Question Answering On Sqa3D
Metrics
AnswerExactMatch (Question Answering)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | AnswerExactMatch (Question Answering) |
|---|---|
| situational-awareness-matters-in-3d-vision | 52.6 |
| deep-modular-co-attention-networks-for-visual-1 | 43.42 |
| sqa3d-situated-question-answering-in-3d | 46.58 |
| frozen-transformers-in-language-models-are | 48.09 |
| sqa3d-situated-question-answering-in-3d | 47.20 |
| crema-multimodal-compositional-video | 54.6 |
| lexicon3d-probing-visual-foundation-models | 50.7 |