AHFu-Net: Align, Hallucinate, and Fuse Network for Missing Multimodal Action Recognition.
Muhammad Adi NugrohoSangmin WooSumin LeeChangick KimPublished in: VCIP (2023)
Keyphrases
- action recognition
- human actions
- bag of words
- action classification
- computer vision
- activity recognition
- spatial temporal
- human detection
- body parts
- recognition of human actions
- view invariant
- recognizing human actions
- mid level
- action detection
- bag of features
- video dataset
- human activities
- motion features
- action recognition in videos
- depth sensors
- recognizing actions
- independent subspace analysis
- human pose
- multiple views
- wireless sensor networks
- feature vectors
- multimedia