Dense Captioning with Joint Inference and Visual Context.
Linjie YangKevin D. TangJianchao YangLi-Jia LiPublished in: CVPR (2017)
Keyphrases
- joint inference
- visual context
- information extraction
- temporal context
- probabilistic model
- entity resolution
- conditional random fields
- semantic role labeling
- graphical models
- object detection
- semantic context
- natural language understanding
- scene interpretation
- visual scene
- belief propagation
- exact inference
- spatio temporal
- semantic analysis
- machine learning
- pairwise
- feature space
- high level
- information retrieval