Making CNNs for Video Parsing Accessible.
Zijin LuoMatthew GuzdialMark RiedlPublished in: CoRR (2019)
Keyphrases
- video data
- video sequences
- video content
- multimedia
- video streams
- closed captions
- digital video
- video analysis
- spatial and temporal
- natural language processing
- video frames
- space time
- natural language
- unsupervised learning
- key frames
- video clips
- real time video
- video images
- machine learning
- cellular neural networks
- video shots
- video segmentation
- video database
- video surveillance
- dynamic textures
- video processing
- event recognition
- context free
- feature vectors
- online video