{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:44:42Z","timestamp":1780418682529,"version":"3.54.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746193","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8967-8971","source":"Crossref","is-referenced-by-count":9,"title":["Text-Image De-Contextualization Detection Using Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Mingzhen","family":"Huang","sequence":"first","affiliation":[{"name":"University at Buffalo, State University of New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"University at Buffalo, State University of New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ching","family":"Chang","sequence":"additional","affiliation":[{"name":"University at Albany, State University of New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Lyu","sequence":"additional","affiliation":[{"name":"University at Buffalo, State University of New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.545"},{"key":"ref11","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240707"},{"key":"ref14","article-title":"Multi-modal semantic inconsistency detection in social media news posts","author":"mccrae","year":"2021"},{"key":"ref15","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref16","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref18","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00380"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.163"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123385"},{"key":"ref7","first-page":"180","article-title":"fake news","volume":"65","author":"molina","year":"2021","journal-title":"is not simply false information a concept explication and taxonomy of online content \" American behavioral scientist"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137600"},{"key":"ref1","first-page":"1","article-title":"Combatting against covid-19 & misinformation: A systematic review","author":"ali","year":"2020","journal-title":"Hum Arenas"},{"key":"ref9","article-title":"Cosmos: Catching out-of-context misinformation with self-supervised learning","author":"aneja","year":"2021"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746193.pdf?arnumber=9746193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:14:59Z","timestamp":1661199299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746193","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}