A Multi-modal System for Video Semantic Understanding.
Zhengwei LvTao LeiXiao LiangZhizhong ShiDuoxing LiuPublished in: CCKS (Evaluation Track) (2021)
Keyphrases
- multi modal
- semantic concepts
- video search
- high dimensional
- semantic video retrieval
- video sequences
- video data
- visual concepts
- video shots
- audio visual
- automatic image annotation
- multi modality
- image annotation
- video content
- cross modal
- multiple modalities
- multimedia
- video frames
- semantic information
- humanoid robot
- video retrieval
- semantic similarity
- video streams
- image processing