Attention-Based Convolutional LSTM for Describing Video.
Zhongyu LiuTian ChenEnjie DingYafeng LiuWanli YuPublished in: IEEE Access (2020)
Keyphrases
- video sequences
- video data
- video content
- real time
- focus of attention
- multimedia
- video segmentation
- video analysis
- video clips
- video streams
- spatial and temporal
- real time video
- visual saliency
- key frames
- video frames
- activity recognition
- saliency map
- dynamic scenes
- multi view
- high resolution
- multiscale
- image sequences
- deep learning
- machine learning