Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video.
Antonino FurnariGiovanni Maria FarinellaPublished in: CoRR (2020)
Keyphrases
- human actions
- video data
- video sequences
- multimedia
- video streams
- action classification
- recognizing human actions
- video content
- action detection
- action recognition
- video images
- video analysis
- video retrieval
- real time
- data sets
- video indexing
- digital video
- video database
- key frames
- spatial and temporal
- video frames
- video clips
- video surveillance
- neural network
- human activities
- real time video
- space time
- visual data
- video shots
- computer vision