# Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation

arXiv: https://arxiv.org/abs/1504.07159 · HTML: https://mlsanity.com/paper/1504.07159/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2015.

## Built on by (most cited first, 14 of 14)

- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Low-resolution Human Pose Estimation](https://mlsanity.com/paper/2109.09090/) (2021)
- [An Adversarial Human Pose Estimation Network Injected with Graph Structure](https://mlsanity.com/paper/2103.15534/) (2021)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Animal Behavior Analysis Methods Using Deep Learning: A Survey](https://mlsanity.com/paper/2405.14002/) (2024)
- [ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones](https://mlsanity.com/paper/2108.10515/) (2021)
- [Sparse and Privacy-enhanced Representation for Human Pose Estimation](https://mlsanity.com/paper/2309.09515/) (2023)
- [Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/2303.14888/) (2023)
- [HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation](https://mlsanity.com/paper/2410.22079/) (2024)
- [2D Pre-Training for 3D Pose Estimation](https://mlsanity.com/paper/2604.22830/) (2026)

## Abstract (arXiv)

We propose a new learning-based method for estimating 2D human pose from a single image, using Dual-Source Deep Convolutional Neural Networks (DS-CNN). Recently, many methods have been developed to estimate human pose by using pose priors that are estimated from physiologically inspired graphical models or learned from a holistic perspective. In this paper, we propose to integrate both the local (body) part appearance and the holistic view of each local part for more accurate human pose estimation. Specifically, the proposed DS-CNN takes a set of image patches (category-independent object proposals for training and multi-scale sliding windows for testing) as the input and then learns the appearance of each local part by considering their holistic views in the full body. Using DS-CNN, we achieve both joint detection, which determines whether an image patch contains a body joint, and joint localization, which finds the exact location of the joint in the image patch. Finally, we develop an algorithm to combine these joint detection/localization results from all the image patches for estimating the human pose. The experimental results show the effectiveness of the proposed method by comparing to the state-of-the-art human-pose estimation methods based on pose priors that are estimated from physiologically inspired graphical models or learned from a holistic perspective.