MovieChat+

Reported on 2 benchmarks across 1 task · 1 paper

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

Natural Language Processing2 results

Question AnsweringonNExT-QA (Open-ended VideoQA)
Accuracy· 2024-04-26
54.8
best: 61.6 (Flash-VStream)
MovieChat+: Question-aware Sparse Memory for Long Video Question Answering arXiv:2404.17176
Question AnsweringonNExT-QA (Open-ended VideoQA)
Confidence Score· 2024-04-26
3
best: 2.7 (MovieChat)
MovieChat+: Question-aware Sparse Memory for Long Video Question Answering arXiv:2404.17176