Adaptive pose priors for pictorial structures

By Benjamin Sapp, Christopher T. Jordan, B. Taskar. 2010

155 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].”
Determinantal Point Processes for Machine Learning (2012, methodology): “[126] on similar images; they assign a value to every proposed location and orientation yr of part r.”
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations (2014, methodology): “Conditional Random Fields (CRFs): Our model is also related to the conditional random field literature on data-dependent priors [18, 13, 15, 19].”
Articulated Human Detection with Flexible Mixtures of Parts (2013, methodology): “Past work has explored the use of superpixels [28], contours [26], [29], [30], foreground/ background color models [9], [7], edge-based descriptors [31], [32], and gradient descriptors [27], [33].”
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.”
Cascaded Pyramid Network for Multi-person Pose Estimation (2017, background): “More specifically, the classical works [1, 34, 13, 33, 8, 44, 29, 20] formulate the problem of human keypoints estimation as a tree-structured or graphical model problem and predict keypoint locations based on hand-crafted features.”
Structured Determinantal Point Processes (2010, background): “Full details of the quality terms are provided in [14].”
Human Pose Estimation with Fields of Parts (2014, methodology): “Examples of better appearance models are the local image conditioned features used in [25], the use of mid-level representations via Poselets [14,3,22], or semantic segmentation information to include background evidence [10,31,20,4].”
Classifying Actions and Measuring Action Similarity by Modeling the Mutual Context of Objects and Human Poses (2011, unknown): “…et al., 2006), object bounding boxes obtained from independent object detectors (Felzenszwalb et al., 2010), as well as initial pose estimation results from a pictorial structure model (Sapp et al., 2010) estimated from all training images, regardless of the belongingness of different atomic poses.”
Pose-Sensitive Embedding by Nonlinear NCA Regression (2010, background): “In a similar spirit, more general techniques using pictorial structures [3, 12, 35], “poselets” [6], and other part-models [11] have received increased attention.”
Pose for Action - Action for Pose (2016, background): “Pose estimation in videos can be improved by taking temporal information or motion cues into account [2], [10], [12], [14], [16], [45].”
Human Pose Estimation Using Body Parts Dependent Joint Regressors (2013, methodology): “For instance, several tree models are combined by a boosting procedure in [37], whereas [28] predicts some parameters of the tree model from the image data.”
From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation (2021, background): “One of the most popular early approaches is the pictorial structure [9, 2, 29] which uses a tree structure to model the spatial relationships among body parts.”
Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose (2016, methodology): “The pictorial structure model is introduced in the early stage for detection [30] and extended in [31], [32], [33], [34] which used a geometrybased tree model to represent the body.”