Variational Stacked Local Attention Networks for Diverse Video Captioning.
Tonmoay DebAkib SadmaneeKishor Kumar BhaumikAmin Ahsan AliM. Ashraful AminA. K. M. Mahbubur RahmanPublished in: CoRR (2022)
Keyphrases
- multimedia
- video data
- video frames
- video content
- video retrieval
- real time
- video sequences
- video database
- video clips
- video segmentation
- video analysis
- video on demand
- multimedia data
- information transfer
- video images
- network analysis
- event detection
- network structure
- video streams
- image segmentation
- optical flow computation
- real time video
- event recognition
- community structure
- variational methods
- video shots
- temporal information
- spatial and temporal
- space time
- real world