Pictorial Structures for Object Recognition

By Pedro F. Felzenszwalb, Dan Huttenlocher. 2004

2,542 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

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.”
Deformable part models are convolutional neural networks (2014, background): “DPMs update pictorial structure models [8, 11] (which date back to the 1970s) with modern image features and machine learning algorithms.”
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “For OCR and CoNLL, the max oracle consists of the Viterbi algorithm (Viterbi, 1967); for HorseSeg – in graph cut (Boykov & Kolmogorov, 2004), for LSP – in belief propagation on a tree with messages passed by a generalized distance transform (Felzenszwalb & Huttenlocher, 2005).”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, methodology): “The so called Pictorial Strictures (PSs), introduced by Fishler and Elschlager [8], were made tractable and practical by Felzenszwalb and Huttenlocher [6] using the distance transform trick.”
Determinantal Point Processes for Machine Learning (2012, methodology): “Our factors are given by the standard pictorial structure model [50, 52],”
Feature Boosting Network For 3D Pose Estimation (2019, background): “[20] proposed to represent the human body by a collec-”
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations (2014, methodology): “Pictorial Structure: We recover pictorial structure models [6] by only allowing one relationship type (i.”
Articulated Human Detection with Flexible Mixtures of Parts (2013, methodology): “Object detection: In terms of object detection, our work is most similar to pictorial structure models that reason about mixtures of parts [39], [1], [4], [15].”
Reading Text in the Wild with Convolutional Neural Networks (2014, methodology): “These are grouped into words using a pictorial structures framework (Felzenszwalb and Huttenlocher 2005) for a small fixed lexicon.”
Sharing Visual Features for Multiclass and Multiview Object Detection (2007, background): “Recently, it has become popular to detect objects by detecting their parts and checking that they satisfy certain spatial constraints (see, e.g., [12], [ 10 ]).”
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, background): “To handle more complex articulations, size change and rotation of parts were modeled in [21], and mixture of part appearance and articulation types were modeled in [6, 60, 10].”
Improving Generalization via Scalable Neighborhood Component Analysis (2018, background): “Most of the research in this area is focused on designing better invariant category representations (e.g. bag-of-words [45], pictorial models [5]).”
DenseBox: Unifying Landmark Localization with End to End Object Detection (2015, methodology): “Second, object models such as pictorial structure model (PSM) [12] and deformable part-based model (DPM) [11, 46, 43] allow object parts (e.g. head, torso, arms and legs of human) to deform with geometric constraints.”
SIFT Flow: Dense Correspondence across Scenes and Its Applications (2011, neutral): “✦”
Flowing ConvNets for Human Pose Estimation in Videos (2015, methodology): “Traditional methods for pose estimation have often used pictorial structure models [2, 8, 10, 27, 39], which optimise a configuration of parts as a function of local image evidence for a part, and a prior for the relative positions of parts in the human kinematic chain.”
Recurrent Human Pose Estimation (2016, methodology): “many years approaches have used variations on the pictorial structure model [14], [16] of a combination of part detectors and configuration constraints [2], [15], [30], [34], [44].”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “This can be seen as an unsupervised and efficient variant of both deformable part models [18, 19] and graph matching methods [5, 14].”