Recurrent convolutional video captioning with global and local attention.
Tao JinYingming LiZhongfei ZhangPublished in: Neurocomputing (2019)
Keyphrases
- video frames
- multimedia
- video sequences
- video content
- video data
- space time
- spatial and temporal
- video clips
- global information
- video database
- video analysis
- dynamic scenes
- deep learning
- neural network
- video images
- online video
- recurrent neural networks
- network architecture
- video retrieval
- real time
- multimedia data
- data sets