Multi-context Attention for Human Pose Estimation

Citations Over TimeTop 1% of 2017 papers

Abstract

In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate attention maps from features at multiple resolutions with various semantics. The Conditional Random Field (CRF) is utilized to model the correlations among neighboring regions in the attention map. We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on detailed descriptions for different body parts. Hence our model has the ability to focus on different granularity from local salient regions to global semantic consistent spaces. Additionally, we design novel Hourglass Residual Units (HRUs) to increase the receptive field of the network. These units are extensions of residual units with a side branch incorporating filters with larger receptive field, hence features with various scales are learned and combined within the HRUs. The effectiveness of the proposed multi-context attention mechanism and the hourglass residual units is evaluated on two widely used human pose estimation benchmarks. Our approach outperforms all existing methods on both benchmarks over all the body parts. Code has been made publicly available.

Related Papers

• → Mathematical model and worm wheel tooth working surfaces of the ZN-type hourglass worm gear set(2009)37 cited
• → Hourglass Control Methods in Numerical Simulation Code RingForm(2011)
• → Subcycled Hourglass Control for Explicit Time Integration of Dynamic Relaxation Equations(2002)
• Treatment of element distortion for ring rolling process(2011)
• Hourglass Control in Dynamic Explicit Simulation of Cold Ring Rolling Process(2007)