Low-Complexity Scaler Based On Convolutional Neural Networks For Adaptive Video Streaming

Bottom-up human pose estimation has raised more investigation in recent years, especially 2D keypoints regression. However, the state-of-art DEKR still has some aspects (e.g., speed and accuracy) to be improved. in this paper, we propose a new framework named DEKRv2, which has been enhanced compared to DEKR. When DEKR calculates the offset of each keypoint, it only considers the features of the current keypoint and neglects the constraints between the adjacent keypoints. We adopt a coarse-to-fine feature extraction method to obtain a more accurate feature location of keypoints for this problem. We also find that the multi-branch network in DEKR is very time-consuming because it is serial. We designed a more effective module based on Group Convolution to replace the multi-branches network in DEKR, and it can reduce reasoning time. Experiments on the CrowdPose dataset show that our method achieves superior compared with DEKR in speed or accuracy, respectively. in the single-scale test, our method obtains 66.6 mAP, 0.6 higher than DEKR. The codes and models are available at https://github.com/chaowentao/DEKRv2.