ConvFormer：通过利用动态多头卷积注意力机制在Transformer模型中减少3D人体姿态估计的参数
ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention
AI总结：
提出ConvFormer卷积Transformer，利用动态多头卷积自注意力机制全面建模时空关节关系，在三个基准数据集上实现SOTA或接近SOTA性能的同时显著减少了模型参数。
摘要：
最近，全Transformer架构已经取代了事实上的卷积架构，用于3D人体姿态估计任务。在本文中，我们提出了ConvFormer，这是一种新颖的卷积Transformer，它利用一种新的动态多头卷积自注意力机制来进行单目3D人体姿态估计。我们设计了一个空间和时间卷积Transformer，以全面建模单帧内的人体关节关系以及整个运动序列中的全局关节关系。此外，我们为时间ConvFormer引入了一种新颖的时间关节轮廓概念，它能立即为局部关节特征邻域融合完整的时间信息。我们在三个常见的基准数据集上定量和定性地验证了我们的方法：Human3.6M、MPI-INF-3DHP和HumanEva。我们进行了大量实验以确定最佳超参数集。这些实验表明，与先前的Transformer模型相比，我们实现了显著的参数减少，同时在所有三个数据集上都达到了最先进（SOTA）或接近SOTA的性能。此外，对于H36M上的Protocol III，我们在GT和CPN检测输入下均达到了SOTA。最后，我们在MPI-INF-3DHP数据集的所有三个指标上以及Protocol II下HumanEva的所有三个受试者上均获得了SOTA。
英文摘要：
Recently, fully-transformer architectures have replaced the defacto convolutional architecture for the 3D human pose estimation task. In this paper we propose \textbf{\textit{ConvFormer}}, a novel convolutional transformer that leverages a new \textbf{\textit{dynamic multi-headed convolutional self-attention}} mechanism for monocular 3D human pose estimation. We designed a spatial and temporal convolutional transformer to comprehensively model human joint relations within individual frames and globally across the motion sequence. Moreover, we introduce a novel notion of \textbf{\textit{temporal joints profile}} for our temporal ConvFormer that fuses complete temporal information immediately for a local neighborhood of joint features. We have quantitatively and qualitatively validated our method on three common benchmark datasets: Human3.6M, MPI-INF-3DHP, and HumanEva. Extensive experiments have been conducted to identify the optimal hyper-parameter set. These experiments demonstrated that we achieved a \textbf{significant parameter reduction relative to prior transformer models} while attaining State-of-the-Art (SOTA) or near SOTA on all three datasets. Additionally, we achieved SOTA for Protocol III on H36M for both GT and CPN detection inputs. Finally, we obtained SOTA on all three metrics for the MPI-INF-3DHP dataset and for all three subjects on HumanEva under Protocol II.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
