Efficient object localization using Convolutional Networks

作者：Jonathan Tompson, Ross Goroshin, Arjun Jain, Yann LeCun, Christoph Bregler · 年份：2015 · DOI：10.1109/cvpr.2015.7298664 · 被引用次数：1366 · 研究领域：Human Pose and Action Recognition、Advanced Neural Network Applications、Video Surveillance and Tracking Methods

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].