Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video.
Antonino FurnariGiovanni Maria FarinellaPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2021)
Keyphrases
- human actions
- video sequences
- video streams
- multimedia
- video data
- real time
- action classification
- real time video
- video retrieval
- action detection
- video database
- video content
- video frames
- action recognition
- space time
- action selection
- neural network
- key frames
- spatio temporal
- surveillance videos
- video segmentation
- video shots
- digital video
- visual features
- compressed video
- video images
- state space
- online video
- visual data
- video analysis