Weakly-supervised Transfer for 3D Human Pose Estimation in the Wild

52 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.

End-to-End Recovery of Human Shape and Pose (2017, methodology): “[45], many recent methods estimate 3D joints directly from images in a deep learning framework [33, 43, 44, 51, 52].”
Deep Learning-based Human Pose Estimation: A Survey (2020, background): “Recent works cited in References [242, 271, 308] revealed the poor generalization of models trained with biased datasets by cross-dataset inference.”
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation (2020, background): “, [133], [139], [140], [141] can also be used for offline domain adaptation.”
Imposing Hard Constraints on Deep Networks: Promises and Limitations (2017, background): “They are different from those of [23] but similar in spirit.”
Learning Monocular 3D Human Pose Estimation from Multi-view Images (2018, methodology): “Weak supervision has been explored for pose estimation purposes in [31], which involves complementing fully-annotated data with 2D pose annotations.”
Hand Pose Estimation via Latent 2.5D Heatmap Regression (2018, methodology): “The closest work to ours are the approaches of [29, 30, 56, 58] in that they also perform 2.”