[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1109/CVPR.2013.471guideproceedingsArticle/Chapter ViewAbstractPublication PagesConference Proceedingsacm-pubtype
Article

MODEC: Multimodal Decomposable Models for Human Pose Estimation

Published: 23 June 2013 Publication History

Abstract

We propose a multimodal, decomposable model for articulated human pose estimation in monocular images. A typical approach to this problem is to use a linear structured model, which struggles to capture the wide range of appearance present in realistic, unconstrained images. In this paper, we instead propose a model of human pose that explicitly captures a variety of pose modes. Unlike other multimodal models, our approach includes both global and local pose cues and uses a convex objective and joint training for mode selection and pose estimation. We also employ a cascaded mode selection step which controls the trade-off between speed and accuracy, yielding a 5x speedup in inference and learning. Our model outperforms state-of-the-art approaches across the accuracy-speed trade-off curve for several pose datasets. This includes our newly-collected dataset of people in movies, FLIC, which contains an order of magnitude more labeled data for training and testing than existing datasets.

Cited By

View all
  • (2024)WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair UsersProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3642555(1-25)Online publication date: 11-May-2024
  • (2024)On Mobile Pose Estimation and Action Recognition Design and ImplementationPattern Recognition and Image Analysis10.1134/S105466182401003634:1(126-136)Online publication date: 1-Mar-2024
  • (2023)Dance with You: The Diversity Controllable Dancer Generation via Diffusion ModelsProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612046(8504-8514)Online publication date: 26-Oct-2023
  • Show More Cited By

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings
CVPR '13: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition
June 2013
3752 pages
ISBN:9780769549897

Publisher

IEEE Computer Society

United States

Publication History

Published: 23 June 2013

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 20 Dec 2024

Other Metrics

Citations

Cited By

View all
  • (2024)WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair UsersProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3642555(1-25)Online publication date: 11-May-2024
  • (2024)On Mobile Pose Estimation and Action Recognition Design and ImplementationPattern Recognition and Image Analysis10.1134/S105466182401003634:1(126-136)Online publication date: 1-Mar-2024
  • (2023)Dance with You: The Diversity Controllable Dancer Generation via Diffusion ModelsProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612046(8504-8514)Online publication date: 26-Oct-2023
  • (2023)Robust vision-based glove pose estimation for both hands in virtual realityVirtual Reality10.1007/s10055-023-00860-627:4(3133-3148)Online publication date: 1-Dec-2023
  • (2022)Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and ModelsACM Computing Surveys10.1145/353338455:6(1-42)Online publication date: 7-Dec-2022
  • (2022)Multimodal In-bed Pose and Shape Estimation under the BlanketsProceedings of the 30th ACM International Conference on Multimedia10.1145/3503161.3548063(2411-2419)Online publication date: 10-Oct-2022
  • (2021)Automatic test suite generation for key-points detection DNNs using many-objective search (experience paper)Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis10.1145/3460319.3464802(91-102)Online publication date: 11-Jul-2021
  • (2021)Multi-human Parsing with a Graph-based Generative Adversarial ModelACM Transactions on Multimedia Computing, Communications, and Applications10.1145/341821717:1(1-21)Online publication date: 16-Apr-2021
  • (2021)A review of deep learning techniques for 2D and 3D human pose estimationImage and Vision Computing10.1016/j.imavis.2021.104282114:COnline publication date: 1-Oct-2021
  • (2020)Learning Joint Structure for Human Pose EstimationACM Transactions on Multimedia Computing, Communications, and Applications10.1145/339230216:3(1-17)Online publication date: 5-Jul-2020
  • Show More Cited By

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media