2021/10/11 by Guillem Brasó, Brasó, Guillem, Nikita Kister +3 · 1 citation
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Artificial intelligence #Center (category theory) #Cluster analysis #Code (set theory) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Context (archaeology) #Detector #Engineering #FOS: Computer and information sciences #Gait Recognition and Analysis #Geography #Human Pose and Action Recognition #Inference #Pattern recognition (psychology) #Pose #Set (abstract data type) #Transformer #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.2110.05132
Accepted to ICCV 2021; reports improved multi-scale results
arxiv created 2021/10/11 · openalex publication_date 2021/10/11 · arxiv updated 2021/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image. Our approach uses a transformer to obtain context-aware embeddings for all detected keypoints and centers and then applies multi-head attention to directly group joints into their corresponding person centers. While most bottom-up methods rely on non-learnable clustering at inference, CenterGroup uses a fully differentiable attention mechanism that we train end-to-end together with our keypoint detector. As a result, our method obtains state-of-the-art performance with up to 2.5x faster inference time than competing bottom-up methods. Our code is available at https://github.com/dvl-tum/center-group .