Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context.
Jie ZhangYin ZhaoLongjun CaiChaoping TuWu WeiPublished in: CoRR (2019)
Keyphrases
- temporal context
- multi modal fusion
- temporal information
- video data
- video sequences
- video content
- video shots
- spatial context
- key frames
- audio visual
- spatio temporal
- video database
- video streams
- object recognition
- facial features
- sports video
- multimedia
- space time
- spatial and temporal
- video retrieval
- video analysis
- video clips
- low level
- visual data
- dynamic scenes
- detection algorithm
- multi modal
- computer vision
- visual features
- detection method