Hierarchical Vision-Language Alignment for Video Captioning.
Junchao ZhangYuxin PengPublished in: MMM (1) (2019)
Keyphrases
- real time
- video data
- computer vision
- programming language
- video sequences
- video content
- image processing
- vision system
- video streams
- digital video
- video analysis
- coarse to fine
- hierarchical clustering
- video frames
- real time video
- multimedia
- video shots
- hierarchical structure
- language learning
- space time
- natural language
- dynamic scenes
- video database
- video images
- hierarchical model
- image alignment
- online video
- video surveillance
- temporal information
- spatial and temporal
- multi view
- spatio temporal