# 3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition

arXiv: https://arxiv.org/abs/2303.14474 · HTML: https://mlsanity.com/paper/2303.14474/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 87 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [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)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [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)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs](https://mlsanity.com/paper/1803.07294/) (2018)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [CAT: Cross Attention in Vision Transformer](https://mlsanity.com/paper/2106.05786/) (2021)
- [Interpretable 3D Human Action Analysis with Temporal Convolutional Networks](https://mlsanity.com/paper/1704.04516/) (2017)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching](https://mlsanity.com/paper/1911.04131/) (2019)
- [Global Second-order Pooling Convolutional Networks](https://mlsanity.com/paper/1811.12006/) (2018)
- [Self-supervised Video Transformer](https://mlsanity.com/paper/2112.01514/) (2021)

## Built on by (most cited first, 30 of 40)

- [Advancing Video Anomaly Detection: A Concise Review and a New Dataset](https://mlsanity.com/paper/2402.04857/) (2024)
- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [LLMs are Good Action Recognizers](https://mlsanity.com/paper/2404.00532/) (2024)
- [Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition](https://mlsanity.com/paper/2412.14719/) (2024)
- [Just Add π! Pose Induced Video Transformers for Understanding Activities of Daily Living](https://mlsanity.com/paper/2311.18840/) (2023)
- [Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer](https://mlsanity.com/paper/2407.12322/) (2024)
- [Do Language Models Understand Time?](https://mlsanity.com/paper/2412.13845/) (2024)
- [One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching](https://mlsanity.com/paper/2307.07286/) (2023)
- [Flow Dynamics Correction for Action Recognition](https://mlsanity.com/paper/2310.10059/) (2023)
- [Taylor Videos for Action Recognition](https://mlsanity.com/paper/2402.03019/) (2024)
- [InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition](https://mlsanity.com/paper/2310.10547/) (2023)
- [Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections](https://mlsanity.com/paper/2411.14796/) (2024)
- [Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition](https://mlsanity.com/paper/2507.21977/) (2025)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.10745/) (2024)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition](https://mlsanity.com/paper/2411.05692/) (2024)
- [Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition](https://mlsanity.com/paper/2503.14960/) (2025)
- [Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples](https://mlsanity.com/paper/2510.25345/) (2025)
- [DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling](https://mlsanity.com/paper/2501.12086/) (2025)
- [Feature Hallucination for Self-supervised Action Recognition](https://mlsanity.com/paper/2506.20342/) (2025)
- [SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders](https://mlsanity.com/paper/2411.19544/) (2024)
- [Evolving Skeletons: Motion Dynamics in Action Recognition](https://mlsanity.com/paper/2501.02593/) (2025)
- [Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition](https://mlsanity.com/paper/2502.16493/) (2025)
- [Learning Adaptive Node Selection with External Attention for Human Interaction Recognition](https://mlsanity.com/paper/2507.03936/) (2025)
- [Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition](https://mlsanity.com/paper/2512.21064/) (2025)
- [Continual Gesture Learning without Data via Synthetic Feature Sampling](https://mlsanity.com/paper/2408.12629/) (2024)
- [GMFL-Net: A Global Multi-geometric Feature Learning Network for Repetitive Action Counting](https://mlsanity.com/paper/2409.00330/) (2024)
- [Physics Augmented Tuple Transformer for Autism Severity Level Detection](https://mlsanity.com/paper/2409.18438/) (2024)
- [CoCoDiff: Diversifying Skeleton Action Features via Coarse-Fine Text-Co-Guided Latent Diffusion](https://mlsanity.com/paper/2504.21266/) (2025)

## Abstract (arXiv)

Many skeletal action recognition models use GCNs to represent the human body by 3D body joints connected body parts. GCNs aggregate one- or few-hop graph neighbourhoods, and ignore the dependency between not linked body joints. We propose to form hypergraph to model hyper-edges between graph nodes (e.g., third- and fourth-order hyper-edges capture three and four nodes) which help capture higher-order motion patterns of groups of body joints. We split action sequences into temporal blocks, Higher-order Transformer (HoT) produces embeddings of each temporal block based on (i) the body joints, (ii) pairwise links of body joints and (iii) higher-order hyper-edges of skeleton body joints. We combine such HoT embeddings of hyper-edges of orders 1, ..., r by a novel Multi-order Multi-mode Transformer (3Mformer) with two modules whose order can be exchanged to achieve coupled-mode attention on coupled-mode tokens based on 'channel-temporal block', 'order-channel-body joint', 'channel-hyper-edge (any order)' and 'channel-only' pairs. The first module, called Multi-order Pooling (MP), additionally learns weighted aggregation along the hyper-edge mode, whereas the second module, Temporal block Pooling (TP), aggregates along the temporal block mode. Our end-to-end trainable network yields state-of-the-art results compared to GCN-, transformer- and hypergraph-based counterparts.