Imperceptible Adversarial Attack With Multigranular Spatiotemporal Attention for Video Action Recognition.
Guoming WuYangfan XuJun LiZhi-Ping ShiXianglong LiuPublished in: IEEE Internet Things J. (2023)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- static images
- space time
- recognizing human actions
- recognition of human actions
- activity recognition
- spatial and temporal
- motion features
- space time interest points
- bag of words
- spatio temporal interest points
- human activities
- human detection
- body parts
- mid level
- motion history images
- video frames
- computer vision
- view invariant
- depth sensors
- video sequences
- video data
- spatio temporal
- human pose
- bag of features
- motion capture data
- video content
- video streams
- recognizing actions
- dynamic textures
- temporal structure
- human activity recognition
- video analysis
- key frames
- event detection
- bit rate
- moving objects