# Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets

arXiv: https://arxiv.org/abs/2412.09037 · HTML: https://mlsanity.com/paper/2412.09037/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 94 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 7 of 7)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [A Short Note on the Kinetics-700-2020 Human Action Dataset](https://mlsanity.com/paper/2010.10864/) (2020)
- [Exploring Contrastive Learning in Human Activity Recognition for Healthcare](https://mlsanity.com/paper/2011.11542/) (2020)
- [Assessing the State of Self-Supervised Human Activity Recognition using Wearables](https://mlsanity.com/paper/2202.12938/) (2022)
- [Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets](https://mlsanity.com/paper/2211.16878/) (2022)
- [Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition](https://mlsanity.com/paper/2312.02185/) (2023)
- [iMove: Exploring Bio-impedance Sensing for Fitness Activity Recognition](https://mlsanity.com/paper/2402.09445/) (2024)

## Built on by (most cited first, 4 of 4)

- [TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices](https://mlsanity.com/paper/2507.07949/) (2025)
- [FedFitTech: A Baseline in Federated Learning for Fitness Tracking](https://mlsanity.com/paper/2506.16840/) (2025)
- [BabyMamba-HAR: Lightweight Selective State Space Models for Efficient Human Activity Recognition on Resource Constrained Devices](https://mlsanity.com/paper/2602.09872/) (2026)
- [WHAR Arena: Benchmarking the State of the Art in Efficient Wearable Human Activity Recognition](https://mlsanity.com/paper/2606.13194/) (2026)

## Abstract (arXiv)

The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research prioritizes statistical metrics over examining negative sample details. While recent models like transformers have been applied to HAR datasets with limited success from the benchmark metrics, their counterparts have effectively solved problems on similar levels with near 100% accuracy. This raises questions about the limitations of current approaches. This paper aims to address these open questions by conducting a fine-grained inspection of six popular HAR benchmark datasets. We identified for some parts of the data, none of the six chosen state-of-the-art ML methods can correctly classify, denoted as the intersect of false classifications (IFC). Analysis of the IFC reveals several underlying problems, including ambiguous annotations, irregularities during recording execution, and misaligned transition periods. We contribute to the field by quantifying and characterizing annotated data ambiguities, providing a trinary categorization mask for dataset patching, and stressing potential improvements for future data collections.