VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks.
Hung LeNancy F. ChenSteven C. H. HoiPublished in: CoRR (2021)
Keyphrases
- video data
- video sequences
- multimedia
- video content
- video streams
- real time
- network architecture
- video analysis
- video processing
- real time video
- peer to peer
- video segmentation
- human activities
- video surveillance
- programming language
- digital video
- network conditions
- computer vision
- video images
- temporal information
- multimedia data
- video on demand
- video frames
- space time
- scalable video
- video delivery
- video retrieval
- computer networks
- network traffic
- spatio temporal
- metadata
- social networks
- neural network