Over the past few years, the vision transformer and its various forms have gained significance in human pose estimation. By treating image patches as tokens, transformers can capture global relationships wisely, estimate the keypoint tokens by leveraging the visual tokens, and recognize the posture of the human body. Nevertheless, global attention is computationally demanding, which poses a challenge for scaling up transformer-based methods to high-resolution features. In this paper, we introduce sparsity in both keypoint token attention and visual token attention to improve human pose estimation. Experimental results on the MPII dataset demonstrate that our model has a higher level of accuracy and proved the feasibility of the method, achieving new state-of-the-art results. The idea can also provide references for other transformer-based models.

翻译：近年来，视觉Transformer及其各种变体在人体姿态估计中日益重要。通过将图像块视为令牌，Transformer能够智能地捕获全局关系，利用视觉令牌估计关键点令牌，并识别人体姿态。然而，全局注意力计算成本高昂，这给基于Transformer的方法扩展到高分辨率特征带来了挑战。本文在关键点令牌注意力和视觉令牌注意力中引入稀疏性，以改进人体姿态估计。在MPII数据集上的实验结果表明，我们的模型具有更高的准确率，验证了该方法的可行性，并取得了新的最优结果。这一思路也可为其他基于Transformer的模型提供参考。