Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition.
Hasan Abed Al Kader HammoudShuming LiuMohammad AlkhrasiFahad AlbalawiBernard GhanemPublished in: CoRR (2023)
Keyphrases
- action recognition in videos
- action recognition
- human actions
- action classification
- countermeasures
- spatial temporal
- video dataset
- action detection
- recognizing human actions
- motion features
- activity recognition
- static images
- human activities
- spatio temporal interest points
- bag of words
- human detection
- recognition of human actions
- space time interest points
- body parts
- computer vision
- video sequences
- ddos attacks
- mid level
- video data
- human pose
- motion history images
- feature vectors
- recognizing actions
- motion capture data
- multimedia
- human activity recognition
- human motion
- video retrieval
- video shots
- video streams
- view invariant
- visual features
- depth sensors
- image classification
- event recognition
- video images
- bag of features
- video analysis