Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation.
Tsu-Jui FuLicheng YuNing ZhangCheng-Yang FuJong-Chyi SuWilliam Yang WangSean BellPublished in: CoRR (2022)
Keyphrases
- video data
- multimedia
- video content
- video sequences
- video frames
- video streams
- real time
- video database
- real time video
- video search
- video retrieval
- video clips
- video processing
- video images
- multi modal
- online video
- video shots
- video segments
- news video
- text detection
- story segmentation
- dynamic scenes
- video surveillance
- semantic concepts
- video segmentation
- text documents