# Mixture Dense Regression for Object Detection and Human Pose Estimation

arXiv: https://arxiv.org/abs/1912.00821 · HTML: https://mlsanity.com/paper/1912.00821/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2019.

## Built on by (most cited first, 29 of 29)

- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression](https://mlsanity.com/paper/2206.02338/) (2022)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation](https://mlsanity.com/paper/2207.02466/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation](https://mlsanity.com/paper/2109.03622/) (2021)
- [End-to-End Supervised Multilabel Contrastive Learning](https://mlsanity.com/paper/2307.03967/) (2023)
- [Learning Quality-aware Representation for Multi-person Pose Regression](https://mlsanity.com/paper/2201.01087/) (2022)
- [Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15939/) (2024)
- [Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks](https://mlsanity.com/paper/2109.05776/) (2021)
- [Learning Proposals for Practical Energy-Based Regression](https://mlsanity.com/paper/2110.11948/) (2021)
- [BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations](https://mlsanity.com/paper/2112.10716/) (2021)
- [A survey of top-down approaches for human pose estimation](https://mlsanity.com/paper/2202.02656/) (2022)
- [Learning Probabilistic Coordinate Fields for Robust Correspondences](https://mlsanity.com/paper/2306.04231/) (2023)
- [ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification](https://mlsanity.com/paper/2401.01448/) (2024)
- [Bottom-up approaches for multi-person pose estimation and it's applications: A brief review](https://mlsanity.com/paper/2112.11834/) (2021)
- [ECG-Based Electrolyte Prediction: Evaluating Regression and Probabilistic Methods](https://mlsanity.com/paper/2212.13890/) (2022)
- [MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model](https://mlsanity.com/paper/2302.08751/) (2023)
- [Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting](https://mlsanity.com/paper/2302.11078/) (2023)
- [Multimodal Scientific Learning Beyond Diffusions and Flows](https://mlsanity.com/paper/2602.00960/) (2026)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.12247/) (2024)

## Abstract (arXiv)

Mixture models are well-established learning approaches that, in computer vision, have mostly been applied to inverse or ill-defined problems. However, they are general-purpose divide-and-conquer techniques, splitting the input space into relatively homogeneous subsets in a data-driven manner. Not only ill-defined but also well-defined complex problems should benefit from them. To this end, we devise a framework for spatial regression using mixture density networks. We realize the framework for object detection and human pose estimation. For both tasks, a mixture model yields higher accuracy and divides the input space into interpretable modes. For object detection, mixture components focus on object scale, with the distribution of components closely following that of ground truth the object scale. This practically alleviates the need for multi-scale testing, providing a superior speed-accuracy trade-off. For human pose estimation, a mixture model divides the data based on viewpoint and uncertainty -- namely, front and back views, with back view imposing higher uncertainty. We conduct experiments on the MS COCO dataset and do not face any mode collapse.