang","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science & Engineering,China"}]},{"given":"Huiguo","family":"He","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,China"}]},{"given":"Xiwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwest Normal University,School of Computer Science and Engineering,China"}]},{"given":"Nannan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of System Science and Engineering,China"}]},{"given":"Jiasi","family":"Weng","sequence":"additional","affiliation":[{"name":"Jinan University,College of Cyber Security,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3167910"},{"key":"ref3","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3421623"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3423390"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3341457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413879"},{"article-title":"Vision language models in autonomous driving and intelligent transportation systems","year":"2023","author":"Zhou","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69525-5_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04393-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3280389"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3375620"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MIPRO60963.2024.10569238"},{"key":"ref21","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"North American Chapter of the Association for Computational Linguistics"},{"key":"ref22","first-page":"19730","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3357118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141886"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277389"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"}],"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\/11209977.pdf?arnumber=11209977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:46:58Z","timestamp":1761889618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209977","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}