AI Paper Atlas

Research map / Video / Action recognition

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

Xingyu Liu, Sanping Zhou, Le Wang, Gang Hua

ICCV 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 15 citations (OpenAlex)

Read the paper

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
replace DASTM with PAINet's parallel attention branchesfew-shot skeleton action recognition · NTU-T 5-way 1-shot, ST-GCNaccuracy (%): 75.1 -> 82.4Improved
replace DASTM with PAINetfew-shot skeleton action recognition · Kinetics 5-way 1-shot, ST-GCNaccuracy (%): 39.3 -> 42.4Improved
add Temporal-Channel Mixer to the Cross Spatial Alignment branch (ablation)PAINet · NTU-T 1-shot, ST-GCNaccuracy (%): 80.1 -> 79.3Hurt
add Temporal-Channel Mixer to the Cross Temporal Alignment branch (ablation)PAINet · NTU-T 1-shot, ST-GCNaccuracy (%): 78.9 -> 80.8Improved
add spatial self-attention to the temporal alignment branch (ablation)PAINet · NTU-T 1-shot, ST-GCNaccuracy (%): 80.8 -> 81.8Improved
merge the two parallel branches (ablation)PAINet · NTU-T 1-shot, ST-GCNaccuracy (%): 81.8 -> 82.4Improved
add joint-part and joint-semantic relations to spatial self-attention (ablation)spatial aggregation · NTU-T 1-shot, ST-GCNaccuracy (%): 81.9 -> 82.4Improved
use random masking in spatial self-attention (ablation)spatial aggregation · NTU-T 1-shot, ST-GCNaccuracy (%): 81.9 -> 81.6Hurt
use channel-specific attention instead of self-attention (ablation)spatial aggregation · NTU-T 1-shot, ST-GCNaccuracy (%): 81.9 -> 80.8Hurt
use directional average symmetric surface metric on frame pairs instead of Hungarian matching (ablation)temporal set metric · NTU-T 1-shot, ST-GCNaccuracy (%): 80.5 -> 82.4Improved
use pair-based instead of frame-based subsequences with DASSM (ablation)temporal set metric · NTU-T 1-shot, ST-GCNaccuracy (%): 81.3 -> 82.4Improved
use complex MS-G3D backbone instead of ST-GCNPAINet · NTU-T 1-shotaccuracy (%): 82.4 -> 81.3No clear effect

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