TGANv2

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision2 results

VideoonUCF-101 16 frames, Unconditional, Single GPU
Inception Score· 2018-11-22
21.45
best: 22.91 (TGAN-F)
SOTA
Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN arXiv:1811.09245
VideoonUCF-101 16 frames, 128x128, Unconditional
Inception Score· 2018-11-22
24.34
best: 28.87 (TGANv2 (2020))
Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN arXiv:1811.09245

Natural Language Processing2 results

Video GenerationonUCF-101 16 frames, Unconditional, Single GPU
Inception Score· 2018-11-22
21.45
best: 22.91 (TGAN-F)
SOTA
Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN arXiv:1811.09245
Video GenerationonUCF-101 16 frames, 128x128, Unconditional
Inception Score· 2018-11-22
24.34
best: 28.87 (TGANv2 (2020))
Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN arXiv:1811.09245