# Ensemble One-dimensional Convolution Neural Networks for Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/1801.02475 · HTML: https://mlsanity.com/paper/1801.02475/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2018.

## Built on by (most cited first, 10 of 10)

- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition](https://mlsanity.com/paper/2112.10992/) (2021)
- [One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching](https://mlsanity.com/paper/2307.07286/) (2023)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [3D Plant Root Skeleton Detection and Extraction](https://mlsanity.com/paper/2508.08094/) (2025)
- [Theater Aid System for the Visually Impaired Through Transfer Learning of Spatio-Temporal Graph Convolution Networks](https://mlsanity.com/paper/2306.16357/) (2023)
- [Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition](https://mlsanity.com/paper/2207.10519/) (2022)
- [TemporalAugmenter: An Ensemble Recurrent Based Deep Learning Approach for Signal Classification](https://mlsanity.com/paper/2401.06970/) (2024)
- [Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition](https://mlsanity.com/paper/2401.14034/) (2024)
- [One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning](https://mlsanity.com/paper/2609.07078/) (2026)

## Abstract (arXiv)

In this paper, we proposed a effective but extensible residual one-dimensional convolution neural network as base network, based on the this network, we proposed four subnets to explore the features of skeleton sequences from each aspect. Given a skeleton sequences, the spatial information are encoded into the skeleton joints coordinate in a frame and the temporal information are present by multiple frames. Limited by the skeleton sequence representations, two-dimensional convolution neural network cannot be used directly, we chose one-dimensional convolution layer as the basic layer. Each sub network could extract discriminative features from different aspects. Our first subnet is a two-stream network which could explore both temporal and spatial information. The second is a body-parted network, which could gain micro spatial features and macro temporal features. The third one is an attention network, the main contribution of which is to focus the key frames and feature channels which high related with the action classes in a skeleton sequence. One frame-difference network, as the last subnet, mainly processes the joints changes between the consecutive frames. Four subnets ensemble together by late fusion, the key problem of ensemble method is each subnet should have a certain performance and between the subnets, there are diversity existing. Each subnet shares a wellperformance basenet and differences between subnets guaranteed the diversity. Experimental results show that the ensemble network gets a state-of-the-art performance on three widely used datasets.