DFN: A deep fusion network for flexible single and multi-modal action recognition.
Chuankun LiYonghong HouWanqing LiZewei DingPichao WangPublished in: Expert Syst. Appl. (2024)
Keyphrases
- multi modal
- action recognition
- multi modality
- single modality
- bag of words
- activity recognition
- human actions
- action classification
- human detection
- audio visual
- computer vision
- fusing multiple
- view invariant
- recognizing human actions
- image annotation
- action detection
- depth sensors
- recognition of human actions
- semantic concepts
- high dimensional
- machine learning
- action recognition in videos
- motion history images
- video search
- human pose
- feature extraction