Generative Video Transformer: Can Objects be the Words?
Yi-Fu WuJaesik YoonSungjin AhnPublished in: CoRR (2021)
Keyphrases
- semantic labels
- video sequences
- multimedia
- video images
- video data
- space time
- n gram
- visual data
- multimedia objects
- object detection and tracking
- generative model
- real time
- image sequences
- object motion
- power system
- spatial and temporal
- video content
- dynamic scenes
- related words
- human activities
- video segments
- objects in video sequences
- multiple objects
- data objects
- key frames
- video streams
- fuzzy logic
- d objects
- expert systems
- neural network