Action Recognition in Dark Videos Using Spatio-Temporal Features and Bidirectional Encoder Representations From Transformers.
Himanshu SinghSaurabh SumanBadri Narayan SubudhiVinit JakhetiyaAshish GhoshPublished in: IEEE Trans. Artif. Intell. (2023)
Keyphrases
- action recognition
- human actions
- video dataset
- action classification
- recognition of human actions
- recognizing human actions
- ucf sports
- mid level
- space time interest points
- human activities
- spatio temporal interest points
- view invariant
- recognizing actions
- bag of words
- motion features
- action recognition in videos
- static images
- action detection
- computer vision
- human detection
- activity recognition
- mid level features
- spatial temporal
- body parts
- human object interactions
- video sequences
- motion history images
- bag of features
- bit rate
- video frames
- action primitives
- motion estimation
- low level descriptors
- depth sensors
- spatio temporal
- motion capture data
- visual features
- space time
- image representation
- video clips
- human body
- motion vectors