Omni-VideoAssistant

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Natural Language Processing2 results

Question AnsweringonMSRVTT-QA
Accuracy· 2023-08-08
55.3
best: 72.4 (Flash-VStream)
SOTA
OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation arXiv:2308.04126
Question AnsweringonMSRVTT-QA
Confidence Score· 2023-08-08
3.3
best: 1.8 (Video LLaMA-7B)
OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation arXiv:2308.04126

Reasoning2 results

Video Question AnsweringonMSRVTT-QA
Accuracy· 2023-08-08
55.3
best: 72.4 (Flash-VStream)
SOTA
OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation arXiv:2308.04126
Video Question AnsweringonMSRVTT-QA
Confidence Score· 2023-08-08
3.3
best: 1.8 (Video LLaMA-7B)
OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation arXiv:2308.04126