机译:记住和忘记:视频和文本融合,用于视频问答
School of Computer and Information Engineering, Anyang Normal University,Henan Key Laboratory of Oracle Bone Inscriptions Information Processing, Anyang Normal University,Collaborative Innovation Center of International Dissemination of Chinese Language Henan Province (HNIDCL);
School of Computer Science and Technology, Tianjin University;
School of Computer and Information Engineering, Anyang Normal University,Henan Key Laboratory of Oracle Bone Inscriptions Information Processing, Anyang Normal University,Collaborative Innovation Center of International Dissemination of Chinese Language Henan Province (HNIDCL);
Video QA; Forget memory network; Fused video and text features;
机译:视频问答的勿忘观察者模型
机译:统一开放式视频问答的视频和问题注意
机译:视频问题回答的多粒子关注特征的分层时间融合
机译:用于视频问答和检索的联合序列融合模型
机译:可见光谱和红外光谱中的多传感器融合:改进视频序列中的行人跟踪(法文)。
机译:更正:更好地记住低信息感健康促进视频并激活与记忆编码相关的大脑区域
机译:建立新图书馆:记住答案,记住问题
机译:连接对话的第一步:在自由文本问题和预先录制的视频答案之间进行调解