Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision

51 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Compositional Human Pose Regression (2017, methodology): “While they are widely used for 3D pose estimation [54, 30, 28, 43, 24, 42, 33], the performance is not satisfactory.”
Exploiting Temporal Information for 3D Human Pose Estimation (2017, methodology): “7 Rogez et al [9] (MA) – – – – – – – – – – – – – – – 87.”
Learning to Estimate 3D Hand Pose from Single RGB Images (2017, background): “[10] uses transfer learning to infer the 3D body pose directly from images with a single network.”
Deep learning tools for the measurement of animal behavior in neuroscience (2019, background): “Yet currently, the highest accuracy is achieved by using multiple 2D views to reconstruct a 3D estimate (Figure 1b; (20, 35)), but other ways of “lifting" 2D into 3D are being actively explored (20, 36, 37).”
Real-Time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor (2017, methodology): “Network Design The ResNet[2] architecture has been successfully used for full body pose estimation in previous work [6].”
Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach (2017, methodology): “[15], which finetuned 2D pose network [11] with 3D data for information transfer.”
Weakly-supervised Transfer for 3D Human Pose Estimation in the Wild (2017, methodology): “MPI-INF-3DHP [16] is a newly proposed 3D human pose dataset.”