# Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition

arXiv: https://arxiv.org/abs/2604.21011 · HTML: https://mlsanity.com/paper/2604.21011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (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)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1912.06971/) (2019)
- [iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis](https://mlsanity.com/paper/2107.00285/) (2021)
- [FineAction: A Fine-Grained Video Dataset for Temporal Action Localization](https://mlsanity.com/paper/2105.11107/) (2021)
- [Benchmarking Micro-action Recognition: Dataset, Methods, and Applications](https://mlsanity.com/paper/2403.05234/) (2024)
- [Temporal Interlacing Network](https://mlsanity.com/paper/2001.06499/) (2020)
- [Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification](https://mlsanity.com/paper/2307.10624/) (2023)
- [Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition](https://mlsanity.com/paper/2412.14719/) (2024)
- [TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition](https://mlsanity.com/paper/1703.10667/) (2017)
- [Micro-gesture Online Recognition using Learnable Query Points](https://mlsanity.com/paper/2407.04490/) (2024)
- [MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion](https://mlsanity.com/paper/2507.08344/) (2025)
- [Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition](https://mlsanity.com/paper/2507.21977/) (2025)

## Abstract (arXiv)

Micro-actions are subtle, localized movements lasting 1-3 seconds such as scratching one's head or tapping fingers. Such subtle actions are essential for social communication, ubiquitously used in natural interactions, and thus critical for fine-grained video understanding, yet remain poorly understood by current computer vision systems. We identify a fundamental challenge: micro-actions exhibit diverse spatio-temporal characteristics where some are defined by spatial configurations while others manifest through temporal dynamics. Existing methods that commit to a single spatio-temporal decomposition cannot accommodate this diversity. We propose a dual-path network that processes anatomically-grounded spatial entities through parallel Spatial-Temporal (ST) and Temporal-Spatial (TS) pathways. The ST path captures spatial configurations before modeling temporal dynamics, while the TS path inverts this order to prioritize temporal dynamics. Rather than fixed fusion, we introduce entity-level adaptive routing where each body part learns its optimal processing preference, complemented by Mutual Action Consistency (MAC) loss that enforces cross-path coherence. Extensive experiments demonstrate competitive performance on MA-52 dataset and state-of-the-art results on iMiGUE dataset. Our work reveals that architectural adaptation to the inherent complexity of micro-actions is essential for advancing fine-grained video understanding.