AI Paper Atlas

Research map / 3D vision / Human pose estimation

BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN

AAAI 2019 · 3D vision › Human pose estimation · approach: Human motion prediction · 133 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 BiHMP-GAN instead of Conv-MotionHuman motion prediction · Human 3.6M, Walking, 1000msprediction error: 0.92 -> 0.85Helped
Use BiHMP-GAN instead of Conv-MotionHuman motion prediction · Human 3.6M, Eating, 1000msprediction error: 1.24 -> 1.20Helped
Use BiHMP-GAN instead of Conv-MotionHuman motion prediction · Human 3.6M, Smoking, 1000msprediction error: 1.62 -> 1.11Helped
Use BiHMP-GAN instead of RRNNHuman motion prediction · Human 3.6M, Discussion, 1000msprediction error: 1.79 -> 1.77Helped
Add learned pose-embedding transformations (ablation)BiHMP-GAN · Human 3.6Mprediction errorHelped
Feed the intrinsic encoder hidden state along with the previous pose feature to the decoder (ablation)BiHMP-GAN · Human 3.6Mprediction errorHelped
Add recursive prediction regularization (ablation)BiHMP-GAN · Human 3.6Mlong-term prediction errorHelped

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