AI Paper Atlas

Research map / 3D vision / Human pose estimation

Social Diffusion: Long-term Multiple Human Motion Anticipation

Julian Tanke, Linguang Zhang, Amy Zhao, Chengcheng Tang, Yujun Cai, Lezi Wang, Po-Chen Wu, Juergen Gall, Cem Keskin

ICCV 2023 · 3D vision › Human pose estimation · approach: Human motion prediction · 30 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
use diffusion with causal temporal convolution instead of autoregressive transformermulti-person motion anticipation · 3DPWMPJPE (dm): 7.83 -> 3.55 at 3sImproved
Social Diffusion versus HRI at 1 second on MuPoTS-3DSocial Diffusion · MuPoTS-3DMPJPE (dm): 0.94 -> 1.15Hurt
forecast long-term with non-autoregressive diffusion instead of MRT autoregressiveSocial Diffusion · HagglingNDMS at frame 1300: 0.047 -> 0.226Improved
add order-invariant aggregation of other people's information (average) (ablation)Social Diffusion · HagglingSSCP: 0.3576 -> 0.3252Improved
add order-invariant aggregation (average) (ablation)Social Diffusion · HagglingNDMS: 0.2301 -> 0.2297No clear effect
use average aggregation instead of multi-head attention (ablation)Social Diffusion · HagglingSSCP: 0.3278 -> 0.3252Improved
add context aggregation for buyer role preservation (ablation)Social Diffusion · Hagglingbuyer detection accuracy: 0.8812 -> 0.8938Improved

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