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/UniVL + MELTR

UniVL + MELTR

Reported on 37 benchmarks across 4 tasks · 1 paper · 6 SOTA

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

Computer Vision33 results

VideoonYouCook2
text-to-video R@1· 2023-03-23
33.7
best: 50.4 (VAST)
SOTA
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonYouCook2
BLEU-3· 2023-03-23
24.12
SOTA
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonYouCook2
BLEU-4· 2023-03-23
17.92
best: 18.2 (VAST)
SOTA
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonYouCook2
METEOR· 2023-03-23
22.56
SOTA
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonYouCook2
ROUGE-L· 2023-03-23
47.04
SOTA
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonYouCook2
text-to-video R@1· 2023-03-23
33.7
best: 50.4 (VAST)
SOTA
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT-1kA
text-to-video Median Rank· 2023-03-23
4
best: 13 (JSFusion)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT-1kA
text-to-video R@1· 2023-03-23
31.1
best: 62.9 (HunYuan_tvr (huge))
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT-1kA
text-to-video R@10· 2023-03-23
68.3
best: 90.8 (HunYuan_tvr (huge))
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT-1kA
text-to-video R@5· 2023-03-23
55.7
best: 84.5 (HunYuan_tvr (huge))
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonYouCook2
text-to-video Median Rank· 2023-03-23
3
best: 77 (Satar et al.)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonYouCook2
text-to-video R@10· 2023-03-23
74.8
best: 80.8 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonYouCook2
text-to-video R@5· 2023-03-23
63.1
best: 74.3 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT
text-to-video Median Rank· 2023-03-23
4
best: 55 (C+LSTM+SA+FC7)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT
text-to-video R@1· 2023-03-23
28.5
best: 64 (GRAM)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT
text-to-video R@10· 2023-03-23
67.6
best: 89.6 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
VideoonMSR-VTT
text-to-video R@5· 2023-03-23
55.5
best: 84.3 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonMSR-VTT
BLEU-4· 2023-03-23
44.17
best: 57.8 (mPLUG-2)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonMSR-VTT
CIDEr· 2023-03-23
52.77
best: 80 (mPLUG-2)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonMSR-VTT
METEOR· 2023-03-23
29.26
best: 38.7 (MV-GPT)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonMSR-VTT
ROUGE-L· 2023-03-23
62.35
best: 70.1 (mPLUG-2)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video CaptioningonYouCook2
CIDEr· 2023-03-23
1.9
best: 116.4 (HowToCaption)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT-1kA
text-to-video Median Rank· 2023-03-23
4
best: 13 (JSFusion)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· 2023-03-23
31.1
best: 62.9 (HunYuan_tvr (huge))
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· 2023-03-23
68.3
best: 90.8 (HunYuan_tvr (huge))
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· 2023-03-23
55.7
best: 84.5 (HunYuan_tvr (huge))
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonYouCook2
text-to-video Median Rank· 2023-03-23
3
best: 77 (Satar et al.)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonYouCook2
text-to-video R@10· 2023-03-23
74.8
best: 80.8 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonYouCook2
text-to-video R@5· 2023-03-23
63.1
best: 74.3 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT
text-to-video Median Rank· 2023-03-23
4
best: 55 (C+LSTM+SA+FC7)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT
text-to-video R@1· 2023-03-23
28.5
best: 64 (GRAM)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT
text-to-video R@10· 2023-03-23
67.6
best: 89.6 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Video RetrievalonMSR-VTT
text-to-video R@5· 2023-03-23
55.5
best: 84.3 (VAST)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009

Natural Language Processing4 results

Sentiment AnalysisonCMU-MOSI
Acc-2· 2023-03-23
85.3
best: 90.35 (MMML)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Sentiment AnalysisonCMU-MOSI
Corr· 2023-03-23
0.789
best: 0.8824 (MMML)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Sentiment AnalysisonCMU-MOSI
F1· 2023-03-23
85.4
best: 90.35 (MMML)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009
Sentiment AnalysisonCMU-MOSI
MAE· 2023-03-23
0.759
best: 0.5573 (MMML)
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models arXiv:2303.13009