A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues.
Yunxin LiBaotian HuXinyu ChenYuxin DingLin MaMin ZhangPublished in: CoRR (2023)
Keyphrases
- multi modal
- cross modal
- video search
- multi modality
- visual representations
- nonmonotonic inference
- audio visual
- single modality
- visual information
- high level
- multiple modalities
- low level
- multimedia
- bayesian networks
- contextual information
- image annotation
- humanoid robot
- visual data
- visual features
- context aware
- medical images
- image analysis
- high dimensional
- face recognition
- image processing
- uni modal