AI Paper Atlas

Research map / 3D vision / Human pose estimation

Prompting Future Driven Diffusion Model for Hand Motion Prediction

Bowen Tang, Kaihao Zhang, Wenhan Luo, Wei Liu, HONGDONG LI

ECCV 2024 · 3D vision › Human pose estimation · approach: Human motion prediction · 9 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 the future-driven prompting (GTEN/RDGN) to STEN (ablation)PromptFDDM · FPHAADE: 0.473 -> 0.413Improved
add SE-block to ST-GCN units (ablation)PromptFDDM · HO3DADE: 0.196 -> 0.163Improved
add SE-block to ST-GCN units (ablation)PromptFDDM · FPHAAPD: 16.008 -> 19.798Improved
add interactive prompts (ablation)PromptFDDM · HO3DAPD: 3.851 -> 4.541Improved
add interactive prompts (ablation)PromptFDDM · HO3DADE: 0.161 -> 0.163No clear effect
use Linear variance scheduler instead of Sqrt or Cosine (ablation)PromptFDDM · FPHAADE: 0.452 (Sqrt), 0.448 (Cosine) -> 0.413Improved
use L = 20 DCT rows instead of 5 (ablation)PromptFDDM · HO3DAPD: 1.532 -> 4.541Improved
increase noise prediction network layers (2 to 12) (ablation)PromptFDDM · FPHAADE: 0.419 -> 0.422No clear effect
use PromptFDDM instead of HumanMAC on HO3D accuracyPromptFDDM · HO3DADE: 0.155 (HumanMAC) vs 0.163Mixed

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