Make It Move: Controllable Image-to-Video Generation with Text Descriptions.
Yaosi HuChong LuoZhenzhong ChenPublished in: CoRR (2021)
Keyphrases
- image data
- natural language descriptions
- textual descriptions
- input image
- image content
- multiscale
- image features
- single image
- low level
- image analysis
- image classification
- static images
- semantic labels
- visual data
- text information
- image frames
- image description
- visual cues
- video images
- video streams
- segmentation method
- segmentation algorithm
- weakly labeled
- image retrieval
- test images
- image collections
- video analysis
- feature points
- text mining
- information retrieval
- video sequences
- high level
- image segmentation
- temporal continuity
- video files
- text regions
- web images
- pixel values
- video frames
- edge detection
- high resolution