Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net.
Tianrui LiuQingjie MengJunjie HuangAthanasios VlontzosDaniel RueckertBernhard KainzPublished in: CoRR (2021)
Keyphrases
- video summarization
- spatio temporal
- reinforcement learning
- temporal segmentation
- audio visual
- event detection
- video content
- video sequences
- key frames
- video browsing
- surveillance videos
- image sequences
- video summaries
- moving objects
- low level features
- space time
- learning algorithm
- video data
- state space
- video representation
- video retrieval
- video frames
- three dimensional
- machine learning
- visual features
- similarity measure
- multimedia
- video surveillance
- computer vision
- personal photos