VDub: Modifying Face Video of Actors for Plausible Visual Alignment to a Dubbed Audio Track.
Pablo GarridoLevi ValgaertsH. SarmadiI. SteinerKiran VaranasiPatrick PérezChristian TheobaltPublished in: Comput. Graph. Forum (2015)
Keyphrases
- visual data
- visual speech
- visual information
- video indexing and retrieval
- multimedia
- content based video retrieval
- audio video
- visual features
- scene change detection
- video data
- cross modal
- video content
- digital video
- video content analysis
- video database
- mouth region
- visual cues
- multimedia processing
- video analysis
- audio visual
- multimodal fusion
- multimedia data
- audio files
- multimedia information
- visual analysis
- video search
- real time
- audio features
- low level
- audio stream
- video indexing
- human faces
- video files
- video sequences
- video shots
- news video
- video frames
- multimodal information
- audio signals
- face detection and tracking
- content based retrieval
- key frames
- broadcast news
- audio content
- digital audio
- story segmentation
- video streams
- facial images
- signal processing
- video retrieval
- video clips
- soccer video
- video signals
- multi modal
- facial expressions
- semantic concepts
- video segments
- image retrieval
- video material
- temporal segmentation
- image sequences
- face alignment
- video annotation
- face images
- media streams