LLoVi (GPT-3.5)

Reported on 4 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 Processing2 results

Question AnsweringonEgoSchema (fullset)
Accuracy· 2023-12-28
50.3
best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
A Simple LLM Framework for Long-Range Video Question-Answering arXiv:2312.17235
Question AnsweringonEgoSchema (subset)
Accuracy· 2023-12-28
57.6
best: 68.6 (Tarsier (34B))
A Simple LLM Framework for Long-Range Video Question-Answering arXiv:2312.17235

Reasoning2 results

Video Question AnsweringonEgoSchema (fullset)
Accuracy· 2023-12-28
50.3
best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
A Simple LLM Framework for Long-Range Video Question-Answering arXiv:2312.17235
Video Question AnsweringonEgoSchema (subset)
Accuracy· 2023-12-28
57.6
best: 68.6 (Tarsier (34B))
A Simple LLM Framework for Long-Range Video Question-Answering arXiv:2312.17235