# Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation

arXiv: https://arxiv.org/abs/1604.03334 · HTML: https://mlsanity.com/paper/1604.03334/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2016.

## Built on by (most cited first, 8 of 8)

- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications](https://mlsanity.com/paper/2208.03826/) (2022)
- [Learning to Imitate Object Interactions from Internet Videos](https://mlsanity.com/paper/2211.13225/) (2022)
- [Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements](https://mlsanity.com/paper/2111.00763/) (2021)
- [Efficient Virtual View Selection for 3D Hand Pose Estimation](https://mlsanity.com/paper/2203.15458/) (2022)
- [Modern Augmented Reality: Applications, Trends, and Future Directions](https://mlsanity.com/paper/2202.09450/) (2022)
- [End-to-End 3D Hand Pose Estimation from Stereo Cameras](https://mlsanity.com/paper/2206.01384/) (2022)
- [Are Candidate Models Really Needed for Active Learning?](https://mlsanity.com/paper/2605.14689/) (2026)

## Abstract (arXiv)

Discriminative methods often generate hand poses kinematically implausible, then generative methods are used to correct (or verify) these results in a hybrid method. Estimating 3D hand pose in a hierarchy, where the high-dimensional output space is decomposed into smaller ones, has been shown effective. Existing hierarchical methods mainly focus on the decomposition of the output space while the input space remains almost the same along the hierarchy. In this paper, a hybrid hand pose estimation method is proposed by applying the kinematic hierarchy strategy to the input space (as well as the output space) of the discriminative method by a spatial attention mechanism and to the optimization of the generative method by hierarchical Particle Swarm Optimization (PSO). The spatial attention mechanism integrates cascaded and hierarchical regression into a CNN framework by transforming both the input(and feature space) and the output space, which greatly reduces the viewpoint and articulation variations. Between the levels in the hierarchy, the hierarchical PSO forces the kinematic constraints to the results of the CNNs. The experimental results show that our method significantly outperforms four state-of-the-art methods and three baselines on three public benchmarks.