Results 1  10
of
755
Majorization for CRFs and Latent Likelihoods
"... The partition function plays a key role in probabilistic modeling including conditional random fields, graphical models, and maximum likelihood estimation. To optimize partition functions, this article introduces a quadratic variational upper bound. This inequality facilitates majorization methods: ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
The partition function plays a key role in probabilistic modeling including conditional random fields, graphical models, and maximum likelihood estimation. To optimize partition functions, this article introduces a quadratic variational upper bound. This inequality facilitates majorization methods
Automatic discovery of meaningful object parts with latent CRFs
 In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2010. Bibliography 192
"... Object recognition is challenging due to high intraclass variability caused, e.g., by articulation, viewpoint changes, and partial occlusion. Successful methods need to strike a balance between being flexible enough to model such variation and discriminative enough to detect objects in cluttered, ..."
Abstract

Cited by 23 (0 self)
 Add to MetaCart
tered, real world scenes. Motivated by these challenges we propose a latent conditional random field (CRF) based on a flexible assembly of parts. By modeling part labels as hidden nodes and developing an EM algorithm for learning from class labels alone, this new approach enables the automatic discovery
Exploiting semantic constraints for estimating supersenses with CRFs
 In Proc. SDM 2009. Frank Reichartz, Hannes
, 2009
"... The annotation of words and phrases by ontology concepts is extremely helpful for semantic interpretation. However many ontologies, e.g. WordNet, are too finegrained and even human annotators often have disagreements about the precise word sense. Therefore we use coarsegrained supersenses of WordN ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
Net. We employ conditional random fields (CRFs) to predict these supersenses taking into account the interaction of neigboring words. As the annotation of training data is costly we modify the CRF algorithm to process lumped labels, i.e. a set of possible labels for each training example, one of which
Modeling HighDimensional Humans for Activity Anticipation using Gaussian Process Latent CRFs
"... Abstract—For robots, the ability to model human configurations and temporal dynamics is crucial for the task of anticipating future human activities, yet requires conflicting properties: On one hand, we need a detailed highdimensional description of human configurations to reason about the physica ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
. It assumes that the highdimensional representation is generated from a latent variable corresponding to its lowdimensional representation using a Gaussian process. The generative process not only defines the mapping function between the high and lowdimensional spaces, but also models a distribution
Conditional random people: Tracking humans with crfs and grid filters
 In IEEE Conference on Computer Vision and Pattern Recognition (CVPR
, 2006
"... We describe a statespace tracking approach based on a Conditional Random Field (CRF) model, where the observation potentials are learned from data. We find functions that embed both state and observation into a space where similarity corresponds to L1 distance, and define an observation potential b ..."
Abstract

Cited by 32 (2 self)
 Add to MetaCart
We describe a statespace tracking approach based on a Conditional Random Field (CRF) model, where the observation potentials are learned from data. We find functions that embed both state and observation into a space where similarity corresponds to L1 distance, and define an observation potential based on distance in this space. This potential is extremely fast to compute and in conjunction with a gridfiltering framework can be used to reduce a continuous state estimation problem to a discrete one. We show how a state temporal prior in the gridfilter can be computed in a manner similar to a sparse HMM, resulting in realtime system performance. The resulting system is used for human pose tracking in video sequences. 1
Posterior regularization for structured latent variable models
 Journal of Machine Learning Research
, 2010
"... We present posterior regularization, a probabilistic framework for structured, weakly supervised learning. Our framework efficiently incorporates indirect supervision via constraints on posterior distributions of probabilistic models with latent variables. Posterior regularization separates model co ..."
Abstract

Cited by 135 (8 self)
 Add to MetaCart
We present posterior regularization, a probabilistic framework for structured, weakly supervised learning. Our framework efficiently incorporates indirect supervision via constraints on posterior distributions of probabilistic models with latent variables. Posterior regularization separates model
ContextDependent Pretrained Deep Neural Networks for Large Vocabulary Speech Recognition
 IEEE Transactions on Audio, Speech, and Language Processing
, 2012
"... Abstract—We propose a novel contextdependent (CD) model for large vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pretrained deep neural network hidden Markov model (DNNHMM) hybrid architecture that trains the ..."
Abstract

Cited by 224 (42 self)
 Add to MetaCart
mixture model (GMM)HMMs, with an absolute sentence accuracy improvement of 5.8 % and 9.2 % (or relative error reduction of 16.0 % and 23.2%) over the CDGMMHMMs trained using the minimum phone error rate (MPE) and maximum likelihood (ML) criteria, respectively. Index Terms—Speech recognition, deep
Novel Estimation Methods for Unsupervised Discovery of Latent Structure in Natural Language Text
, 2006
"... This thesis is about estimating probabilistic models to uncover useful hidden structure in data; specifically, we address the problem of discovering syntactic structure in natural language text. We present three new parameter estimation techniques that generalize the standard approach, maximum likel ..."
Abstract

Cited by 38 (11 self)
 Add to MetaCart
likelihood estimation, in different ways. Contrastive estimation maximizes the conditional probability of the observed data given a “neighborhood” of implicit negative examples. Skewed deterministic annealing locally maximizes likelihood using a cautious parameter search strategy that starts with an easier
SemiSupervised Recursive Autoencoders for Predicting Sentiment Distributions
 In EMNLP
, 2011
"... We introduce a novel machine learning framework based on recursive autoencoders for sentencelevel prediction of sentiment label distributions. Our method learns vector space representations for multiword phrases. In sentiment prediction tasks these representations outperform other stateoftheart ..."
Abstract

Cited by 137 (10 self)
 Add to MetaCart
We introduce a novel machine learning framework based on recursive autoencoders for sentencelevel prediction of sentiment label distributions. Our method learns vector space representations for multiword phrases. In sentiment prediction tasks these representations outperform other stateoftheart approaches on commonly used datasets, such as movie reviews, without using any predefined sentiment lexica or polarity shifting rules. We also evaluate the model’s ability to predict sentiment distributions on a new dataset based on confessions from the experience project. The dataset consists of personal user stories annotated with multiple labels which, when aggregated, form a multinomial distribution that captures emotional reactions. Our algorithm can more accurately predict distributions over such labels compared to several competitive baselines. 1
Discriminative Mixtures of Sparse Latent Fields for Risk Management
"... We describe a simple and efficient approach to learning structures of sparse highdimensional latent variable models. Standard algorithms either learn structures of specific predefined forms, or estimate sparse graphs in the data space ignoring the possibility of the latent variables. In contrast, o ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
We describe a simple and efficient approach to learning structures of sparse highdimensional latent variable models. Standard algorithms either learn structures of specific predefined forms, or estimate sparse graphs in the data space ignoring the possibility of the latent variables. In contrast
Results 1  10
of
755