The Representation and Matching of Pictorial Structures

By M. Fischler, R. Elschlager. 1973

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, methodology): “For most of its history, the research in human pose estimation has been heavily based on the idea of part-based models, as pioneered by the Pictorial Structures model of Fischer and Elschlager [16].”
Scalable, High-Quality Object Detection (2014, methodology): “The previous state-of-the-art paradigm in detection is to use part-based models [6, 5] such as Deformable Part Models (DPMs).”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, methodology): “Following previous work on part localization from, e.g. [4,17,19], we experiment with three deﬁnitions of δ : – δ MGi ( x i ) ﬁts a mixture of Gaussians model with N g components to the training data for part p i .”
Determinantal Point Processes for Machine Learning (2012, methodology): “Our factors are given by the standard pictorial structure model [50, 52],”
Covariant Compositional Networks For Learning Graphs (2018, methodology): “At a conceptual level, this is similar to part-based modeling, which has a long history in machine learning (Fischler & Elschlager, 1973; Ohta et al., 1978; Tu et al., 2005; Felzenszwalb & Hutten-locher, 2005; Zhu & Mumford, 2006; Felzenszwalb et al., 2010).”
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”
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations (2014, background): “Most work on pose estimation has been based on graphical model [8, 6, 27, 1, 10, 2, 4].”
Articulated Human Detection with Flexible Mixtures of Parts (2013, methodology): “We describe a general, flexible mixture model that jointly captures spatial relations between part locations and co-occurrence relations between part mixtures, augmenting standard pictorial structure models that encode just spatial relations.”
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].”
Strong Appearance and Expressive Spatial Models for Human Pose Estimation (2013, methodology): “In the following we brieﬂy summarise the basic tree-structured pictorial structures model [11, 13], that will serve as the baseline model for our analysis.”
50 Years of object recognition: Directions forward (2013, methodology): “Within this context, the work by Fischler and Elschlager [107] which was previously discussed, could also be classified as falling within this category since it relies on a parts-based representation of objects.”
Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation (2015, methodology): “Following the pictorial-structure model [19, 1], a variety of part-based methods have been developed for human pose estimation [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15].”
Adaptive pose priors for pictorial structures (2010, methodology): “Part-based models for recognition of articulated objects, proposed nearly forty years ago by Fischler and Elschlager [10], represent an object as a collection of distinctive parts and geometric relationships between them.”
Efficient matching of pictorial structures (2000, methodology): “In this paper we consider the problem of matching pictorial structures to images, as introduced by Fischler and Elschlager [7] nearly 30 years ago.”
Attribute-Based Classification for Zero-Shot Visual Object Categorization (background): “On a higher level of abstraction, pictorial structures [20], the constellation model [21] and recent discriminatively trained deformable part models [22] are examples of the many methods that recognize objects in images by detecting discriminative parts.”
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model (2018, background): “Proir to the recent trend towards deep convolutional networks [4, 5], early successful models for human pose estimation centered around inference mechanisms on part-based graphical models [6, 7], representing a person by a collection of configurable parts.”