Exploring the Role of Audio in Video Captioning.
Computer Vision and Pattern Recognition（2024）
关键词
Video Captioning,Large-scale Datasets,Speaker Recognition,Video Dataset,Acoustic Events,Text Transcription,Information Bottleneck,Text Modality,Attention Mechanism,Video Clips,Representation Learning,Fusion Method,Language Model,Local Module,Underfitting,Single Sentence,Human Speech,Multimodal Learning,Transformer Layers,Speech Information,Local Fusion,Video Encoding,Transformer Block,Encoder-decoder Framework,Beginning Of The Sentence
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要