Papers › Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition

Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition

20 Jan 2020IEEE Access ( Volume: 8 ) 2020 1archive 2025-07-28

Yanbo Fan, Shuchen Weng, Yong Zhang, Boxin Shi, Yi Zhang

Skeleton-based human action recognition is becoming popular due to its computational efficiency and robustness. Since not all skeleton joints are informative for action recognition, attention mechanisms are adopted to extract informative joints and suppress the influence of irrelevant ones. However, existing attention frameworks usually ignore helpful scenario context information. In this paper, we propose a cross-attention module that consists of a self-attention branch and a cross-attention branch for skeleton-based action recognition. It helps to extract joints that are not only more informative but also highly correlated to the corresponding scenario context information. Moreover, the cross-attention module maintains input variables’ size and can be flexibly incorporated into many existing frameworks without breaking their behaviors. To facilitate end-to-end training, we further develop a scenario context information extraction branch to extract context information from raw RGB video directly. We conduct comprehensive experiments on the NTU RGB+D and the Kinetics databases, and experimental results demonstrate the correctness and effectiveness of the proposed model.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionComputational EfficiencySkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D RGB+Skeleton (cross-attention) Accuracy (CS) 84.23 #99 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D RGB+Skeleton (cross-attention) Accuracy (CV) 89.27 #99 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections