# Learning Adaptive Node Selection with External Attention for Human Interaction Recognition

arXiv: https://arxiv.org/abs/2507.03936 · HTML: https://mlsanity.com/paper/2507.03936/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 5 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [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)
- [Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1912.06971/) (2019)
- [View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1804.07453/) (2018)
- [Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates](https://mlsanity.com/paper/1706.08276/) (2017)
- [3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition](https://mlsanity.com/paper/2303.14474/) (2023)
- [Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation](https://mlsanity.com/paper/2410.00464/) (2024)
- [IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition](https://mlsanity.com/paper/2207.12100/) (2022)
- [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)
- [Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition](https://mlsanity.com/paper/2307.07469/) (2023)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks](https://mlsanity.com/paper/2301.11495/) (2023)
- [Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition](https://mlsanity.com/paper/2208.06174/) (2022)
- [TASAR: Transfer-based Attack on Skeletal Action Recognition](https://mlsanity.com/paper/2409.02483/) (2024)
- [Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition](https://mlsanity.com/paper/2402.02431/) (2024)
- [Stitch Contrast and Segment_Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos](https://mlsanity.com/paper/2412.14988/) (2024)

## Built on by (most cited first, 1 of 1)

- [De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift](https://mlsanity.com/paper/2609.32454/) (2026)

## Abstract (arXiv)

Most GCN-based methods model interacting individuals as independent graphs, neglecting their inherent inter-dependencies. Although recent approaches utilize predefined interaction adjacency matrices to integrate participants, these matrices fail to adaptively capture the dynamic and context-specific joint interactions across different actions. In this paper, we propose the Active Node Selection with External Attention Network (ASEA), an innovative approach that dynamically captures interaction relationships without predefined assumptions. Our method models each participant individually using a GCN to capture intra-personal relationships, facilitating a detailed representation of their actions. To identify the most relevant nodes for interaction modeling, we introduce the Adaptive Temporal Node Amplitude Calculation (AT-NAC) module, which estimates global node activity by combining spatial motion magnitude with adaptive temporal weighting, thereby highlighting salient motion patterns while reducing irrelevant or redundant information. A learnable threshold, regularized to prevent extreme variations, is defined to selectively identify the most informative nodes for interaction modeling. To capture interactions, we design the External Attention (EA) module to operate on active nodes, effectively modeling the interaction dynamics and semantic relationships between individuals. Extensive evaluations show that our method captures interaction relationships more effectively and flexibly, achieving state-of-the-art performance.