| AvgPool | Average Pooling |
| CBAM | Convolutional Block Attention Module |
| COCO | Common Objects in Context |
| Conv | Convolution |
| DSNT | Differentiable Spatial to Numerical Transform |
| IoU | Intersection over Union |
| KL | Kullback Leibler |
| MaxPool | Maximum Pooling |
| MLP | Multi-Layer Perceptron |
| MPJPE | Mean Per Joint Position Error |
| NME | Normalised Mean Error |
| OKS | Object Keypoint Similarity |
| PCK | Percentage of Correct Keypoints |
| PCK@0.20 | Percentage of Correct Keypoints at a Threshold of 0.20 |
| ROI | Region of Interest |
| SL1 | Smooth L1 |
| YOLO | You Only Look Once |