Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MuLTI

MuLTI

Reported on 14 benchmarks across 3 tasks · 1 paper

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

Computer Vision12 results

VideoonMSR-VTT-1kA
text-to-video R@1· 2023-03-10
54.7
best: 62.9 (HunYuan_tvr (huge))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
VideoonMSR-VTT-1kA
text-to-video R@10· 2023-03-10
86
best: 90.8 (HunYuan_tvr (huge))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
VideoonMSR-VTT-1kA
text-to-video R@5· 2023-03-10
77.7
best: 84.5 (HunYuan_tvr (huge))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
VideoonDiDeMo
text-to-video R@1· uses extra data· 2023-03-10
56.5
best: 74.2 (InternVideo2-6B)
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
VideoonDiDeMo
text-to-video R@10· uses extra data· 2023-03-10
87
best: 94.2 (vid-TLDR (UMT-L))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
VideoonDiDeMo
text-to-video R@5· uses extra data· 2023-03-10
80.2
best: 91.2 (vid-TLDR (UMT-L))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· 2023-03-10
54.7
best: 62.9 (HunYuan_tvr (huge))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· 2023-03-10
86
best: 90.8 (HunYuan_tvr (huge))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· 2023-03-10
77.7
best: 84.5 (HunYuan_tvr (huge))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2023-03-10
56.5
best: 74.2 (InternVideo2-6B)
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2023-03-10
87
best: 94.2 (vid-TLDR (UMT-L))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2023-03-10
80.2
best: 91.2 (vid-TLDR (UMT-L))
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707

Natural Language Processing2 results

Visual Question Answering (VQA)onMSRVTT-QA
Accuracy· uses extra data· 2023-03-10
0.478
best: 0.496 (VLAB)
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707
Visual Question Answering (VQA)onMSVD-QA
Accuracy· uses extra data· 2023-03-10
0.547
best: 0.61 (VLAB)
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling arXiv:2303.05707