Summary of Topological Symmetry Enhanced Graph Convolution For Skeleton-based Action Recognition, by Zeyu Liang et al.
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
by Zeyu Liang, Hailun Xia, Naichuan Zheng, Huan Xu
First submitted to arxiv on: 19 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel approach to skeleton-based action recognition by introducing a Topological Symmetry Enhanced Graph Convolution (TSE-GC) that incorporates symmetry awareness and enables distinct topology learning across different channel partitions. The TSE-GC is combined with a Multi-Branch Deformable Temporal Convolution (MBDTC) for more flexible receptive fields and stronger modeling capacity of temporal dependencies. The resulting model, TSE-GCN, achieves competitive performance on three large datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA, with fewer parameters compared to state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about using computers to recognize human actions from video recordings. It’s trying to solve a problem where current methods are not taking into account the symmetry of the human body. The researchers propose two new techniques: one that helps the computer understand the structure of the action and another that lets it learn more about how actions change over time. They test their method on three big datasets and get good results, even using fewer calculations than other methods. |
Keywords
» Artificial intelligence » Gcn
