【Paper Reading】VideoBERT: A Joint Model for Videoand Language Representation Learning
数据准备:New_HOINew_verbNew_objectPaperreading:Title:VideoBERT:AJointModelforVideoandLanguageRepresentationLearningAuthor:ChenSun,AustinMyers,CarlVondrick,KevinMurphy,andCordeliaSchmid摘要:Self-supervisedle