# Contextual Attention for Hand Detection in the Wild

## TL;DR

This paper introduces Hand-CNN, an advanced convolutional network with a novel attention mechanism for improved hand detection and orientation prediction in unconstrained images, trained on a new large-scale dataset.

## Contribution

The paper proposes a new attention mechanism integrated into MaskRCNN for better hand detection, and provides a large annotated dataset for training and evaluation.

## Key findings

- Hand-CNN outperforms existing methods on multiple datasets.
- The proposed attention module improves detection accuracy.
- Ablation studies confirm the effectiveness of the attention mechanism.

## Abstract

We present Hand-CNN, a novel convolutional network architecture for detecting hand masks and predicting hand orientations in unconstrained images. Hand-CNN extends MaskRCNN with a novel attention mechanism to incorporate contextual cues in the detection process. This attention mechanism can be implemented as an efficient network module that captures non-local dependencies between features. This network module can be inserted at different stages of an object detection network, and the entire detector can be trained end-to-end. We also introduce a large-scale annotated hand dataset containing hands in unconstrained images for training and evaluation. We show that Hand-CNN outperforms existing methods on several datasets, including our hand detection benchmark and the publicly available PASCAL VOC human layout challenge. We also conduct ablation studies on hand detection to show the effectiveness of the proposed contextual attention module.