Summary of Deep Heterogeneous Contrastive Hyper-graph Learning For In-the-wild Context-aware Human Activity Recognition, by Wen Ge et al.
Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity Recognition
by Wen Ge, Guanyi Mou, Emmanuel O. Agu, Kyumin Lee
First submitted to arxiv on: 27 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 proposed Deep Heterogeneous Contrastive Hyper-Graph Learning (DHC-HGL) framework addresses the challenging problem of multi-label classification in Human Activity Recognition (HAR). By capturing heterogenous Context-Aware HAR hypergraph properties, DHC-HGL outperforms state-of-the-art baselines by 5.8% to 16.7% on Matthews Correlation Coefficient (MCC) and 3.0% to 8.4% on Macro F1 scores in rigorous evaluation on two datasets. The framework innovatively constructs three sub-hypergraphs, each passed through custom HyperGraph Convolution (HGC) layers designed for edge-heterogeneity, and adopts a contrastive loss function for node-heterogeneity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to recognize human activities is proposed, which does better than other methods by correctly recognizing 5.8% to 16.7% more activities. This method works well on two different datasets and shows that it can be used in real-world applications. |
Keywords
» Artificial intelligence » Activity recognition » Classification » Contrastive loss
