# Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment

arXiv: https://arxiv.org/abs/2407.19675 · HTML: https://mlsanity.com/paper/2407.19675/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 29 Jul 2024.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (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)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels](https://mlsanity.com/paper/2203.03884/) (2022)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2111.12903/) (2021)
- [What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment](https://mlsanity.com/paper/1904.04346/) (2019)
- [Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network](https://mlsanity.com/paper/1904.05547/) (2019)
- [Learning To Score Olympic Events](https://mlsanity.com/paper/1611.05125/) (2016)
- [Uncertainty-aware Score Distribution Learning for Action Quality Assessment](https://mlsanity.com/paper/2006.07665/) (2020)
- [Group-aware Contrastive Regression for Action Quality Assessment](https://mlsanity.com/paper/2108.07797/) (2021)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data](https://mlsanity.com/paper/2108.02934/) (2021)
- [Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection](https://mlsanity.com/paper/2209.01589/) (2022)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [Action Quality Assessment with Temporal Parsing Transformer](https://mlsanity.com/paper/2207.09270/) (2022)
- [Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature](https://mlsanity.com/paper/2303.12332/) (2023)
- [Localization Uncertainty Estimation for Anchor-Free Object Detection](https://mlsanity.com/paper/2006.15607/) (2020)
- [Multi-Stage Contrastive Regression for Action Quality Assessment](https://mlsanity.com/paper/2401.02841/) (2024)

## Built on by (most cited first, 8 of 8)

- [Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression](https://mlsanity.com/paper/2501.03674/) (2025)
- [A Comprehensive Survey of Action Quality Assessment: Method and Benchmark](https://mlsanity.com/paper/2412.11149/) (2024)
- [Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2512.15153/) (2025)
- [A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions](https://mlsanity.com/paper/2502.02817/) (2025)
- [TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching](https://mlsanity.com/paper/2411.17130/) (2024)
- [Learning Group Interactions and Semantic Intentions for Multi-Object Trajectory Prediction](https://mlsanity.com/paper/2412.15673/) (2024)
- [Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization](https://mlsanity.com/paper/2504.13460/) (2025)
- [Latent Visual Diffusion Reasoning with Monte Carlo Tree Search](https://mlsanity.com/paper/2606.27988/) (2026)

## Abstract (arXiv)

Existing action quality assessment (AQA) methods often require a large number of label annotations for fully supervised learning, which are laborious and expensive. In practice, the labeled data are difficult to obtain because the AQA annotation process requires domain-specific expertise. In this paper, we propose a novel semi-supervised method, which can be utilized for better assessment of the AQA task by exploiting a large amount of unlabeled data and a small portion of labeled data. Differing from the traditional teacher-student network, we propose a teacher-reference-student architecture to learn both unlabeled and labeled data, where the teacher network and the reference network are used to generate pseudo-labels for unlabeled data to supervise the student network. Specifically, the teacher predicts pseudo-labels by capturing high-level features of unlabeled data. The reference network provides adequate supervision of the student network by referring to additional action information. Moreover, we introduce confidence memory to improve the reliability of pseudo-labels by storing the most accurate ever output of the teacher network and reference network. To validate our method, we conduct extensive experiments on three AQA benchmark datasets. Experimental results show that our method achieves significant improvements and outperforms existing semi-supervised AQA methods.