Articulated Pose Estimation Using Hierarchical Exemplar-Based Models
This work addresses pose estimation for articulated objects like humans, which is an incremental improvement over existing methods for semi-rigid objects.
The paper tackles the problem of estimating articulated human poses by proposing a novel formulation that combines hierarchical exemplar-based models with deep convolutional neural networks, achieving state-of-the-art results on benchmarks like the Leeds Sports Dataset and CUB-200-2011.
Exemplar-based models have achieved great success on localizing the parts of semi-rigid objects. However, their efficacy on highly articulated objects such as humans is yet to be explored. Inspired by hierarchical object representation and recent application of Deep Convolutional Neural Networks (DCNNs) on human pose estimation, we propose a novel formulation that incorporates both hierarchical exemplar-based models and DCNNs in the spatial terms. Specifically, we obtain more expressive spatial models by assuming independence between exemplars at different levels in the hierarchy; we also obtain stronger spatial constraints by inferring the spatial relations between parts at the same level. As our method strikes a good balance between expressiveness and strength of spatial models, it is both effective and generalizable, achieving state-of-the-art results on different benchmarks: Leeds Sports Dataset and CUB-200-2011.