Hidden Conditional Random Fields

By Ariadna Quattoni, Sy Bor Wang, Louis-philippe Morency, Michael Collins, Trevor Darrell. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007

564 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c29f33e3d13a6447ea0ece36cf5add5f5e32fab2

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

In Signal Processing

Citations in the corpus

Multimodal Language Analysis with Recurrent Multistage Fusion (2018, methodology): “…Models (HMMs) (Baum and Petrie, 1966), Conditional Random Fields (CRFs) (Lafferty et al., 2001), and Hidden Conditional Random Fields (HCRFs) (Quattoni et al., 2007) were shown to work well on modeling sequential data from the language (Misawa et al., 2017; Ma and Hovy, 2016; Huang et al.,…”
Efficient Structured Prediction with Latent Variables for General Graphical Models (2012, methodology): “HCRFs (Quattoni et al., 2007) and LSSVMs (Yu & Joachims, 2009) are the most common frameworks employed to deal with latent variable models in structured prediction problems.”
Hidden-Unit Conditional Random Fields (2011, background): “The reader should not confuse hidden-unit CRFs with the " hidden CRF " (Quattoni et al., 2010).”
Memory Fusion Network for Multi-view Sequential Learning (2018, methodology): “Song2012 (⊳): MV-HCRF (Song, Morency, and Davis 2012) is an extension of the HCRF for Multi-view data.”
Beyond Actions: Discriminative Models for Contextual Group Activities (2010, methodology): “Our model is directly inspired by some recent work on learning discriminative models that allow the use of latent variables [1, 6, 15, 19, 25], particularly when the latent variables have complex structures.”
Deep Learning for Semantic Part Segmentation with High-Level Guidance (2015, background): “…(2001); He et al. (2004); (ii) unlike common CRFs, there are also hidden variables h, which results in a Hidden Conditional Random Fields (HCRFs) Quattoni et al. (2007); Murphy (2012); (iii) however, unlike the loopy graphs used in generic HCRFs, the factor graph in this model is bipartite,…”
Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks (2017, methodology): “The CNN-CRFs used in this work are extensions of hidden CRFs introduced in [26, 27].”
Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data (2014, background): “Hidden Markov Model (HMM) [16–18, 8] and Conditional Random Field (CRF) [19–21] are popular models for this approach.”
Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph (2019, methodology): “Conditional Random Fields (CRFs) have been popularly used to model the statistical dependencies among predictions in images [10, 43, 27, 25, 4] and videos [23, 31].”
A discriminatively trained, multiscale, deformable part model (2008, background): “However, unlike a hidden CRF, a latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive training examples.”
Exploring Compositional High Order Pattern Potentials for Structured Output Learning (2013, methodology): “The former strategy is employed by latent structural SVMs [35], while the latter is employed by hidden CRF models [24].”
Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering (2014, background): “The relation to other hierarchical approaches is also beneficial, given the many successful hierarchical approaches in computer vision, from the classifier cascades used for face detection [46], the Part-Based Model and Latent SVMs [12] applied to general object category detection, Conditional Rando”
A review of natural language processing techniques for opinion mining systems (2017, background): “The model is analogous to hidden-state random condition fields [78] where observation nodes represent features of sentences, and the label of each sentence is treated as a latent variable.”
Learning Factorized Multimodal Representations (2018, methodology): “Variants of EF-HCRF: EF-HCRF: (Hidden Conditional Random Field) (Quattoni et al., 2007) uses a HCRF to learn a set of latent variables conditioned on the concatenated input at each time step.”
A conditional random field-based model for joint sequence segmentation and classification (2013, methodology): “Therefore, sequence classification in our model consists in merely computing the class-conditional partition functions Z(x|h), and picking the class ĥ ∈ H which maximizes them.”