VTLayout: A Multi-Modal Approach for Video Text Layout.
Yuxuan ZhaoJin MaZhongang QiZehua XieYu LuoQiusheng KangYing ShanPublished in: ACM Multimedia (2023)
Keyphrases
- multi modal
- video search
- multiple modalities
- semantic concepts
- multi modality
- audio visual
- video data
- video streams
- text retrieval
- video analysis
- information retrieval
- multimedia
- video content
- video sequences
- broadcast news
- video database
- multimedia documents
- single modality
- video shots
- video clips
- image annotation
- multimedia data
- image segmentation