Latte: Latent Diffusion Transformer for Video Generation.
Xin MaYaohui WangGengyun JiaXinyuan ChenZiwei LiuYuan-Fang LiCunjian ChenYu QiaoPublished in: CoRR (2024)
Keyphrases
- video sequences
- multimedia
- fuzzy logic
- video data
- video content
- video frames
- video streams
- video analysis
- real time video
- fault diagnosis
- video clips
- video segmentation
- space time
- diffusion process
- video images
- computer vision
- video processing
- multiscale
- partial discharge
- temporal information
- digital video
- video database
- video retrieval
- video surveillance
- human actions
- neural network
- generative model
- motion estimation
- artificial intelligence