Make It Move: Controllable Image-to-Video Generation with Text Descriptions.
Yaosi HuChong LuoZhenzhong ChenPublished in: CVPR (2022)
Keyphrases
- textual descriptions
- natural language descriptions
- single image
- image data
- input image
- weakly labeled
- image retrieval
- high resolution
- image description
- image segmentation
- image regions
- web images
- image classification
- image features
- image analysis
- image content
- image collections
- video images
- image frames
- semantic labels
- caption text
- visual cues
- visual data
- low level
- edge detection
- key frames
- high level
- video sequences
- video search
- visual concepts
- segmentation method
- test images
- video data
- video frames
- text mining
- text detection
- pixel values
- text generation
- multiscale
- video content
- video files
- multimedia