Modeling annotated data

By David M. Blei, Michael I. Jordan. 2003

1,268 citations recorded by the source corpus.

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

In Computer Vision and Pattern Recognition

In Probabilistic & Bayesian Methods

Citations in the corpus

Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “Multi-modal LDA (mmLDA) and correspondence LDA (cLDA) [2] methods learn the joint distribution of image features and text captions by finding correlations between the two sets of hidden topics.”
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, background): “There has been a lot of work on the multi-label classification problem of associating images with individual words or tags (see, e.g., Blei & Jordan, 2003; Barnard, Duygulu, Forsyth, Freitas, Blei, & Jordan, 2003; Feng & Lapata, 2008; Deschacht & Moens, 2007; Lavrenko, Manmatha, & Jeon, 2004;…”
Beyond CCA: Moment Matching for Multi-View Models (2016, background): “For example, due to the close relation of DCCA and DICA, the former is closely related to the multi-view topic models (see, e.g., Blei & Jordan, 2003).”
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “This task has traditionally been addressed with the help of sophisticated generative models such as Blei and Jordan (2003); Carneiro et al. (2007); Lavrenko et al. (2003).”
Content Driven User Profiling for Comment-Worthy Recommendations of News and Blog Articles (2015, methodology): “Due to this fact, proportion over topics should vary across the segments within an article and CorrLDA [11] fails to capture this aspect.”
Supervised Learning of Semantic Classes for Image Annotation and Retrieval (2007, methodology): “The basic idea underlying the unsupervised learning formulation [3], [4], [12], [13], [15], [21], [31] is to introduce a variable L that encodes hidden states of the world.”
Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey (2017, methodology): “ And they showed that BioLDA can be applied to increase the application of molecular bonding techniques as heat maps. 10 Hamed Jelodar et al. 1 2011 -study Model ears Estimation / ence Methods Domain [70] Corr A 2003 EM A al [75] Model 2004 Sampling A authors, topics [76] T) 2005 Sampling A T) ery [”
Max-margin Latent Dirichlet Allocation for Image Classification and Annotation (2011, background): “Much work [1, 3, 4, 12, 13, 20, 21] in image classification and labeling uses topic models, which are a class of powerful tools originally proposed in text modeling and have gained much popularity in computer vision recently.”
A Statistical Model for General Contextual Object Recognition (2004, background): “Previous work shows that it is reasonable to use such loosely labeled data for problems in vision and image retrieval[1, 4, 13, 11, 2, 7].”
Automatic image annotation and retrieval using cross-media relevance models (2003, background): “Blei and Jordan [3] extended the Latent Dirichlet Allocation (LDA) Model and proposed a Correlation LDA model which relates words and images.”
Automatic Image Annotation Using Auxiliary Text Information (2008, methodology): “LDA represents documents as a mixture of topics and has been previously used to perform document classi-ﬁcation (Blei et al., 2003) and ad-hoc information retrieval (Wei and Croft, 2006) with good results.”
MMALFM (2018, methodology): “In Corr-LDA [7], image is the primary modality and is generated first, and the captionword is then generated based on the topic of an image region, which the word is associated with.”
Topic Models for Image Annotation and Text Illustration (2010, methodology): “annotation as a problem of statistical inference in a graphical model (Barnard et al., 2002; Blei and Jordan, 2003; Wang et al., 2009).”
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval (2016, methodology): “To capture the correlation between images and annotations, Latent Dirichlet Allocation (LDA) [12] has been extended to learn the joint distribution of multi-modal data such as Correspondence LDA (Corr-LDA) [10] and Topic-regression Multi-modal LDA (Tr-mm LDA) [11].”
Multi-Modal Bayesian Embeddings for Learning Social Knowledge Graphs (2015, methodology): “Although Corr-LDA [ Blei and Jordan, 2003 ] and the author-topic model [ Rosen-Zvi et al. , 2004 ] can be used for multi-modal modeling, the topic models use discrete representation for observed variables, and are not able to exploit the continuous semantics of words and authors.”
A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation (2009, methodology): “Table 1:Comparison of precision and recall values for annotation and segmentation with Corr-LDA [6], our model without LSBP (Simp.”
Learning Tags from Unsegmented Videos of Multiple Human Actions (2011, methodology): “In contrast to existing annotation models [4], [26], [16], we therefore learn a full generalized linear model to predict tags (activities) from topics.”
Automatic Caption Generation for News Images (2013, background): “Regions are then described by a standard set of features, including color, texture, and shape, and subsequently treated as continuous vectors (e.g., [5], [42]) or in quantized form (e.g., [3], [22]).”
Topic regression multi-modal Latent Dirichlet Allocation for image annotation (2010, methodology): “In the specific case of statistical topic models applied to the task of image annotation, the seminal work of Blei et al. [2] proposed 2 association models—multi-modal LDA (mmLDA) and correspondence LDA (cLDA)—which extend the basic Latent Dirichlet Allocation (LDA) model to learn the joint distribu”