Litcius/Paper detail

TokenPose: Learning Keypoint Tokens for Human Pose Estimation

Yanjie Li, Shoukui Zhang, Zhicheng Wang, Sen Yang, Wankou Yang, Shu‐Tao Xia, Erjin Zhou

20212021 IEEE/CVF International Conference on Computer Vision (ICCV)380 citationsDOI

Abstract

Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints. In this paper, we propose a novel approach based on Token representation for human Pose estimation (TokenPose). In detail, each keypoint is explicitly embedded as a token to simultaneously learn constraint relationships and appearance cues from images. Extensive experiments show that the small and large TokenPose models are on par with state-of-the-art CNN-based counterparts while being more lightweight. Specifically, our TokenPose-S and TokenPose-L achieve 72.5 AP and 75.8 AP on COCO validation dataset respectively, with significant reduction in parameters (↓80.6% ; ↓ 56.8%) and GFLOPs (↓ 75.3%; ↓24.7%). Code is publicly available <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> .

Topics & Concepts

Security tokenPoseConstraint (computer-aided design)Computer scienceRepresentation (politics)FLOPSArtificial intelligenceCode (set theory)Convolutional neural networkReduction (mathematics)Pattern recognition (psychology)Computer visionMathematicsProgramming languagePolitical sciencePoliticsParallel computingGeometryComputer securitySet (abstract data type)LawHuman Pose and Action RecognitionVideo Surveillance and Tracking MethodsHand Gesture Recognition Systems
TokenPose: Learning Keypoint Tokens for Human Pose Estimation | Litcius