# Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour

arXiv: https://arxiv.org/abs/2208.03819 · HTML: https://mlsanity.com/paper/2208.03819/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 53 references that are in the map.
- First posted on arXiv 7 Aug 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [Self-supervised Learning on Graphs: Deep Insights and New Direction](https://mlsanity.com/paper/2006.10141/) (2020)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition](https://mlsanity.com/paper/2010.09978/) (2020)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Universal Graph Transformer Self-Attention Networks](https://mlsanity.com/paper/1909.11855/) (2019)
- [Temporal Relational Modeling with Self-Supervision for Action Segmentation](https://mlsanity.com/paper/2012.07508/) (2020)
- [Feedback Graph Convolutional Network for Skeleton-based Action Recognition](https://mlsanity.com/paper/2003.07564/) (2020)
- [Quo Vadis, Skeleton Action Recognition ?](https://mlsanity.com/paper/2007.02072/) (2020)
- [Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model](https://mlsanity.com/paper/2011.02451/) (2020)
- [Structured Context Enhancement Network for Mouse Pose Estimation](https://mlsanity.com/paper/2012.00630/) (2020)

## Built on by (most cited first, 4 of 4)

- [CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey](https://mlsanity.com/paper/2301.06187/) (2023)
- [SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation](https://mlsanity.com/paper/2312.12347/) (2023)
- [Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding](https://mlsanity.com/paper/2510.10682/) (2025)
- [MTT-Bench: Predicting Social Dominance in Mice via Multimodal Large Language Models](https://mlsanity.com/paper/2604.22492/) (2026)

## Abstract (arXiv)

Automated social behaviour analysis of mice has become an increasingly popular research area in behavioural neuroscience. Recently, pose information (i.e., locations of keypoints or skeleton) has been used to interpret social behaviours of mice. Nevertheless, effective encoding and decoding of social interaction information underlying the keypoints of mice has been rarely investigated in the existing methods. In particular, it is challenging to model complex social interactions between mice due to highly deformable body shapes and ambiguous movement patterns. To deal with the interaction modelling problem, we here propose a Cross-Skeleton Interaction Graph Aggregation Network (CS-IGANet) to learn abundant dynamics of freely interacting mice, where a Cross-Skeleton Node-level Interaction module (CS-NLI) is used to model multi-level interactions (i.e., intra-, inter- and cross-skeleton interactions). Furthermore, we design a novel Interaction-Aware Transformer (IAT) to dynamically learn the graph-level representation of social behaviours and update the node-level representation, guided by our proposed interaction-aware self-attention mechanism. Finally, to enhance the representation ability of our model, an auxiliary self-supervised learning task is proposed for measuring the similarity between cross-skeleton nodes. Experimental results on the standard CRMI13-Skeleton and our PDMB-Skeleton datasets show that our proposed model outperforms several other state-of-the-art approaches.