Enhancing Audio-Visual Question Answering with Missing Modality via Trans-Modal Associative Learning.
Kyu Ri ParkYoungmin OhJung Uk KimPublished in: ICASSP (2024)
Keyphrases
- audio visual
- question answering
- associative learning
- multi modal
- passage retrieval
- natural language processing
- natural language
- information extraction
- visual information
- information retrieval
- multimedia
- domain knowledge
- high dimensional
- visual data
- image data
- data mining
- hidden markov models
- labeled data
- reinforcement learning
- image annotation
- machine learning