Learning to Discretely Compose Reasoning Module Networks for Video Captioning.
Ganchao TanDaqing LiuMeng WangZheng-Jun ZhaPublished in: IJCAI (2020)
Keyphrases
- learning process
- learning algorithm
- multimedia
- video sequences
- knowledge base
- online learning
- spatio temporal
- knowledge acquisition
- connectionist networks
- video content
- real time
- neural network
- knowledge representation
- reinforcement learning
- metadata
- unsupervised learning
- mobile learning
- video streams
- learning tasks
- learning problems
- social networks
- video retrieval
- learning analytics
- video database
- inductive inference
- reasoning systems