Video captioning based on vision transformer and reinforcement learning.
Hong ZhaoZhiwen ChenLan GuoZeyu HanPublished in: PeerJ Comput. Sci. (2022)
Keyphrases
- reinforcement learning
- real time
- video data
- multimedia
- video sequences
- computer vision
- vision system
- function approximation
- video content
- video streams
- video frames
- video analysis
- multi agent
- image processing
- video segmentation
- visual data
- fuzzy logic
- video surveillance
- machine learning
- visual perception
- temporal difference
- reinforcement learning algorithms
- real time video
- neural network
- spatial and temporal
- multimedia data
- dynamic programming
- power transformers
- genetic algorithm
- event recognition
- learning algorithm
- expert systems
- spatio temporal
- model free
- control system
- state space
- optimal policy
- video clips
- video retrieval
- fault diagnosis
- event detection
- temporal information