# Action Recognition for Depth Video using Multi-view Dynamic Images

arXiv: https://arxiv.org/abs/1806.11269 · HTML: https://mlsanity.com/paper/1806.11269/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2018.

## Built on by (most cited first, 18 of 18)

- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [Contrastive Positive Mining for Unsupervised 3D Action Representation Learning](https://mlsanity.com/paper/2208.03497/) (2022)
- [Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning](https://mlsanity.com/paper/2207.09644/) (2022)
- [No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces](https://mlsanity.com/paper/2203.11113/) (2022)
- [Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer](https://mlsanity.com/paper/2407.12322/) (2024)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Real-time 3D human action recognition based on Hyperpoint sequence](https://mlsanity.com/paper/2111.08492/) (2021)
- [STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition](https://mlsanity.com/paper/2303.18177/) (2023)
- [Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2305.12959/) (2023)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)
- [KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition](https://mlsanity.com/paper/2409.09444/) (2024)
- [Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions](https://mlsanity.com/paper/2108.13055/) (2021)
- [Content-Distortion High-Order Interaction for Blind Image Quality Assessment](https://mlsanity.com/paper/2504.05076/) (2025)
- [Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer](https://mlsanity.com/paper/2504.20530/) (2025)
- [Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences](https://mlsanity.com/paper/2101.07618/) (2021)
- [Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations](https://mlsanity.com/paper/2411.10077/) (2024)
- [Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis](https://mlsanity.com/paper/2501.07221/) (2025)
- [GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representation](https://mlsanity.com/paper/2603.16154/) (2026)

## Abstract (arXiv)

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow for motion characterization, dynamic imaging exhibits superior efficiency and compactness. Inspired by the success of dynamic imaging in RGB video, this study extends it to the depth domain. To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed. In particular, the raw depth video is densely projected with respect to different virtual imaging viewpoints by rotating the virtual camera within the 3D space. Subsequently, dynamic images are extracted from the obtained multi-view depth videos and multi-view dynamic images are thus constructed from these images. Accordingly, more view-tolerant visual cues can be involved. A novel CNN model is then proposed to perform feature learning on multi-view dynamic images. Particularly, the dynamic images from different views share the same convolutional layers but correspond to different fully connected layers. This is aimed at enhancing the tuning effectiveness on shallow convolutional layers by alleviating the gradient vanishing problem. Moreover, as the spatial occurrence variation of the actions may impair the CNN, an action proposal approach is also put forth. In experiments, the proposed approach can achieve state-of-the-art performance on three challenging datasets.