AI Paper Atlas

Research map / 3D vision / Human pose estimation

Aggregated Multi-GANs for Controlled 3D Human Motion Prediction

AAAI 2021 · 3D vision › Human pose estimation · approach: Human motion prediction · 57 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 five body-chain sub-GANs with aggregation instead of one whole-pose GAN (ablation)AM-GAN · H3.6m WalkingMAE: 0.90 -> 0.23 (80 ms); 2.01 -> 0.84 (1000 ms)Helped
Use five body-chain sub-GANs with aggregation instead of one whole-pose GAN (ablation)AM-GAN · H3.6m DiscussionMAE: 2.20 -> 0.28 (80 ms); 3.20 -> 1.58 (1000 ms)Helped
Add a local critic (ablation)AM-GAN · H3.6m WalkingMAE: 0.40 -> 0.23 (80 ms); 1.01 -> 0.84 (1000 ms)Helped
Add a local critic (ablation)AM-GAN · H3.6m DiscussionMAE: 0.40 -> 0.28 (80 ms); 2.89 -> 1.58 (1000 ms)Helped
Add a global critic (ablation)AM-GAN · H3.6m WalkingMAE: 0.35 -> 0.23 (80 ms); 1.92 -> 0.84 (1000 ms)Mixed
Add a global critic (ablation)AM-GAN · H3.6m DiscussionMAE: 0.29 -> 0.28 (80 ms); 1.19 -> 1.58 (1000 ms)Mixed
Use AM-GAN rather than QuaterNetH3.6m motion prediction · H3.6m Average (11 remaining actions)MAE: 0.38 -> 0.37 (80 ms); 1.82 -> 1.75 (1000 ms)Helped

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