2D Human Pose Estimation: New Benchmark and State of the Art Analysis

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 3686 - 3693
• Main Authors: Andriluka, Mykhaylo, Pishchulin, Leonid, Gehler, Peter, Schiele, Bernt
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Benchmark testing; Benchmarking; Complexity theory; Computer vision; Estimation; Failure; Human; human pose estimation; Joints; Labels; Measurement; Pattern recognition; performance evaluation; Three dimensional; Torso; Training; Trains

Human pose estimation has made significant progress during the last years. However current datasets are limited in their coverage of the overall pose estimation challenges. Still these serve as the common sources to evaluate, train and compare different models on. In this paper we introduce a novel...