Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition

About

Graph Convolutional Networks (GCNs) have been widely used to model the high-order dynamic dependencies for skeleton-based action recognition. Most existing approaches do not explicitly embed the high-order spatio-temporal importance to joints' spatial connection topology and intensity, and they do not have direct objectives on their attention module to jointly learn when and where to focus on in the action sequence. To address these problems, we propose the To-a-T Spatio-Temporal Focus (STF), a skeleton-based action recognition framework that utilizes the spatio-temporal gradient to focus on relevant spatio-temporal features. We first propose the STF modules with learnable gradient-enforced and instance-dependent adjacency matrices to model the high-order spatio-temporal dynamics. Second, we propose three loss terms defined on the gradient-based spatio-temporal focus to explicitly guide the classifier when and where to look at, distinguish confusing classes, and optimize the stacked STF modules. STF outperforms the state-of-the-art methods on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400 datasets in all 15 settings over different views, subjects, setups, and input modalities, and STF also shows better accuracy on scarce data and dataset shifting settings.

Lipeng Ke, Kuan-Chuan Peng, Siwei Lyu• 2022

Related benchmarks

TaskDatasetResultRank
Action RecognitionNTU RGB+D 120 (X-set)
Accuracy89.9
661
Action RecognitionNTU RGB+D 60 (X-sub)
Accuracy92.5
467
Action RecognitionNTU RGB+D X-sub 120
Accuracy88.9
377
Skeleton-based Action RecognitionNTU RGB+D (Cross-View)
Accuracy96.9
213
Skeleton-based Action RecognitionNTU RGB+D 120 (X-set)
Top-1 Accuracy89.9
184
Action RecognitionNTU RGB+D X-View 60
Accuracy96.9
172
Skeleton-based Action RecognitionNTU RGB+D 120 Cross-Subject
Top-1 Accuracy88.9
143
Skeleton-based Action RecognitionNTU RGB+D 60 (X-View)
Top-1 Accuracy96.9
126
Skeleton-based Action RecognitionKinetics-Skeleton
Top-1 Acc39.9
82
Skeleton-based Action RecognitionNTU-RGB+D 120 (X-Sub)
Accuracy88.9
63
Showing 10 of 15 rows

Other info

Follow for update