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/OPT

OPT

Reported on 10 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 Vision5 results

Image RetrievalonLocalized Narratives
Text-to-image R@1· 2021-07-01
0.4196
SOTA
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation arXiv:2107.00249
Image RetrievalonLocalized Narratives
Text-to-image R@10· 2021-07-01
0.8126
SOTA
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation arXiv:2107.00249
Image RetrievalonLocalized Narratives
Text-to-image R@5· 2021-07-01
0.72
SOTA
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation arXiv:2107.00249
VideoonVimeo90K
LPIPS
0.0359
best: 0.01 (CDFI)
VideoonVimeo90K
MS-SSIM
0.9675
best: 0.9701 (DMVFN)

Audio3 results

Text to Audio RetrievalonLocalized Narratives
Text-to-audio R@1· 2021-07-01
0.78
SOTA
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation arXiv:2107.00249
Text to Audio RetrievalonLocalized Narratives
Text-to-audio R@10· 2021-07-01
0.958
SOTA
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation arXiv:2107.00249
Text to Audio RetrievalonLocalized Narratives
Text-to-audio R@5· 2021-07-01
0.927
SOTA
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation arXiv:2107.00249

Time Series2 results

Video PredictiononVimeo90K
LPIPS
0.0359
Video PredictiononVimeo90K
MS-SSIM
0.9675
best: 0.9701 (DMVFN)