Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation

By Yuandong Tian, C. Lawrence Zitnick, Srinivasa G. Narasimhan. 2012

151 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Convolutional Pose Machines (2016, background): “Hierarchical models [35, 37] represent the relationships between parts at different scales and sizes in a hierarchical tree structure.”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, methodology): “Richer higher-order spatial relationships were captured in a hierarchical model by Tian et al. [25].”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Recent methods have also explored using part hierarchies [16,17] and condition the detection of smaller parts that model regions around anatomical joints on the localization of larger composite parts or poselets [11,10,18,19] that model limbs in canonical configurations and tend to be easier to dete”
An Efficient Convolutional Network for Human Pose Estimation (2016, background): “Another line of research is based on Hierarchical models [24, 26] that first detect larger parts in the image and then condition the detection of difficult smaller parts on detected larger parts.”
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (2014, background): “This has been addressed by proposing richer structures that aim to resolve the weakness of a tree model by adding additional constraints between the limbs [10], [11], [12], [13] or using a fully connected graphical model [14], [15].”
Multi-source Deep Learning for Human Pose Estimation (2014, methodology): “Despite many years of research [49, 51, 1, 39, 5, 54, 53], pose estimation remains a difficult problem.”
Deep learning for visual understanding: A review (2016, methodology): “One typical part-based approach is pictorial structures [196], which takes advantage of a tree model to capture the geometric relations between adjacent parts and has been developed by various well-known part-based methods [197 – 200].”
Chained Predictions Using Convolutional Neural Networks (2016, background): “cost and has been addressed in various ways: mixture model of parts [17]; mixtures of full body models [18]; higher-order spatial relationships [19]; image dependent pictorial structures [20,21,22,?].”
Multi-task Recurrent Neural Network for Immediacy Prediction (2015, methodology): “Both holistic models [28, 11, 19, 20, 33] and local models [31, 8, 39, 6, 9, 30, 24, 10, 26, 14, 29, 35, 25, 1, 21, 4] were used for estimating the pose of a single person.”
Beyond Physical Connections: Tree Models in Human Pose Estimation (2013, methodology): “As a consequence, latent variables [1] and loopy graphical models [2] were proposed in the past few years for human pose estimation as the remedy of the problems caused by those “oversimplified” tree models.”
Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture (2014, background): “[19] build a hierarchical tree models to examine spatial relationships between body parts.”
Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation (2015, methodology): “In [2], the hierarchical structure is incorporated to model high-order spatial relation among parts.”
Articulated Pose Estimation Using Discriminative Armlet Classifiers (2013, unknown): “Tiang et al. [23] explore a hierarchical model using mixture of parts and intermediate latent nodes to capture spatial relationships among them.”
Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation (2017, background): “Hierarchical models [21], [22] represent the relationships between parts at different scales and sizes in a hierarchical tree structure.”
MODEC: Multimodal Decomposable Models for Human Pose Estimation (2013, background): “A third category of models consider both global, local and intermediate part-granularity level modes [21, 17, 3, 18].”
Human Pose Estimation Using Body Parts Dependent Joint Regressors (2013, methodology): “Besides of independent part templates for body parts, also hierarchies of part templates have been proposed [33, 38, 35].”