Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Robots2 results

Activity RecognitiononHuman3.6M
MMDa· 2019-12-21
0.195
best: 0.419 (Deep Video Generation, Prediction and Completion of Human Action Sequences)
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions arXiv:1912.10150
Activity RecognitiononHuman3.6M
MMDs· 2019-12-21
0.218
best: 0.436 (Deep Video Generation, Prediction and Completion of Human Action Sequences)
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions arXiv:1912.10150

Computer Vision2 results

Human action generationonHuman3.6M
MMDa· 2019-12-21
0.195
best: 0.419 (Deep Video Generation, Prediction and Completion of Human Action Sequences)
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions arXiv:1912.10150
Human action generationonHuman3.6M
MMDs· 2019-12-21
0.218
best: 0.436 (Deep Video Generation, Prediction and Completion of Human Action Sequences)
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions arXiv:1912.10150