On the Foundations of Relaxation Labeling Processes

By Robert A. Hummel, Steven W. Zucker. 1983

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

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

In Probabilistic & Bayesian Methods

Citations in the corpus

DeepWalk: online learning of social representations (2014, methodology): “ as an inference in an undirected Markov network, and then use iterative approximate inference algorithms (such as the iterative classication algorithm [31], Gibbs Sampling [14], or label relaxation [18]) to compute the posterior distribution of labels given the network structure. We propose a diere”
Markov Random Field Modeling in Image Analysis (2001, methodology): “The minimal labeling f* is found by using a deterministic relaxation labeling algorithm (Hummel and Zucker 1983).”
Link-Based Classification (2003, background): “The general approach has been studied in numerous fields, including relaxationlabeling in computer vision (Hummel & Zucker, 1983), inference in Markov random fields (Chellappa & Jain, 1993) and loopy belief propagation in Bayesian networks (Murphy & Weiss, 1999).”
Matching 2.5D face scans to 3D models (2006, methodology): “We have formulated the problem into a standard Constraint Satisfaction Problem (CSP) and handled the problem using a relaxation-labeling algorithm [32].”
On the Statistical Analysis of Dirty Pictures (1986, background): “…the formal modelling approach has to be diluted to become workable, I believe that the ideas of the paper are more secure than most of the other relaxation labelling techniques (Hummel and Zucker, 1983) and Professor Besag is to be applauded for leading UK statisticians into this important area.”
Local Modeling of Attributed Graphs: Algorithms and Applications (2016, methodology): “Traditional approaches to relational classification pose the problem as an inference in an undirected Markov network, and then use iterative approximate inference algorithms (such as the iterative classification algorithm [102], Gibbs Sampling [52], or label relaxation [65]) to compute the posterior”
'Online recognition of Chinese characters: the state-of-the-art (2004, background): “It can be formulated as a consistent labeling problem and be solved using heuristic search [95], [135] or relaxation labeling [30], [36].”
Ontology Matching: A Machine Learning Approach (2004, methodology): “Relaxation labeling appears promising for our purposes because it has been applied successfully to similar matching problems in computer vision, natural language processing, and hypertext classification [16, 30, 9].”
Articles: Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis (2009, methodology): “Popescu and Etzioni use an unsupervised clas-siﬁcation technique called relaxation labeling (Hummel and Zucker 1983) to recognize the contextual polarity of words that are at the heads of select opinion phrases.”
Classification in Networked Data: A Toolkit and a Univariate Case Study (2007, unknown): “Two other, closely related, collective inference techniques are (loopy) belief propagation (Pearl, 1988) and relaxation labeling (Rosenfeld et al., 1976; Hummel and Zucker, 1983).”
Robust point matching for nonrigid shapes by preserving local neighborhood structures (2006, methodology): “We can show that our objective function corresponds to the average local consistency measure of the Hummel-Zucker consistency theory [12].”
Localist Attractor Networks (2001, background): “Attractor networks have a long history in neural network research, from relaxation models in vision (Marr & Poggio, 1976; Hummel & Zucker, 1983), to the early work of Hopeld (1982, 1984), to the stochastic Boltzmann machine (Ackley, Hinton, & Sejnowski, 1985; Movellan & McClelland, 1993), to…”
Fast approximate energy minimization via graph cuts (2001, methodology): “Relaxation labeling techniques are actually more general than energy minimization methods, see [ 23 ] and [32].”
Extracting Product Features and Opinions from Reviews (2005, methodology): “OPINE uses a well-known computer vision technique, relaxation labeling (Hummel and Zucker, 1983), in order to solve the three subtasks described above.”