Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors.
Xi WangGen LiYen-Ling KuoMuhammed KocabasEmre AksanOtmar HilligesPublished in: CoRR (2022)
Keyphrases
- commonsense knowledge
- human object interactions
- human actions
- action recognition
- commonsense reasoning
- information gathering
- language understanding
- human pose
- complex events
- spatio temporal
- human motion
- automated reasoning
- space time
- video sequences
- probabilistic model
- theorem prover
- incomplete information
- human activities
- activity recognition
- knowledge representation