InternVideo2

Reported on 5 benchmarks across 3 tasks · 1 paper · 5 SOTA

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

Audio2 results

Audio ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2024-03-22
98.6
best: 99.1 (OmniVec2)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Audio ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2024-03-22
98.6
best: 99.1 (OmniVec2)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Methodology2 results

ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2024-03-22
98.6
best: 99.1 (OmniVec2)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2024-03-22
98.6
best: 99.1 (OmniVec2)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Reasoning1 result

Video Question AnsweringonMVBench
Avg.· 2024-03-22
67.2
best: 69.3 (LinVT-Qwen2-VL (7B))
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377