Toward Automatic Audio Description Generation for Accessible Videos.
Yujia WangWei LiangHaikun HuangYongqi ZhangDingzeyu LiLap-Fai YuPublished in: CHI (2021)
Keyphrases
- video indexing and retrieval
- video sequences
- fully automatic
- visual data
- speech music discrimination
- video content analysis
- video indexing
- multimedia
- video content
- semi automatic
- high level
- audio features
- visual information
- video analysis
- dynamic scenes
- audio signals
- signal processing
- audio visual
- video shots
- generation process
- lecture videos
- temporal segmentation
- video data
- video material
- video clips