AI Paper Atlas

Research map / Video / Action recognition

Few-shot Action Recognition with Permutation-invariant Attention

Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip H. S. Torr, Piotr Koniusz

ECCV 2020 · Video › Action recognition · approach: Disentangled action recognition · 208 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 attention (ablation)C3D SoSN baseline · HMDB51 (proposed split), 5-way 1-shotaccuracy: 40.83 -> 41.27Improved
add temporal attention (ablation)C3D SoSN baseline · HMDB51 (proposed split), 5-way 5-shotaccuracy: 55.18 -> 57.67Improved
add spatial jigsaw self-supervision (ablation)C3D SoSN baseline · HMDB51 (proposed split), 5-way 1-shotaccuracy: 40.83 -> 44.19Improved
add self-supervision to attention model (ablation)ARN with spatial attention · HMDB51 (proposed split), 5-way 1-shotaccuracy: 41.27 -> 44.61Improved
replace naive attention with attention by alignment (ablation)ARN with spatial attention and self-supervision · HMDB51 (proposed split), 5-way 1-shotaccuracy: 44.61 -> 45.17Improved
add alignment loss without self-supervision (ablation)ARN with spatial attention · HMDB51 (proposed split), 5-way 1-shotaccuracy: 41.27 -> 43.11Improved
combine attention, self-supervision and alignment (ablation)C3D SoSN baseline · HMDB51 (proposed split), 5-way 1-shotaccuracy: 40.83 -> 45.17Improved
use second-order pooling with power normalization instead of average pooling (ablation)ARN · HMDB51 (proposed split), pooling, 5-way 1-shotaccuracy: 39.51 -> 40.83Improved
add power normalization to average pooling (ablation)ARN · HMDB51 (proposed split), pooling, 5-way 1-shotaccuracy: 39.51 -> 40.02Improved
add power normalization to second-order pooling (ablation)ARN · HMDB51 (proposed split), pooling, 5-way 1-shotaccuracy: 39.97 -> 40.83Improved
add pooling over blocks instead of none (ablation)ARN · HMDB51 (proposed split), pooling, 5-way 1-shotaccuracy: 35.71 -> 40.83Improved
swap spatial jigsaw for rotation self-supervision with alignment (ablation)ARN+SSA · HMDB51 (proposed split), 5-way 5-shotaccuracy: 60.56 -> 58.96Hurt

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