Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser.
Yung-Hsuan LaiYen-Chun ChenYu-Chiang Frank WangPublished in: CoRR (2023)
Keyphrases
- audio visual
- weakly supervised
- multi modal
- topic models
- relation extraction
- object class
- superpixels
- semi supervised
- natural language processing
- natural language
- named entities
- multimedia
- visual information
- e learning
- information extraction
- visual data
- dimensionality reduction
- co occurrence
- question answering
- domain knowledge
- xml documents
- high dimensional
- object detectors
- image segmentation
- data sets