Exploring a CLIP-Enhanced Automated Approach for Video Description Generation.
Siang-Ling ZhangHuai-Hsun ChengYen-Hsin ChenMei-Chen YehPublished in: APSIPA ASC (2023)
Keyphrases
- video clips
- key frames
- video data
- video content
- multimedia
- video sequences
- video frames
- video streams
- video database
- real time video
- video processing
- real time
- space time
- high level
- compressed video
- video surveillance
- video segments
- semi automated
- spatial temporal
- event detection
- dynamic textures
- low level features
- symbolic descriptions
- long video
- visual data
- video analysis
- multimedia data
- human activities
- computer aided
- neural network