MAViC: Multimodal Active Learning for Video Captioning.
Gyanendra DasXavier ThomasAnant RajVikram GuptaPublished in: CoRR (2022)
Keyphrases
- active learning
- multimedia
- video data
- video streams
- video content
- real time
- video sequences
- learning strategies
- video database
- video clips
- video frames
- multi modal
- spatial and temporal
- real time video
- supervised learning
- video segmentation
- random sampling
- event detection
- video processing
- video images
- selective sampling
- story segmentation
- multi party
- digital video
- audio visual
- multimedia data
- spatio temporal
- machine learning