F: discriminative dense fusion of appearance and motion modalities for end-to-end video classification.
Lin WangXingfu WangAmmar HawbaniYan XiongXu ZhangPublished in: Multim. Tools Appl. (2022)
Keyphrases
- end to end
- video classification
- dynamic textures
- category labels
- spatial and temporal
- optical flow
- image sequences
- motion segmentation
- space time
- motion model
- congestion control
- motion trajectories
- motion estimation
- spatio temporal
- motion patterns
- dynamic scenes
- video shots
- visual data
- moving objects
- human motion
- motion field
- motion analysis
- video content
- video indexing
- multi modal
- key frames
- pose estimation
- visual features
- image classification