MAGVIT: Masked Generative Video Transformer.
Lijun YuYong ChengKihyuk SohnJosé LezamaHan ZhangHuiwen ChangAlexander G. HauptmannMing-Hsuan YangYuan HaoIrfan EssaLu JiangPublished in: CoRR (2022)
Keyphrases
- video sequences
- video streams
- video data
- video content
- multimedia
- generative model
- video analysis
- real time video
- video processing
- video segmentation
- video frames
- online video
- discriminative learning
- video clips
- computer vision
- human actions
- spatial and temporal
- image classification
- bayesian networks
- genetic algorithm
- real time