We propose a cinematographic camera diffusion model using a transformer-based architecture to handle temporality and exploit the stochasticity of diffusion models to generate diverse and qualitative trajectories conditioned by high-level textual descriptions.

We present a novel technique that enables 3D artists to synthesize camera motions in virtual environments following a camera style, while enforcing user-designed camera keyframes as constraints along the sequence.

We propose an example-driven camera controller which can extract camera behaviors from an example film clip and re-apply the extracted behaviors to a 3D animation, through learning from a collection of camera motions.

Multi-modal data can provide more useful information for Human Action Recognition. But with the different formats, different modal data can only be used separately, which results a inefficient fusion. In this paper, we give comprehensive analysis of fusion schemes through experimental results and hope our work could benefit the community in multi-modal action recognition.