机译:具有基于注意的LSTM和语义一致性的视频字幕
Center of Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;
Center of Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;
Department of Computer Science, Columbia University, New York, NY, USA;
Center of Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;
Center of Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;
Visualization; Semantics; Two dimensional displays; Neural networks; Computational modeling; Feature extraction; Correlation;
机译:基于残留注意力的LSTM用于视频字幕
机译:深度多核卷积LSTM网络和基于注意力的视频机制
机译:基于注意力的时空分层ConvLSTM网络,用于视频中的动作识别
机译:批量标准化和堆叠LSTMS对视频字幕的影响
机译:在台湾(中国)使用视频字幕作为外语英语(EFL)对大学生语言学习的影响。
机译:具有预定采样的语义辅助视频标题模型
机译:深度多核卷积LSTM网络和基于关注的视频机制