AI Paper Atlas

Research map / 3D vision / Human pose estimation

HPE-Li: WiFi-enabled Lightweight Dual Selective Kernel Convolution for Human Pose Estimation

Toan D. Gian, Tien Dac Lai, Thien Van Luong, Kok-Seng Wong, Van-Dinh Nguyen

ECCV 2024 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 14 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 frequency-wise selective kernel attention on top of channel-wise SK convolution (ablation)CNN with SKConv · MM-Fi P3-S2MPJPE (mm): 210.45 -> 182.62Improved
replace standard convolution with DSKConv (ablation)CNN backbone · MM-Fi P3-S2MPJPE (mm): 236.59 -> 182.62Improved
use DSKConv instead of dynamic convolution (ablation)CNN backbone · MM-Fi P3-S2MPJPE (mm): 218.92 -> 182.62Improved
use multiple kernel branches (N=4) instead of one (ablation)DSKNet · MM-Fi P3-S1MPJPE (mm): 152.67 -> 149.43Improved
increase branches from 4 to 5 (ablation)DSKNet · MM-Fi P3-S1MPJPE (mm): 149.43 -> 150.21Hurt
increase branches from 3 to 4 (ablation)DSKNet · MM-Fi P3-S1MPJPE (mm): 149.48 -> 149.43No clear effect
use dilated 3x3 (D=2) instead of undilated 5x5 kernel (ablation)DSKConv · MM-Fi P3-S1MPJPE (mm): 149.71 -> 149.43Improved
increase group number G from 32 to 128 (ablation)DSKConv · MM-Fi P3-S1MPJPE (mm): 150.57 -> 150.97No clear effect
set reduction ratio r to 32 versus 1 (ablation)DSKNet · MM-Fi P3-S1MPJPE (mm): 151.85 -> 149.43Improved
add uniform or median denoising filter under AWGN and salt-and-pepper noise (ablation)HPE-Li · MM-Fi P3-S1 with noiseMPJPE (mm)Improved
use plain MSE loss instead of pose adjacency matrix lossHPE-Li · MM-Fi and WiPosepose accuracyImproved

Later papers that compared with this method

2 later accepted papers report HPE-Li as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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