# Relational Network for Skeleton-Based Action Recognition Source: [Relational Network for Skeleton-Based Action Recognition]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:59:51.381Z Authors: Wu Zheng, Lin Li, Zhaoxiang Zhang, Yan Huang, Liang Wang Published: 2018-05-07T14:59:54.000Z ## Abstract With the fast development of effective and low-cost human skeleton capture systems, skeleton-based action recognition has attracted much attention recently. Most existing methods use Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to extract spatio-temporal information embedded in the skeleton sequences for action recognition. However, these approaches are limited in the ability of relational modeling in a single skeleton, due to the loss of important structural information when converting the raw skeleton data to adapt to the input format of CNN or RNN. In this paper, we propose an Attentional Recurrent Relational Network-LSTM (ARRN-LSTM) to simultaneously model spatial configurations and temporal dynamics in skeletons for action recognition. We introduce the Recurrent Relational Network to learn the spatial features in a single skeleton, followed by a multi-layer LSTM to learn the temporal features in the skeleton sequences. Between the two modules, we design an adaptive attentional module to focus attention on the most discriminative parts in the single skeleton. To exploit the complementarity from different geometries in the skeleton for sufficient relational modeling, we design a two-stream architecture to learn the structural features among joints and lines simultaneously. Extensive experiments are conducted on several popular skeleton datasets and the results show that the proposed approach achieves better results than most mainstream methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Action Recognition on Florence 3D (leave-one-subject-out cross val)](): Action Recognition; Florence 3D (leave-one-subject-out cross val); Accuracy: 98.52. - [Action Recognition on MSRAction3D](): Action Recognition; MSRAction3D; Accuracy: 95. - [Action Recognition on NTU RGB+D (Cross-subject)](): Action Recognition; NTU RGB+D (Cross-subject); Accuracy: 81.8. - [Action Recognition on NTU RGB+D (Cross-View)](): Action Recognition; NTU RGB+D (Cross-View); Accuracy: 89.6. ## Original sources and implementation [Original paper]() [PDF]()