Papers › Global Context-Aware Attention LSTM Networks for 3D Action Recognition

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

1 Jul 2017CVPR 2017 7archive 2025-07-28

Jun Liu, Gang Wang, Ping Hu, Ling-Yu Duan, Alex C. Kot

Long Short-Term Memory (LSTM) networks have shown superior performance in 3D human action recognition due to their power in modeling the dynamics and dependencies in sequential data. Since not all joints are informative for action analysis and the irrelevant joints often bring a lot of noise, we need to pay more attention to the informative ones. However, original LSTM does not have strong attention capability. Hence we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for 3D action recognition, which is able to selectively focus on the informative joints in the action sequence with the assistance of global contextual information. In order to achieve a reliable attention representation for the action sequence, we further propose a recurrent attention mechanism for our GCA-LSTM network, in which the attention performance is improved iteratively. Experiments show that our end-to-end network can reliably focus on the most informative joints in each frame of the skeleton sequence. Moreover, our network yields state-of-the-art performance on three challenging datasets for 3D action recognition.

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

3D Action RecognitionAction AnalysisAction RecognitionOne-Shot 3D Action RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
One-Shot 3D Action Recognition NTU RGB+D 120 Fully Connected Accuracy 42.1% #9 of 10 Archive leaderboard report
One-Shot 3D Action Recognition NTU RGB+D 120 Attention Network Accuracy 41.0% #10 of 10 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D GCA-LSTM Accuracy (CS) 76.10 #119 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D GCA-LSTM Accuracy (CV) 84.00 #119 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 GCA-LSTM Accuracy (Cross-Setup) 59.2% #78 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 GCA-LSTM Accuracy (Cross-Subject) 58.3% #78 of 83 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