AI Paper Atlas

Research map / Video / Action recognition

Making the Invisible Visible: Action Recognition Through Walls and Occlusions

Tianhong Li, Lijie Fan, Mingmin Zhao, Yingcheng Liu, Dina Katabi

ICCV 2019 · Video › Action recognition · approach: Skeleton-based action recognition · 144 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 spatio-temporal attention module (ablation)RF-Action · RF-MMD (IoU 0.5)mAP: 80.1 -> 87.8Improved
add spatio-temporal attention module (ablation)RF-Action · PKU-MMDmAP: 92.6 -> 92.9 and 94.2 -> 94.4Improved
add spatio-temporal attention module (ablation)RF-Action · NTU-RGB+Daccuracy: 86.5 -> 86.8 and 91.1 -> 91.6Improved
add multi-proposal module instead of single proposal (ablation)RF-Action · RF-MMD (IoU 0.5)mAP: 65.5 -> 87.8Improved
add PKU-MMD vision skeleton data to RF-MMD training (multimodal training) (ablation)RF-Action · RF-MMD testmAP: 83.3 -> 87.8Improved
add RF-MMD to PKU-MMD training (multimodal training) (ablation)RF-Action · PKU-MMD testmAP: 92.9 -> 93.3 and 94.4 -> 94.9Improved
add PKU-MMD to training versus RF-MMD only, tested on PKU-MMD (ablation)RF-Action · PKU-MMD testmAP: 60.1 -> 93.3 and 60.4 -> 94.9Improved
train end-to-end so action loss backpropagates through skeleton generation (ablation)RF-Action · RF-MMD (IoU 0.5)mAP: 84.3 -> 87.8Improved
train end-to-end so action loss backpropagates through skeleton generation (ablation)RF-Action · RF-MMD skeleton errorskeleton error (cm): 3.8 -> 3.4Improved
use camera ground-truth skeletons instead of RF-derived skeletons at inferenceRF-Action · RF-MMD visible scenes (IoU 0.5)mAP: 87.8 -> 90.5Improved
RF-Action versus HCN on the same skeletonsRF-Action · RF-MMD through-wall (IoU 0.5)mAP: 75.9 -> 83.0Improved
occlusion by walls (through-wall versus visible)RF-Action · RF-MMD (IoU 0.5)mAP: 87.8 -> 83.0Hurt

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