Scalable Neural Video Representations with Learnable Positional Features.
Subin KimSihyun YuJaeho LeeJinwoo ShinPublished in: NeurIPS (2022)
Keyphrases
- video clips
- real time
- neural network
- learning algorithm
- space time
- continuous wavelet transform
- topological features
- scalable video coding
- video images
- network architecture
- temporal information
- video data
- feature set
- co occurrence
- low level
- feature extraction
- multimedia
- video streams
- event detection
- key frames
- video content
- video surveillance
- video retrieval
- representation scheme
- object recognition
- video sequences