CC-LSTM: Cross and Conditional Long-Short Time Memory for Video Captioning.
Jiangbo AiYang YangXing XuJie ZhouHeng Tao ShenPublished in: ICPR Workshops (6) (2020)
Keyphrases
- video streams
- video sequences
- memory usage
- multimedia
- video content
- real time
- video images
- video data
- spatial and temporal
- video frames
- memory space
- video database
- video clips
- random field model
- space time
- memory requirements
- digital video
- multiscale
- limited memory
- temporal information
- video segmentation
- video analysis
- dynamic scenes
- video retrieval
- video surveillance
- event detection
- recurrent neural networks
- video processing
- multi view
- real time video
- memory size
- human actions