{"title":"超越文本，再回来","authors":"Desmond Elliott","doi":"10.1145/3442442.3451896","DOIUrl":null,"url":null,"abstract":"A talk with two parts covering three modalities. In the first part, I will talk about NLP Beyond Text, where we integrate visual context into a speech recognition model and find that the recovery of different types of masked speech inputs is improved by fine-grained visual grounding against detected objects [2]. In the second part, I will come Back Again, and talk about the benefits of textual supervision in cross-modal speech–vision retrieval models [1].","PeriodicalId":129420,"journal":{"name":"Companion Proceedings of the Web Conference 2021","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Beyond Text and Back Again\",\"authors\":\"Desmond Elliott\",\"doi\":\"10.1145/3442442.3451896\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A talk with two parts covering three modalities. In the first part, I will talk about NLP Beyond Text, where we integrate visual context into a speech recognition model and find that the recovery of different types of masked speech inputs is improved by fine-grained visual grounding against detected objects [2]. In the second part, I will come Back Again, and talk about the benefits of textual supervision in cross-modal speech–vision retrieval models [1].\",\"PeriodicalId\":129420,\"journal\":{\"name\":\"Companion Proceedings of the Web Conference 2021\",\"volume\":\"37 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-04-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Companion Proceedings of the Web Conference 2021\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3442442.3451896\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Companion Proceedings of the Web Conference 2021","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3442442.3451896","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A talk with two parts covering three modalities. In the first part, I will talk about NLP Beyond Text, where we integrate visual context into a speech recognition model and find that the recovery of different types of masked speech inputs is improved by fine-grained visual grounding against detected objects [2]. In the second part, I will come Back Again, and talk about the benefits of textual supervision in cross-modal speech–vision retrieval models [1].
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
