Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching

By Wei Peng, Xiaopeng Hong, Haoyu Chen, Guoying Zhao. AAAI Conference on Artificial Intelligence, 2019

367 citations recorded by the source corpus.

Human action recognition from skeleton data, fuelled by the Graph Convolutional Network (GCN) with its powerful capability of modeling non-Euclidean data, has attracted lots of attention. However, many existing GCNs provide a pre-defined graph structure and share it through the entire network, which can loss implicit joint correlations especially for the higher-level features. Besides, the mainstream spectral GCN is approximated by one-order hop such that higher-order connections are not well involved. All of these require huge efforts to design a better GCN architecture. To address these problems, we turn to Neural Architecture Search (NAS) and propose the first automatically designed GCN for this task. Specifically, we explore the spatial-temporal correlations between nodes and build a search space with multiple dynamic graph modules. Besides, we introduce multiple-hop modules and expect to break the limitation of representational capacity caused by one-order approximation. Moreover, a corresponding sampling- and memory-efficient evolution strategy is proposed to search in this space. The resulted architecture proves the effectiveness of the higher-order approximation and the layer-wise dynamic graph modules. To evaluate the performance of the searched model, we conduct extensive experiments on two very large scale skeleton-based action recognition datasets. The results show that our model gets the state-of-the-art results in term of given metrics.

Subfields: Computer Vision and Pattern Recognition, Rehabilitation

View Paper: https://www.semanticscholar.org/paper/3b8076846879dc6e113d934a05b10ef49a34e6a3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Jun Liu
2. Qiuhong Ke
3. Hossein Rahmani
4. Zehua Sun
5. Hong Liu
6. Huan Zhao
7. Sicheng Li
8. Bing Yang

Citations in the corpus

• Pooling Architecture Search for Graph Classification (2021, methodology): “…used in [12, 22, 57, 59], sample architectures with RNN controller and then updated with policy gradient; EA based algorithms, used in [19, 24, 32], select parent architecture from the search space and generate new architectures with mutation [36] and crossover [35], select parent…”
• Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “[174] determined their GCN architecture via a neural architecture search scheme.”
• Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (2021, background): “…and Lin 2018) 88.3 81.5 AS-GCN (Li et al. 2019a) 94.2 86.8 2s AGC-LSTM (Si et al. 2019) 95.0 89.2 2s AGCN (Shi et al. 2019c) 95.1 88.5 2s NAS-GCN (Peng et al. 2020) 95.7 89.4 4s DGNN (Shi et al. 2019a) 96.1 89.9 4s MS-AAGCN (Shi et al. 2019b) 96.2 90.0 2s MS-G3D (Liu et al. 2020) 96.2 91.5 4s…”
• Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition (2020, neutral): “0 – – NAS-GCN [19] AAAI20 – 6.”
• Deep 3D human pose estimation: A review (2021, neutral): “While few works consider NAS for human activity recognition (Peng et al., 2020).”