Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme - Pose Dictionary.
Sibo ZhangJiahong YuanMiao LiaoLiangjun ZhangPublished in: ICASSP (2022)
Keyphrases
- video search
- text detection
- video data
- multimedia
- video content
- video sequences
- online video
- video segments
- video streams
- natural language descriptions
- news video
- multimedia search
- video clips
- multimedia documents
- video analysis
- real time
- video frames
- multimedia data
- keywords
- information retrieval
- video retrieval
- video database
- text mining
- event detection
- textual descriptions
- image classification
- text corpus
- head pose estimation
- hidden markov models
- english words
- person detection