CREMA

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Question AnsweringonSQA3D
AnswerExactMatch (Question Answering)· 2024-02-08
54.6
best: 43.42 (MCAN)
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion arXiv:2402.05889

Reasoning1 result

Video Question AnsweringonNExT-QA
Accuracy· 2024-02-08
73.9
best: 85.5 (LinVT-Qwen2-VL (7B))
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion arXiv:2402.05889