VATT-MBS

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision4 results

Zero-Shot Video RetrievalonYouCook2
text-to-video Mean Rank· 2021-04-22
13
SOTA
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text arXiv:2104.11178
Zero-Shot Video RetrievalonMSR-VTT
text-to-video Median Rank· 2021-04-22
49
best: 66 (MMT)
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text arXiv:2104.11178
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· 2021-04-22
29.7
best: 85.1 (InternVideo2-6B)
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text arXiv:2104.11178
Zero-Shot Video RetrievalonYouCook2
text-to-video R@10· 2021-04-22
45.5
best: 70.8 (OmniVec2)
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text arXiv:2104.11178