intrigue 发表于 2025-4-1 05:26:12

Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimationistent hypothesis. Previous works either use local deformable models deviating from a certain template, or use a global mixture representation in the pose space. In this paper, we propose a new hierarchical spatial model that can capture an exponential number of poses with a compact mixture represen

Lacunar-Stroke 发表于 2025-4-1 06:10:10

https://doi.org/10.1007/978-3-642-33715-4Markov random fields; activity recognition; machine learning; object detectors; saliency models; algorith
页: 1 2 3 4 5 6 [7]
查看完整版本: Titlebook: Computer Vision – ECCV 2012; 12th European Confer Andrew Fitzgibbon,Svetlana Lazebnik,Cordelia Schmi Conference proceedings 2012 Springer-V