# Two-Stream RNN/CNN for Action Recognition in 3D Videos

arXiv: https://arxiv.org/abs/1703.09783 · HTML: https://mlsanity.com/paper/1703.09783/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2017.

## Built on by (most cited first, 7 of 7)

- [Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives](https://mlsanity.com/paper/2406.05615/) (2024)
- [CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner](https://mlsanity.com/paper/2403.10082/) (2024)
- [Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition](https://mlsanity.com/paper/2202.11374/) (2022)
- [RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model](https://mlsanity.com/paper/2407.06162/) (2024)
- [SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation](https://mlsanity.com/paper/2311.17428/) (2023)
- [A Novel Deep Hybrid Framework with Ensemble-Based Feature Optimization for Robust Real-Time Human Activity Recognition](https://mlsanity.com/paper/2508.18695/) (2025)
- [Learning Scene Flow With Skeleton Guidance For 3D Action Recognition](https://mlsanity.com/paper/2306.13285/) (2023)

## Abstract (arXiv)

The recognition of actions from video sequences has many applications in health monitoring, assisted living, surveillance, and smart homes. Despite advances in sensing, in particular related to 3D video, the methodologies to process the data are still subject to research. We demonstrate superior results by a system which combines recurrent neural networks with convolutional neural networks in a voting approach. The gated-recurrent-unit-based neural networks are particularly well-suited to distinguish actions based on long-term information from optical tracking data; the 3D-CNNs focus more on detailed, recent information from video data. The resulting features are merged in an SVM which then classifies the movement. In this architecture, our method improves recognition rates of state-of-the-art methods by 14% on standard data sets.