Unsupervised cross-dataset adaptation via probabilistic amodal 3D human pose completion

Kundu, JN and Rahul, MV and Patravali, J and Babu, RV (2020) Unsupervised cross-dataset adaptation via probabilistic amodal 3D human pose completion. In: 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, 1 - 5 March 2020, Snowmass Village; United States, pp. 458-467.

PDF wac_458-467_2020.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Despite remarkable success of supervised deep learning models for 3D human pose estimation, performance of such models is mostly limited to constrained laboratory settings. Such models not only exhibit an alarming level of dataset bias, but also fail to operate on unconstrained videos in the presence of external variations such as camera motion, partial body visibility, occlusion, etc. Acknowledging these shortcomings, firstly, we aim to formalize a motion representation learning framework by effectively utilizing both constrained and artificially generated unconstrained video samples for datasets with 3D pose annotation. Without ignoring the inherent uncertainty in pose estimation for the truncated video frames, we devise a novel probabilistic amodal pose completion framework to enable generation of multiple plausible pose-filling outcomes. Secondly, to address dataset bias, the probabilistic amodal framework is reutilized to design novel self-supervised objectives. This not only enables adaptation of the model to target unannotated datasets (wild YouTube videos) but also encourages learning of generic motion representations beyond the available supervised data even in unconstrained scenarios. Such a training regime helps us achieve state-of-the art performance on unsupervised cross-dataset pose estimation, with a significant improvement in partially-visible unconstrained scenarios. © 2020 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	Copyright of this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Computer vision; Deep learning, 3D human pose estimation; Camera motions; Learning frameworks; Learning models; Motion representation; Pose estimation; State-of-the-art performance; Video frame, Learning systems
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	15 Apr 2021 06:32
Last Modified:	15 Apr 2021 06:32
URI:	http://eprints.iisc.ac.in/id/eprint/65622

Actions (login required)

View Item