Deep Video Inpainting Guided by Audio-Visual Self-Supervision.
Kyuyeon KimJunsik JungWoo Jae KimSung-Eui YoonPublished in: ICASSP (2022)
Keyphrases
- audio visual
- video summarization
- visual data
- multimedia
- meeting room
- multi modal
- audio visual content
- audio features
- sports video
- visual information
- video sequences
- multi stream
- video data
- temporal context
- person authentication
- multimodal fusion
- video content
- audio visual speech recognition
- video streams
- multimedia data
- video frames
- key frames
- multimedia content
- event detection
- temporal information
- visual features
- multimedia databases
- space time
- high dimensional data
- high dimensional
- training set
- feature extraction