AI Paper Atlas

Research map / Video / Action recognition

PoTion: Pose MoTion Representation for Action Recognition

Vasileios Choutas, Philippe Weinzaepfel, Jérôme Revaud, Cordelia Schmid

CVPR 2018 · Video › Action recognition · approach: Skeleton-based action recognition · 351 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 PoTion to I3DI3D† · JHMDBmean per-class accuracy: 84.1 -> 85.5Improved
Add PoTion to I3DI3D† · HMDBmean per-class accuracy: 80.6 -> 80.9Improved
Add PoTion to I3DI3D† · UCF101mean per-class accuracy: 97.7 -> 98.2Improved
Use intensity-only I aggregation instead of stacked U + I + N (ablation)PoTion · JHMDB-1mean class accuracy: 58.5 ± 1.5 -> 52.2 ± 2.7Hurt
Use intensity-only I aggregation instead of stacked U + I + N (ablation)PoTion · HMDB-1mean class accuracy: 44.4 ± 1.3 -> 43.3 ± 0.4No clear effect
Use U aggregation only instead of stacked U + I + N (ablation)PoTion · HMDB-1mean class accuracy: 44.4 ± 1.3 -> 44.1 ± 0.9No clear effect
Use N aggregation only instead of stacked U + I + N (ablation)PoTion · HMDB-1mean class accuracy: 44.4 ± 1.3 -> 42.5 ± 0.9Hurt
Add random horizontal flip augmentation (ablation)PoTion training · JHMDB-1mean class accuracy: 51.3 ± 5.7 -> 58.5 ± 1.5Improved
Add random horizontal flip augmentation (ablation)PoTion training · HMDB-1mean class accuracy: 43.4 ± 0.6 -> 44.4 ± 1.3No clear effect
Replace estimated pose with ground-truth puppet pose (ablation)PoTion · JHMDB-1mean class accuracy: 58.5 ± 1.5 -> 62.1 ± 1.1Improved
Crop around the puppet when using ground-truth pose (ablation)PoTion with puppet pose · JHMDB-1mean class accuracy: 62.1 ± 1.1 -> 67.9 ± 2.4Improved
Use 1 convolution per block instead of 2 (ablation)PoTion classifier · JHMDB-1mean class accuracy: 58.5 ± 1.5 -> 54.1 ± 1.3Hurt

Later papers that compared with this method

1 later accepted paper reports PoTion as a baseline in their results tables; 1 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