MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning.
Jie LeiLiwei WangYelong ShenDong YuTamara L. BergMohit BansalPublished in: CoRR (2020)
Keyphrases
- video data
- video sequences
- fault diagnosis
- memory requirements
- multimedia
- computing power
- memory usage
- fuzzy logic
- space time
- video processing
- event recognition
- video frames
- video streams
- video database
- real time
- video retrieval
- digital video
- video analysis
- spatial and temporal
- video clips
- video content
- power system
- motion estimation
- video images
- limited memory
- event detection
- online video
- associative memory
- multimedia data
- data structure
- computer vision