Learning associative Markov networks

By B. Taskar, Vassil Chatalbashev, Daphne Koller. 2004

204 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Determinantal Point Processes for Machine Learning (2012, background): “More recently, certain types of inference in binary MRFs with associative (or submodular) potentials ψ have been shown to be tractable [17, 79, 146].”
Learning human activities and object affordances from RGB-D videos (2012, methodology): “y nodes and 592 object nodes, i.e., 6090 variables). B. Learning. We take a large-margin approach to learning the parameter vector w of Eq. (9) from labeled training examples (x 1;y 1);:::;(x M;y M) (Taskar et al., 2004; Tsochantaridis et al., 2004). Our method optimizes a regularized upper bound on”
Instace-Based AMN Classification for Improved Object Recognition in 2D and 3D Laser Range Data (2007, unknown): “In the following we will briefly describe AMNs.”
Discriminative learning of Markov random fields for segmentation of 3D scan data (2005, methodology): “This approach is slower in practice than the iterated min-cut approach, but has the same performance guarantees [21].”
Structured Prediction via the Extragradient Method (2005, methodology): “We could proceed by making use of Lagrangian duality, which yields a joint convex optimization problem; this is the approach explored in [25, 26].”
Collective Classification in Network Data (2008, methodology): “Over the course of this chapter, we have already discussed a few popular applications, such as document classification [41,44], image segmentation [1] and POS tagging [22].”
Classification in Networked Data: A Toolkit and a Univariate Case Study (2007, unknown): “In associative Markov networks (AMNs, Taskar et al., 2004) autocorrelation of labels is explicitly modeled by extending the generalized Potts model (Potts, 1952) (speciﬁcally, to allow different labels to have different penalties).”
Contextually guided semantic labeling and search for three-dimensional point clouds (2013, methodology): “The model admits efficient approximate inference (Rother et al., 2007), and we show that it can be trained using a maximum-margin approach (Taskar et al., 2004; Tsochantaridis et al., 2004; Finley and Joachims, 2008) that globally minimizes an upper bound on the training loss.”
Kernel-Based Learning of Hierarchical Multilabel Classification Models (2006, methodology): “• Primal methods where the solution above inference problem is integrated to theprimal optimization problem, rather than writing down the exponential-sized constraint set (Taskar et al., 2004).”
Learning structured prediction models: a large margin approach (2005, methodology): “Our framework extends the max-margin formulation for Markov networks (Taskar et al., 2003; Taskar et al., 2004a ) and context free grammars (Taskar et al., 2004b), and is similar to other formulations (Altun et al., 2003; Tsochantaridis et al., 2004).”
Learning CRFs Using Graph Cuts (2008, background): “[16] proposed to rescale the margin to enforce the constraint”
Fast Approximate Energy Minimization with Label Costs (2010, unknown): “The label cost terms are included in energy (� ) linearly and can thus be learned by max-margin methods ( Taskar et al. 2004; Tsochantaridis et al. 2006).”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, background): “Graphical Models for 3D Segmentation: Our framework builds on top of a long line of works combining graphical models( [61, 62, 39, 20, 38]) and highly engineered classiﬁers.”
Structured Learning with Approximate Inference (2007, background): “Given a sequence of input/labeling pairs {(xi, zi)}, suppose that there exists a weight vector w∗ with unit norm and γ > 0 such that, for all i, w∗ · (Φ(xi, zi)−Φ(xi, z)) ≥ γ for all z ∈ Z ′(xi) \ {zi}.”
Learning an interactive segmentation system (2009, unknown): “With the two shortcuts δψ y = ψ(x k,y)−ψ(xk,yk) and ly = ∆(y,y), the margin rescaled objective [25] reads”
Learning to place new objects in a scene (2012, methodology): “Several prior works have successfully applied ILP to solve inference in Conditional Random Fields or Markov networks, e.g., Roth and Yih, 2005; Taskar et al., 2004; Yanover et al., 2006; Globerson and Jaakkola, 2007.”
Contextually Guided Semantic Labeling and Search for 3D Point Clouds (2011, methodology): “The model admits efﬁcient approximate inference (Rother et al., 2007), and we show that it can be trained using a maximum-margin approach (Taskar et al., 2004; Tsochantaridis et al., 2004; Finley and Joachims, 2008) that globally minimizes an upper bound on the training loss.”
Efficient Exact Inference for 3D Indoor Scene Understanding (2012, unknown): “…ˆ y given an image x we need to solve the following inference task: The model parameters w commonly referred to as weights can be obtained with structured prediction learning algorithms such as structured SVMs [27, 28], conditional random ﬁelds [29] or approximate structured prediction [30].”