Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy.
Simon GingMaría Alejandra BravoThomas BroxPublished in: ICLR (2024)
Keyphrases
- open ended
- language model
- language modeling
- probabilistic model
- n gram
- decision trees
- information retrieval
- document retrieval
- classification accuracy
- speech recognition
- retrieval model
- image classification
- test collection
- feature vectors
- language modelling
- context sensitive
- statistical language models
- learning outcomes
- pseudo relevance feedback
- feature selection
- vector space model
- image database
- computer supported collaborative learning
- query expansion
- document ranking
- feature space
- ad hoc information retrieval
- language models for information retrieval
- language model for information retrieval