CLEVRER: Collision Events for Video Representation and Reasoning.
Kexin YiChuang GanYunzhu LiPushmeet KohliJiajun WuAntonio TorralbaJoshua B. TenenbaumPublished in: ICLR (2020)
Keyphrases
- video representation
- spatio temporal
- space time
- video analysis
- event detection
- video database
- video streams
- video content
- video clips
- visual vocabulary
- generative model
- dynamic textures
- video objects
- motion patterns
- video synopsis
- video processing
- video retrieval
- video data
- video sequences
- content based retrieval
- dynamic scenes
- image sequences
- key frames
- video segmentation
- spatial and temporal
- probabilistic model
- similarity measure
- face recognition