Description
Stacked Hourglass Networks are a type of convolutional neural network for pose estimation. They are based on the successive steps of pooling and upsampling that are done to produce a final set of predictions.
Papers Using This Method
To Perceive or Not to Perceive: Lightweight Stacked Hourglass Network2023-02-09Robust Table Detection and Structure Recognition from Heterogeneous Document Images2022-03-17Deep Point Cloud Reconstruction2021-11-23Stacked Hourglass Network with a Multi-level Attention Mechanism: Where to Look for Intervertebral Disc Labeling2021-08-14VolNet: Estimating Human Body Part Volumes from a Single RGB Image2021-07-05Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network2021-05-09TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases2021-04-19Traffic Camera Calibration via Vehicle Vanishing Point Detection2021-03-21RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder2020-10-29HoughNet: Integrating near and long-range evidence for bottom-up object detection2020-07-053D Pose Detection in Videos: Focusing on Occlusion2020-06-24Single upper limb pose estimation method based on improved stacked hourglass network2020-04-16RGBD-Dog: Predicting Canine Pose from RGBD Sensors2020-04-16SpotNet: Self-Attention Multi-Task Network for Object Detection2020-02-13Multistage Model for Robust Face Alignment Using Deep Neural Networks2020-02-04MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection2020-01-09Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation2019-11-24Single-shot 3D multi-person pose estimation in complex images2019-11-08Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition2019-10-15Multi-task Localization and Segmentation for X-ray Guided Planning in Knee Surgery2019-07-24