Scalable Mask Annotation for Video Text Spotting.
Haibin HeJing ZhangMengyang XuJuhua LiuBo DuDacheng TaoPublished in: CoRR (2023)
Keyphrases
- video annotation
- semantic labels
- video data
- video segments
- textual descriptions
- video search
- natural language descriptions
- document analysis
- video sequences
- text detection
- multimedia search
- video content
- video retrieval
- multimedia documents
- video database
- closed captions
- news video
- scalable video
- weakly labeled
- information retrieval
- multimedia
- video analysis
- video material
- video streams
- scalable video coding
- cross media
- automatically created
- semantic information
- text retrieval
- key frames
- video frames
- free text
- video clips
- keywords
- real time
- digital photos
- text mining
- streaming services
- printed documents
- multi modal
- lecture videos
- text documents
- automatic annotation
- semantic annotation
- image annotation
- content based retrieval