LoCoNet: Long-Short Context Network for Active Speaker Detection
CVPR 2024（2024）
关键词
Active Speaker,Active Speaker Detection,Local Patterns,Video Frames,Temporal Dependencies,Temporal Model,Long-range Dependencies,Short-term Model,Multiple Speakers,Convolutional Network,Attention Mechanism,Receptive Field,Temporal Context,Inference Speed,Small Face,Visual Encoding,Visible Face
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