Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser.
Yung-Hsuan LaiYen-Chun ChenFrank WangPublished in: NeurIPS (2023)
Keyphrases
- audio visual
- weakly supervised
- multi modal
- topic models
- relation extraction
- superpixels
- object class
- visual information
- visual data
- semi supervised
- natural language
- multimedia
- natural language processing
- named entities
- e learning
- machine learning
- data sets
- semantic relations
- object detectors
- image features
- data points
- high dimensional
- moving objects
- data analysis
- multiscale