AI Paper Atlas

Research map / 3D vision / Human pose estimation

An Adversarial Hierarchical Hidden Markov Model for Human Pose Modeling and Generation

Rui Zhao, Qiang Ji

AAAI 2018 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 14 citations (OpenAlex)

Read the paperCheck 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
add Bayesian hierarchy over parameters (HMM to HHMM)HMM · CMU reconstructionPCC: 0.36 -> 0.81Improved
add Bayesian hierarchy over parameters (HMM to HHMM)HMM · Berkeley reconstructionMSE: 0.87 -> 0.12Improved
train HHMM adversarially instead of by maximum likelihood (ablation)HHMM · Berkeley jumping reconstructionPCC and MSEImproved
train HHMM adversarially instead of by maximum likelihood (ablation)HHMM · reconstructiontraining log-likelihoodHurt
train HHMM adversarially instead of by maximum likelihood (ablation)HHMM · CMU and Berkeley synthesisaverage max SSIM (diversity, lower better)Improved
increase number of hidden states (ablation)HMM · Berkeley jumping reconstructionPCC/MSEHurt
increase number of hidden states (ablation)HHMM · Berkeley jumping reconstructionPCC/MSENo clear effect

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