# Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach

arXiv: https://arxiv.org/abs/2504.07785 · HTML: https://mlsanity.com/paper/2504.07785/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 51 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (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)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Spatiotemporal Contrastive Video Representation Learning](https://mlsanity.com/paper/2008.03800/) (2020)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [TCLR: Temporal Contrastive Learning for Video Representation](https://mlsanity.com/paper/2101.07974/) (2021)
- [SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning](https://mlsanity.com/paper/2301.10921/) (2023)
- [Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning](https://mlsanity.com/paper/1909.01804/) (2019)
- [Dynamic Conceptional Contrastive Learning for Generalized Category Discovery](https://mlsanity.com/paper/2303.17393/) (2023)
- [SVFormer: Semi-supervised Video Transformer for Action Recognition](https://mlsanity.com/paper/2211.13222/) (2022)
- [iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis](https://mlsanity.com/paper/2107.00285/) (2021)
- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [Semi-Supervised Action Recognition with Temporal Contrastive Learning](https://mlsanity.com/paper/2102.02751/) (2021)
- [Benchmarking Micro-action Recognition: Dataset, Methods, and Applications](https://mlsanity.com/paper/2403.05234/) (2024)
- [Survey on Emotional Body Gesture Recognition](https://mlsanity.com/paper/1801.07481/) (2018)

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

- [Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition](https://mlsanity.com/paper/2506.12848/) (2025)

## Abstract (arXiv)

Micro-Action Recognition (MAR) aims to classify subtle human actions in video. However, annotating MAR datasets is particularly challenging due to the subtlety of actions. To this end, we introduce the setting of Semi-Supervised MAR (SSMAR), where only a part of samples are labeled. We first evaluate traditional Semi-Supervised Learning (SSL) methods to SSMAR and find that these methods tend to overfit on inaccurate pseudo-labels, leading to error accumulation and degraded performance. This issue primarily arises from the common practice of directly using the predictions of classifier as pseudo-labels to train the model. To solve this issue, we propose a novel framework, called Asynchronous Pseudo Labeling and Training (APLT), which explicitly separates the pseudo-labeling process from model training. Specifically, we introduce a semi-supervised clustering method during the offline pseudo-labeling phase to generate more accurate pseudo-labels. Moreover, a self-adaptive thresholding strategy is proposed to dynamically filter noisy labels of different classes. We then build a memory-based prototype classifier based on the filtered pseudo-labels, which is fixed and used to guide the subsequent model training phase. By alternating the two pseudo-labeling and model training phases in an asynchronous manner, the model can not only be learned with more accurate pseudo-labels but also avoid the overfitting issue. Experiments on three MAR datasets show that our APLT largely outperforms state-of-the-art SSL methods. For instance, APLT improves accuracy by 14.5% over FixMatch on the MA-12 dataset when using only 50% labeled data. Code will be publicly available.