HQGA

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Reasoning5 results

Video Question AnsweringonNExT-QA
Accuracy· 2021-12-12
51.4
best: 85.5 (LinVT-Qwen2-VL (7B))
SOTA
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering arXiv:2112.06197
Video Question AnsweringonIntentQA
Accuarcy· 2021-12-12
47.7
best: 83.4 (VideoChat2_HD_mistral)
SOTA
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering arXiv:2112.06197
Video Question AnsweringonIntentQA
CH· 2021-12-12
54.3
best: 90 (VideoChat2_HD_mistral)
SOTA
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering arXiv:2112.06197
Video Question AnsweringonIntentQA
CW· 2021-12-12
48.2
best: 84 (VideoChat2_HD_mistral)
SOTA
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering arXiv:2112.06197
Video Question AnsweringonIntentQA
TP&TN· 2021-12-12
41.7
best: 79.1 (Human)
SOTA
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering arXiv:2112.06197