Home > Research > Publications & Outputs > REMOTE

Electronic data

  • AAAI_22_Pose_Estimation

    Accepted author manuscript, 5.48 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

View graph of relations

REMOTE: Reinforced Motion Transformation Network for Semi-supervised 2D Pose Estimation in Videos

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Close
Publication date28/06/2022
Host publicationProceedings of the 36th AAAI Conference on Artificial Intelligence
Place of PublicationPalo Alto, Calif.
PublisherAAAI press
Pages1944-1952
Number of pages9
ISBN (electronic)9781577358763
<mark>Original language</mark>English
Event36th AAAI Conference on Artificial Intelligence - Virtual
Duration: 22/02/20221/03/2022
https://aaai.org/Conferences/AAAI-22/

Conference

Conference36th AAAI Conference on Artificial Intelligence
Period22/02/221/03/22
Internet address

Conference

Conference36th AAAI Conference on Artificial Intelligence
Period22/02/221/03/22
Internet address

Abstract

Existing approaches for 2D pose estimation in videos often require a large number of dense annotations, which are costly and labor intensive to acquire. In this paper, we propose a semi-supervised REinforced MOtion Transformation nEtwork (REMOTE) to leverage a few labeled frames and temporal pose variations in videos, which enables effective learning of 2D pose estimation in sparsely annotated videos. Specifically, we introduce a Motion Transformer (MT) module to perform cross frame reconstruction, aiming to learn motion dynamic knowledge in videos. Besides, a novel reinforcement learning-based Frame Selection Agent (FSA) is designed within our framework, which is able to harness informative frame pairs on the fly to enhance the pose estimator under our cross reconstruction mechanism. We conduct extensive experiments that show the efficacy of our proposed REMOTE framework.