McOmet: Multimodal Fusion Transformer for Physical Audiovisual Commonsense Reasoning.
Daoming ZongShiliang SunPublished in: AAAI (2023)
Keyphrases
- commonsense reasoning
- multimodal fusion
- audio visual
- nonmonotonic reasoning
- event calculus
- knowledge representation
- incomplete information
- high robustness
- multi modal
- visual information
- relevance feedback
- autoepistemic logic
- multimodal interfaces
- missing information
- multimedia
- formal theory
- high accuracy
- domain knowledge
- temporal reasoning
- high dimensional
- machine learning