Leveraging FFT and Hybrid EfficientNet for Enhanced Action Recognition in Video Sequences.
Nang Hung Van NguyenPhuc Hao DoVan-Nam HoangAleksandr BorodkoDuc Tran LePublished in: SoICT (2023)
Keyphrases
- action recognition
- human actions
- video sequences
- body parts
- space time interest points
- bag of words
- activity recognition
- video dataset
- computer vision
- spatial temporal
- human detection
- action classification
- recognition of human actions
- static images
- recognizing human actions
- motion estimation
- human activities
- image sequences
- recognizing actions
- action detection
- human motion
- view invariant
- independent subspace analysis
- motion recognition
- motion vectors
- motion capture data
- video data
- video shots
- machine learning
- feature extraction
- signal processing
- moving objects
- spatio temporal
- visual tracking
- temporal information
- low level
- object tracking
- facial expressions
- space time
- human computer interaction