GTLR: Graph-Based Transformer with Language Reconstruction for Video Paragraph Grounding.
Xun JiangXing XuJingran ZhangFumin ShenZuo CaoXunliang CaiPublished in: ICME (2022)
Keyphrases
- video data
- video frames
- video content
- multimedia
- image reconstruction
- video sequences
- video streams
- space time
- fuzzy logic
- video analysis
- high resolution
- three dimensional
- programming language
- natural language
- real time video
- video surveillance
- language learning
- video clips
- event detection
- key frames
- digital video
- online video
- multimedia data
- neural network
- human activities
- d objects
- graph model
- video database
- optical flow
- reconstruction process
- real time