Efficient object localization using Convolutional Networks
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 648-656
- https://doi.org/10.1109/cvpr.2015.7298664
Abstract
Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introduce invariance and prevent over-training. These benefits of pooling come at the cost of reduced localization accuracy. We introduce a novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image. This refinement model is jointly trained in cascade with a state-of-the-art ConvNet model [21] to achieve improved accuracy in human joint location estimation. We show that the variance of our detector approaches the variance of human annotations on the FLIC [20] dataset and outperforms all existing approaches on the MPII-human-pose dataset [1].Other Versions
This publication has 15 references indexed in Scilit:
- Strong Appearance and Expressive Spatial Models for Human Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Human Pose Estimation Using Body Parts Dependent Joint RegressorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Articulated Pose Estimation Using Discriminative Armlet ClassifiersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Learning effective human pose estimation from inaccurate annotationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Clustered Pose and Nonlinear Appearance Models for Human Pose EstimationPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Poselets: Body part detectors trained using 3D human pose annotationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Pictorial structures revisited: People detection and articulated pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A discriminatively trained, multiscale, deformable part modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- SIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORKInternational Journal of Pattern Recognition and Artificial Intelligence, 1993