Skip to main content

Shifting Perspective to See Difference: A Novel Multi-view Method for Skeleton based Action Recognition.

Hou, R., Li, Y., Zhang, N., Zhou, Y., Yang, X. and Wang, Z., 2022. Shifting Perspective to See Difference: A Novel Multi-view Method for Skeleton based Action Recognition. In: MM '22: Proceedings of the 30th ACM International Conference on Multimedia. New York: Association for Computing Machinery, 4987-4995.

Full text available as:

ACM MM 2022.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


DOI: 10.1145/3503161.3548210


Skeleton-based human action recognition is a longstanding challenge due to its complex dynamics. Some fine-grain details of the dynamics play a vital role in classification. The existing work largely focuses on designing incremental neural networks with more complicated adjacent matrices to capture the details of joints relationships. However, they still have difficulties distinguishing actions that have broadly similar motion patterns but belong to different categories. Interestingly, we found that the subtle differences in motion patterns can be significantly amplified and become easy for audience to distinct through specified view directions, where this property haven't been fully explored before. Drastically different from previous work, we boost the performance by proposing a conceptually simple yet effective Multi-view strategy that recognizes actions from a collection of dynamic view features. Specifically, we design a novel Skeleton-Anchor Proposal (SAP) module which contains a Multi-head structure to learn a set of views. For feature learning of different views, we introduce a novel Angle Representation to transform the actions under different views and feed the transformations into the baseline model. Our module can work seamlessly with the existing action classification model. Incorporated with baseline models, our SAP module exhibits clear performance gains on many challenging benchmarks. Moreover, comprehensive experiments show that our model consistently beats down the state-of-the-art and remains effective and robust especially when dealing with corrupted data. Related code will be available on

Item Type:Book Section
Group:Faculty of Media & Communication
ID Code:38704
Deposited By: Symplectic RT2
Deposited On:15 Jun 2023 15:32
Last Modified:15 Jun 2023 15:32


Downloads per month over past year

More statistics for this item...
Repository Staff Only -