MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning.
Jie LeiLiwei WangYelong ShenDong YuTamara L. BergMohit BansalPublished in: ACL (2020)
Keyphrases
- video data
- fuzzy logic
- video streams
- multimedia
- video frames
- real time video
- real time
- memory requirements
- video content
- online video
- digital video
- video database
- video clips
- recurrent neural networks
- spatial and temporal
- power system
- feed forward
- memory space
- memory usage
- high resolution
- neural network
- genetic algorithm
- limited memory
- computing power
- video processing
- expert systems
- key frames
- video analysis
- video surveillance
- temporal information
- event detection