AI Paper Atlas

Research map / 3D vision / Human pose estimation

Pose Forecasting in Industrial Human-Robot Collaboration

Alessio Sampieri, Guido Maria D’Amely di Melendugno, Andrea Avogaro, Federico Cunico, Francesco Setti, Geri Skenderi, Marco Cristani, Fabio Galasso

ECCV 2022 · 3D vision › Human pose estimation · approach: Human motion prediction · 53 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 space-time separable adjacency (STS-GCN) instead of plain GCN (ablation)GCN · Human3.6M (1000 ms)MPJPE (mm): 123.2 -> 117.0Improved
add a 5th layer to STS-GCN (ablation)STS-GCN · Human3.6M (1000 ms)MPJPE (mm): 117.0 -> 115.9Improved
add a 6th layer to STS-GCN (ablation)STS-GCN · Human3.6M (1000 ms)MPJPE (mm): 115.9 -> 116.1Hurt
add MLP layers between GCN layers (5+5) (ablation)STS-GCN · Human3.6M (1000 ms)MPJPE (mm): 115.9 -> 125.2Hurt
use depth-wise separable convolutions with MLP layers (5+5) (ablation)STS-GCN · Human3.6M (1000 ms)MPJPE (mm): 117.0 -> 114.8Improved
add depth-wise separable convolution to STS-GCN, parameters (ablation)STS-GCN · Human3.6M (1000 ms)parameters (K): 57.6 -> 70.0Hurt
sparsify adjacency with Sparse-GCN learned masks (ablation)STS-DW-GCN · Human3.6M (1000 ms)MPJPE (mm): 114.8 -> 115.7Hurt
sparsify adjacency via teacher-student framework (ablation)STS-DW-GCN · Human3.6M (1000 ms)MPJPE (mm): 114.8 -> 113.9Improved
teacher-student sparsification, parameter count (ablation)STS-DW-GCN · Human3.6M (1000 ms)parameters (K): 70.0 -> 58.6Improved
SeS-GCN vs DCT-RNN-GCN (state of the art)SeS-GCN · Human3.6M (1000 ms)MPJPE (mm): 113.9 vs 112.1No clear effect
SeS-GCN vs STS-GCN on CHICO short termSTS-GCN · CHICO (400 ms)MPJPE (mm): 53.0 -> 48.8Improved
SeS-GCN vs STS-GCN on CHICO long termSTS-GCN · CHICO (1000 ms)MPJPE (mm): 87.4 -> 85.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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