AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Bayesian Adversarial Human Motion Synthesis

Rui Zhao, Hui Su, Qiang Ji

CVPR 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 49 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM motion synthesis · CMU Motion CaptureInception Score: 2.77±0.08 -> 2.86±0.10Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM motion synthesis · Berkeley MHADInception Score: 6.19±0.38 -> 6.49±0.23Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM motion synthesis · CMU Motion CaptureMMD: 3.98±0.23 -> 2.41±0.35Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM motion synthesis · Berkeley MHADMMD: 67.26±0.21 -> 48.70±0.11Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · CMU Motion Capture, Joint set APCC: 0.86±0.12 -> 0.92±0.06Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · CMU Motion Capture, Joint set BPCC: 0.78±0.22 -> 0.85±0.15Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · Berkeley MHAD, Joint set APCC: 0.53±0.42 -> 0.68±0.25Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · Berkeley MHAD, Joint set BPCC: 0.67±0.36 -> 0.73±0.16Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · CMU Motion Capture, Joint set AMSE: 0.28±0.15 -> 0.11±0.05Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · CMU Motion Capture, Joint set BMSE: 0.24±0.79 -> 0.14±0.03Hurt
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · Berkeley MHAD, Joint set AMSE: 0.13±0.38 -> 0.12±0.29Improved
Use Bayesian posterior parameter samples instead of a single MAP estimate (ablation)BH-HSMM data restoration · Berkeley MHAD, Joint set BMSE: 0.21±0.31 -> 0.23±0.37Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy