Learned video compression has recently emerged as an essential research topic in developing advanced technologies, where motion compensation is considered one of the most challenging issues. In this paper, we propose a learned framework via heterogeneous deformable strategy (HDCVC) to tackle problems unstable performance caused by single-size kernels downsampled feature domain. More specificall...

The successful emotional conversation system depends on sufficient perception and appropriate expression of emotions. In a real-life conversation, humans firstly instinctively perceive emotions from multi-source information, including the emotion flow hidden in dialogue history, facial expressions, audio, personalities speakers. Then, they convey suitable according to their personalities, but t...