Pictorial structures revisited: People detection and articulated pose estimation

By Mykhaylo Andriluka, Stefan Roth, Bernt Schiele. 2009

942 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, neutral): “D human pose inference [3, 12, 37, 45, 11, 27, 32, 38, 18].”
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, methodology): “The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
Convolutional Pose Machines (2016, background): “The classical approach to articulated pose estimation is the pictorial structures model [2, 3, 9, 14, 26, 27, 30, 43] in which spatial correlations between parts of the body are expressed as a tree-structured graphical model with kinematic priors that couple connected limbs.”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, background): “Earlier attempts to achieve this were based on richer part detectors [19, 1, 4].”
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation (2014, background): “Subsequently a large number of related models were developed [2, 11, 37, 10].”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Using a skeleton prior inspired by pictorial structures [86], [87], the method begins with a torso point and connects outwards to”
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, background): “The problem of human pose estimation has been intensively studied in the last years, from Pictorial Structures [2, 17, 37] to more recent CNN approaches [34, 25, 38, 20, 41, 54, 5, 51, 52, 36].”
Efficient object localization using Convolutional Networks (2014, methodology): “Following the seminal work of Felzenszwalb et al. [10] on ‘Deformable Part Models’ (DPM) for human-body-pose estimation, many algorithms have been proposed to improve on the DPM archiecture [2, 9, 23, 7].”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, methodology): “We apply Bayes’ rule, use the typical assumption that training images and part proposals are independent given the model parameters [1], assume flat priors for a (no prior preference for the object’s center) and d (no prior preference for part offsets), and independent priors for b and s:”
Articulated Human Detection with Flexible Mixtures of Parts (2013, methodology): “Approaches include conditional random fields [24], margin-based learning [25], and boosted detectors [26], [27], [21].”
Recurrent Human Pose Estimation (2016, methodology): “Inspired by the idea of part-based models [2], [3], we additionally propose body part heatmaps which are constructed by pairs of keypoints.”
Learning Human Pose Estimation Features with Convolutional Networks (2013, background): “In a similar spirit, more general techniques using pictorial structures [2, 3, 17, 37, 33, 34], “poselets” [9], and other part-models [16, 50] have received increased attention.”
Strong Appearance and Expressive Spatial Models for Human Pose Estimation (2013, methodology): “We incorporate their ﬁndings and include two modiﬁcations to the standard PS model.”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Pictorial structure models [1,2,3,4,5,6], express the human body as a tree-structured graphical model with kinematic priors that couple connected limbs.”
Multi-task Recurrent Neural Network for Immediacy Prediction (2015, methodology): “Existing works either considered only single person pose estimation [31, 34, 8, 39, 6, 9, 30, 24, 2, 26, 14, 29, 35, 25, 1, 21] or multi-person pose estimation [37, 13], while our model jointly takes 1-person and 2-person pose estimation as the input.”
Detecting People Looking at Each Other in Videos (2013, background): “…work on automatic character identi-ﬁcation (Everingham et al. 2006; Cour et al. 2009; Sivic et al. 2009), human pose estimation (Ferrari et al. 2009; Andriluka et al. 2009; Bourdev et al. 2010; Sapp et al. 2010;Yang et al. 2012), human action recognition (Laptev et al. 2008; Liu et al. 2009;…”
Posebits for Monocular Human Pose Estimation (2014, methodology): “Finally, our work is inspired by work on poselets [5], a new notion of parts, which do not necessarily correspond to intuitive body parts (e.g. as in [1, 27]).”
Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, neutral): “Among classical meth-ods, Pictorial Structures [2] and poselet-based features [31] have been widely used in the past.”
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects (2014, methodology): “Specifically, we use a multi-class random forest trained on dense shape-context descriptors [1].”