Deep Video Inpainting Guided by Audio-Visual Self-Supervision.
Kyuyeon KimJunsik JungWoo Jae KimSung-Eui YoonPublished in: CoRR (2023)
Keyphrases
- audio visual
- video summarization
- visual data
- multimedia
- meeting room
- audio features
- multi modal
- audio visual content
- visual information
- temporal context
- sports video
- video data
- multimodal fusion
- person authentication
- audio visual speech recognition
- video streams
- video content
- multi stream
- video sequences
- multimedia data
- video frames
- contextual information
- feature extraction
- image data
- visual features
- key frames
- image sequences
- computer vision