On the Performance Evaluation of Action Recognition Models on Transcoded Low Quality Videos.
Aoi OtaniRyota HashiguchiKazuki OmiNorishige FukushimaToru TamakiPublished in: CoRR (2022)
Keyphrases
- action recognition
- low quality
- human actions
- action classification
- high quality
- recognition of human actions
- bag of words
- video dataset
- recognizing human actions
- recognizing actions
- computer vision
- human detection
- view invariant
- motion features
- human pose
- human activities
- activity recognition
- motion history images
- body parts
- mid level features
- human object interactions
- space time interest points
- bag of features
- recognition algorithm
- video content
- action detection
- object detection
- video sequences
- multiscale
- action recognition in videos
- ucf sports