AI Paper Atlas

Research map / Video / Action recognition

Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion

Quoc-Huy Tran, Muhammad Ahmed, Murad Popattia, Muhammad Hassan Ahmed, Andrey Konin, Zeeshan Zia

ECCV 2024 · Video › Action recognition · approach: Skeleton-based action recognition · 4 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 spatial transformer to the heatmap video transformer (ablation)LA2DS · H2Ophase progression: 0.9039 -> 0.9280Improved
Add temporal transformer (ablation)LA2DS · H2Ophase classification accuracy: 64.40 -> 70.12Improved
Use joint+limb heatmaps instead of joints only (ablation)LA2DS · H2Ophase classification accuracy: 66.09 -> 70.12Improved
Add all four 2D heatmap augmentations versus none (ablation)LA2DS · H2Ophase classification accuracy: 63.12 -> 70.12Improved
Add temporal augmentation (ablation)LA2DS · H2Ophase classification accuracy: 64.82 -> 70.12Improved
Use temporally smooth correlated noise for position and orientation augmentationLA2DS · H2OaccuracyNo clear effect
Use 2D heatmaps instead of 3D coordinates under missing keypoints (p=100%)LA2DS vs CASA · H2Ophase classification accuracy: 60.93 -> 68.94Improved
Use 2D heatmaps instead of 3D coordinates under noisy keypointsLA2DS vs CASA · H2Ophase classification accuracy: 63.69 -> 68.23Improved
Fuse RGB with pose heatmaps (late fusion)LA2DS · Penn Actionphase classification accuracy: 92.63 -> 93.57Improved
Use video transformer ViViT on RGB inside LAVLAV · Penn Actionphase classification accuracy: 83.56 -> 70.66Hurt
Use STGCN encoder in CASACASA · Penn Actionphase classification accuracy: 88.55 -> 87.45Hurt
Use skeleton-only input versus RGB methods with few labelsLA2DS · IKEA ASMphase classification accuracy: 26.43 vs 29.78 (LAV)Mixed

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