Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learning.
Amir ZiaiAneesh VartakaviPublished in: CoRR (2024)
Keyphrases
- language model
- active learning
- probabilistic model
- video sequences
- multimedia
- video content
- decision trees
- video frames
- document retrieval
- information retrieval
- language modeling
- video data
- n gram
- learning algorithm
- language modelling
- test collection
- speech recognition
- query expansion
- training set
- query terms
- bayesian networks
- video retrieval
- training data
- video shots
- feature selection
- language models for information retrieval