Few-shot generative model for skeleton-based human action synthesis using cross-domain adversarial learning.
Kenichiro FukushiYoshitaka NozakiKosuke NishiharaKentaro NakaharaPublished in: WACV (2024)
Keyphrases
- generative model
- cross domain
- learning algorithm
- prior knowledge
- action recognition
- human actions
- learning process
- probabilistic model
- knowledge transfer
- spatio temporal
- reinforcement learning
- active learning
- supervised learning
- video sequences
- visual features
- em algorithm
- human motion
- learning tasks
- activity recognition
- topic models
- unsupervised learning
- pairwise
- computer vision