Utilizing a Dense Video Captioning Technique for Generating Image Descriptions of Comics for People with Visual Impairments.
Suhyun KimSemin LeeKyungok KimUran OhPublished in: IUI (2024)
Keyphrases
- image data
- input image
- image features
- image frames
- image pixels
- image collections
- image analysis
- image content
- single image
- image segmentation
- video files
- multiscale
- video sequences
- image description
- pixel values
- textual descriptions
- image classification
- edge detection
- low level
- image retrieval
- pre trained
- video images
- static images
- high level
- feature points
- similarity measure
- image pairs
- visual cues
- video content
- vector field
- spatial information
- space time
- image representation
- high frame rate