PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 1, 2019109 citationsOpen Access

Rethinking on Multi-Stage Networks for Human Pose Estimation

WLWenbo LiAl-Farabi Kazakh National UniversityZWZhicheng WangShanghai Power Equipment Research InstituteBYBinyi YinHubei University

Key Points

Key points are not available for this paper at this time.

Abstract

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Li et al. (2019) studied this question.

synapsesocial.com/papers/6a1265398edbaba0bf672bf9https://doi.org/10.48550/arxiv.1901.00148
Ask AI
Helpful
Bookmark
Share
View Full Paper