Abstract
Abstract
In the field of human pose estimation, most of the existing methods focus on improving the generalization performance of the model, while ignoring the significant efficiency issues. This leads to an increasing amount of model parameters and needs to take up more and more computing resources, which greatly reduces the practical value of the model. In order to solve this problem, we propose a novel lightweight network structure called Effective and Lightweight Pose Network (ELPN). At the same time, for the sake of alleviating the difficulty of lightweight model training, we propose a Multi-Angle Pose Distillation (MAPD) model training method that can more effectively train particularly small pose network models. In quantitative experiments, our models have excellent performance on two mainstream benchmark datasets: the MPII and the COCO. In qualitative testing, our models can accurately locate the keypoints of complex human movements. These fully demonstrates the efficiency and effectiveness of our methods. Our models have the characteristics of high precision, small size and fast inference speed. It is a cost-effective model with greater practical value.
Subject
General Physics and Astronomy
Reference44 articles.
1. Attention guided unified network for panoptic segmentation;Li;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2019
2. State-aware reidentification feature for multi-target multi-camera tracking;Li,2019
3. Effective active skeleton representation for low latency human action recognition;Cai;IEEE Transactions on Multimedia,2015
4. Attention-based multi-view re-observation fusion network for skeletal action recognition;Fan;IEEE Transactions on Multimedia,2018
5. Let your body speak: Communicative cue extraction on natural interaction using rgbd data;Marcos-Ramiro;IEEE Transactions on Multimedia,2015
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献