TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

SotA/Computer Vision/Video/Kinetics-600 12 frames, 64x64

Video on Kinetics-600 12 frames, 64x64

Metric: FVD (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕FVD▼Extra DataPaperDate↕Code
1LVT224.73NoLatent Video Transformer2020-06-18Code
2OmniTokenizer-AR32.9NoOmniTokenizer: A Joint Image-Video Tokenizer for...2024-06-13Code
3DVD-GAN31.1NoAdversarial Video Generation on Complex Datasets2019-07-15Code
4RaMViD16.46NoDiffusion Models for Video Prediction and Infill...2022-06-15Code
5RIN (400 steps)11.5NoScalable Adaptive Computation for Iterative Gene...2022-12-22Code
6RIN (1000 steps)10.8NoScalable Adaptive Computation for Iterative Gene...2022-12-22Code
7MAGVIT9.9NoMAGVIT: Masked Generative Video Transformer2022-12-10Code
8LARP5.1NoLARP: Tokenizing Videos with a Learned Autoregre...2024-10-28Code
9W.A.L.T.-L3.3NoPhotorealistic Video Generation with Diffusion M...2023-12-11-
10SiD22.3NoSimpler Diffusion (SiD2): 1.5 FID on ImageNet512...2024-10-25-