A Parameter Efficient Human Pose Estimation Method Based on Densely Connected Convolutional Module
A Parameter Efficient Human Pose Estimation Method Based on Densely Connected Convolutional Module is a scholarly work, published in 2018 in ''IEEE Access''. The main subjects of the publication include anomaly detection, convolutional neural network, layer, artificial intelligence, pose, feature extraction, data set, computer science, computation, feature, computational complexity theory, set, Multiple object tracking, pose estimation, 3D pose estimation, pattern recognition, and algorithm. The authors propose a novel densely connected convolutional module (DCCM)-based convolutional neural network for human pose estimation, which can achieve higher parameter efficiency compared to the state-of-the-art works.