Papers › Multi-Context Attention for Human Pose Estimation

Multi-Context Attention for Human Pose Estimation

24 Feb 2017CVPR 2017 7arXiv:1702.07432archive 2025-07-28

Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L. Yuille, Xiaogang Wang

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 the detailed description 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 fields, 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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bearpaw/pose-attention mentioned on GitHubtorch report
wbenbihi/hourglasstensorlfow mentioned on GitHubtfMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation Leeds Sports Poses Multi-Context Attention PCK 92.6% #8 of 18 Archive leaderboard report
Pose Estimation MPII Human Pose Multi-Context Attention PCKh-0.5 91.5 #17 of 46 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections