# Identifying Ethical Biases in Action Recognition Models

arXiv: https://arxiv.org/abs/2604.17971 · HTML: https://mlsanity.com/paper/2604.17971/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 35)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [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)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition](https://mlsanity.com/paper/1912.05534/) (2019)
- [Synthetic Humans for Action Recognition from Unseen Viewpoints](https://mlsanity.com/paper/1912.04070/) (2019)
- [Large-scale Robustness Analysis of Video Action Recognition Models](https://mlsanity.com/paper/2207.01398/) (2022)
- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)
- [SynthCity: A large scale synthetic point cloud](https://mlsanity.com/paper/1907.04758/) (2019)
- [ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly](https://mlsanity.com/paper/2003.01920/) (2020)
- [Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation](https://mlsanity.com/paper/2308.05441/) (2023)
- [Human Action Recognition without Human](https://mlsanity.com/paper/1608.07876/) (2016)
- [Is Appearance Free Action Recognition Possible?](https://mlsanity.com/paper/2207.06261/) (2022)
- [VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models](https://mlsanity.com/paper/2503.07575/) (2025)
- [A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2503.23398/) (2025)
- [IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos](https://mlsanity.com/paper/2007.06317/) (2020)
- [Leveraging Temporal Contextualization for Video Action Recognition](https://mlsanity.com/paper/2404.09490/) (2024)

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

- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)

## Abstract (arXiv)

Human Action Recognition (HAR) models are increasingly deployed in high-stakes environments, yet their fairness across different human appearances has not been analyzed. We introduce a framework for auditing bias in HAR models using synthetic video data, generated with full control over visual identity attributes such as skin color. Unlike prior work that focuses on static images or pose estimation, our approach preserves temporal consistency, allowing us to isolate and test how changes to a single attribute affect model predictions. Through controlled interventions using the BEDLAM simulation platform, we show whether some popular HAR models exhibit statistically significant biases on the skin color even when the motion remains identical. Our results highlight how models may encode unwanted visual associations, and we provide evidence of systematic errors across groups. This work contributes a framework for auditing HAR models and supports the development of more transparent, accountable systems in light of upcoming regulatory standards.