# Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition

arXiv: https://arxiv.org/abs/2307.11973 · HTML: https://mlsanity.com/paper/2307.11973/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 58 references that are in the map.
- First posted on arXiv 22 Jul 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [A Riemannian Network for SPD Matrix Learning](https://mlsanity.com/paper/1608.04233/) (2016)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1912.06971/) (2019)
- [Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables](https://mlsanity.com/paper/1604.08880/) (2016)
- [Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks](https://mlsanity.com/paper/1707.05740/) (2017)
- [3DV: 3D Dynamic Voxel for Action Recognition in Depth Video](https://mlsanity.com/paper/2005.05501/) (2020)
- [RGB-D-based Human Motion Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/1711.08362/) (2017)
- [Interaction Relational Network for Mutual Action Recognition](https://mlsanity.com/paper/1910.04963/) (2019)
- [GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition](https://mlsanity.com/paper/2111.13089/) (2021)
- [Skeleton-Based Online Action Prediction Using Scale Selection Network](https://mlsanity.com/paper/1902.03084/) (2019)
- [Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition](https://mlsanity.com/paper/2207.08095/) (2022)
- [Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs](https://mlsanity.com/paper/2207.12648/) (2022)

## Abstract (arXiv)

As a fundamental aspect of human life, two-person interactions contain meaningful information about people's activities, relationships, and social settings. Human action recognition serves as the foundation for many smart applications, with a strong focus on personal privacy. However, recognizing two-person interactions poses more challenges due to increased body occlusion and overlap compared to single-person actions. In this paper, we propose a point cloud-based network named Two-stream Multi-level Dynamic Point Transformer for two-person interaction recognition. Our model addresses the challenge of recognizing two-person interactions by incorporating local-region spatial information, appearance information, and motion information. To achieve this, we introduce a designed frame selection method named Interval Frame Sampling (IFS), which efficiently samples frames from videos, capturing more discriminative information in a relatively short processing time. Subsequently, a frame features learning module and a two-stream multi-level feature aggregation module extract global and partial features from the sampled frames, effectively representing the local-region spatial information, appearance information, and motion information related to the interactions. Finally, we apply a transformer to perform self-attention on the learned features for the final classification. Extensive experiments are conducted on two large-scale datasets, the interaction subsets of NTU RGB+D 60 and NTU RGB+D 120. The results show that our network outperforms state-of-the-art approaches in most standard evaluation settings.