Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion.
Josip SaricSacha VrazicSinisa SegvicPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- motion features
- feature vectors
- feature set
- motion analysis
- key frames
- image features
- spatial and temporal
- space time
- video data
- point features
- visual cues
- video representation
- feature correspondences
- appearance features
- static images
- video clips
- regression model
- multiple features
- support vector regression
- video content
- optical flow fields
- video sequences
- invariant features
- image sequences
- temporal filtering
- low level
- video streams
- feature interactions
- temporal structure
- motion estimation
- object motion
- semantic concepts
- video analysis
- flow field
- motion model
- semantic information
- action recognition
- visual features
- semantic similarity
- global features
- video shots
- feature selection
- feature space
- multimedia