Multi-Modal Deep Reinforcement Learning for Edge-Assisted Video Analytics.
Shen HeChaokun ZhangAojia LvJingshun DuWenyu QuPublished in: CSCWD (2023)
Keyphrases
- multi modal
- video analytics
- reinforcement learning
- video analysis
- computer vision
- multi modality
- state space
- edge detection
- edge information
- semantic concepts
- cross modal
- audio visual
- video search
- transfer learning
- single modality
- public space
- video data
- high dimensional
- human computer interaction
- medical images
- face recognition