# Active Transfer Learning for Efficient Video-Specific Human Pose Estimation

arXiv: https://arxiv.org/abs/2311.05041 · HTML: https://mlsanity.com/paper/2311.05041/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 68 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Graph Embedded Pose Clustering for Anomaly Detection](https://mlsanity.com/paper/1912.11850/) (2019)
- [Diverse mini-batch Active Learning](https://mlsanity.com/paper/1901.05954/) (2019)
- [Sim2real transfer learning for 3D human pose estimation: motion to the rescue](https://mlsanity.com/paper/1907.02499/) (2019)
- [On Statistical Bias In Active Learning: How and When To Fix It](https://mlsanity.com/paper/2101.11665/) (2021)
- [OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association](https://mlsanity.com/paper/2103.02440/) (2021)
- [Detect-and-Track: Efficient Pose Estimation in Videos](https://mlsanity.com/paper/1712.09184/) (2017)
- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Learning Temporal Pose Estimation from Sparsely-Labeled Videos](https://mlsanity.com/paper/1906.04016/) (2019)
- [Test-Time Personalization with a Transformer for Human Pose Estimation](https://mlsanity.com/paper/2107.02133/) (2021)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/2210.11940/) (2022)
- [A Method for Stopping Active Learning Based on Stabilizing Predictions and the Need for User-Adjustable Stopping](https://mlsanity.com/paper/1409.5165/) (2014)
- [Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network](https://mlsanity.com/paper/1806.00746/) (2018)
- [Semantic Segmentation with Active Semi-Supervised Learning](https://mlsanity.com/paper/2203.10730/) (2022)
- [Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification](https://mlsanity.com/paper/1904.02454/) (2019)
- [Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition](https://mlsanity.com/paper/2209.00641/) (2022)
- [DeepAL: Deep Active Learning in Python](https://mlsanity.com/paper/2111.15258/) (2021)
- [Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration](https://mlsanity.com/paper/2304.04437/) (2023)
- [Key Frame Proposal Network for Efficient Pose Estimation in Videos](https://mlsanity.com/paper/2007.15217/) (2020)
- [Towards human-level performance on automatic pose estimation of infant spontaneous movements](https://mlsanity.com/paper/2010.05949/) (2020)
- [Transfer Learning for Pose Estimation of Illustrated Characters](https://mlsanity.com/paper/2108.01819/) (2021)

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

- [Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment](https://mlsanity.com/paper/2503.17267/) (2025)
- [StepAL: Step-aware Active Learning for Cataract Surgical Videos](https://mlsanity.com/paper/2507.22059/) (2025)
- [MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction](https://mlsanity.com/paper/2511.15179/) (2025)
- [Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval](https://mlsanity.com/paper/2602.03157/) (2026)

## Abstract (arXiv)

Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To address this issue, we present our approach combining Active Learning (AL) and Transfer Learning (TL) to adapt HP estimators to individual video domains efficiently. For efficient learning, our approach quantifies (i) the estimation uncertainty based on the temporal changes in the estimated heatmaps and (ii) the unnaturalness in the estimated full-body HPs. These quantified criteria are then effectively combined with the state-of-the-art representativeness criterion to select uncertain and diverse samples for efficient HP estimator learning. Furthermore, we reconsider the existing Active Transfer Learning (ATL) method to introduce novel ideas related to the retraining methods and Stopping Criteria (SC). Experimental results demonstrate that our method enhances learning efficiency and outperforms comparative methods. Our code is publicly available at: https://github.com/ImIntheMiddle/VATL4Pose-WACV2024