Simultaneous image classification and annotation

By Chong Wang, David M. Blei, Li Fei-Fei. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009

622 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7fdf31d5ebdd293b3027e6555e256a936ff5515a

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

How Many Words Is a Picture Worth? Automatic Caption Generation for News Images (2010, methodology): “able models (Blei and Jordan, 2003; Barnard et al., 2002; Wang et al., 2009), and models inspired by information retrieval (Lavrenko et al.”
Topic regression multi-modal Latent Dirichlet Allocation for image annotation (2010, methodology): “For the LabelMe dataset, following the work in [14], we use the 8-category subset which contains 2,687 images from the classes: ‘coast’, ‘forest’, ‘highway’, ‘inside city’, ‘mountain’, ‘open country’, ‘street’, and ‘tall building’.”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, background): “(ii) The other difference is more subtle – existing supervised topic models such as CorrLDA [52], SLDA [50] and derivatives [49] only weakly influence the learned topics.”
Advances in Variational Inference (2017, background): “tion methods which involve inner optimization routines [16], [206], [222] often become prohibitively slow for practical inference tasks.”
Latent Dirichlet Allocation Models for Image Classification (2013, methodology): “Wang et al. [25] applied this generic framework to the task of image classification, where Y takes on discrete responses, by making use of the generalized linear model exponential family relevant to a categorical response.”
A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data (2014, methodology): “As previously mentioned, multimodal data is often modeled using extensions of the basic LDA topic model, such as Corr-LDA [2], Multimodal LDA [5] and MDRF [4].”
Efficient Incremental Learning for Mobile Object Detection (2019, background): “problem is automatic image annotation [17, 4], which is a process that relies on the computer system assigning metadata (e.”
Spectral Methods for Supervised Topic Models (2014, methodology): “Some representative models are supervised LDA (sLDA) [8] that captures a real-valued regression response for each document, multiclass sLDA [21] that learns with discrete classification responses, discriminative LDA (DiscLDA) [14] that incorporates classification response via discriminative linear…”
Automatic Caption Generation for News Images (2013, background): “The literature is littered with various attempts to learn the associations between image features and words using supervised classification [1], [2], instantiations of the noisy-channel model [3], latent variable models [4], [5], [6], and models inspired by information retrieval [7], [8].”
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos (2020, methodology): “Other works use EM [42] to link text and image regions [43].”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, methodology): “, [1], [2], [3], [4]), in this work we propose to represent the joint interpretation of video and text in the form of a parse graph.”
Learning Tags from Unsegmented Videos of Multiple Human Actions (2011, methodology): “, the root of a Bayesian Network [16], or topic conditional classifier [26]).”
Learning Consistent Feature Representation for Cross-Modal Multimedia Retrieval (2015, methodology): “In the computer vision and the multimedia research field, the cross-modal learning and matching have many applications, such as the heterogeneity face recognition [13], [16], [19], [32], image labeling [35], [36], [47], image retrieval [9], [10], [12], [33], attribute based classification tasks [8],”
Integrated visual vocabulary in latent Dirichlet allocation–based scene classification for IKONOS image (2014, neutral): “θd;k 1⁄4 pðz 1⁄4 kÞ XN i1⁄41 φðiÞ k;t; (8)”
RILOD: near real-time incremental learning for object detection at the edge (2019, background): “Automatic Image Annotation: A related research topic to our automatic training dataset construction problem is automatic image annotation [4, 17], which is a process that relies on the computer system assigning metadata (e.”
MedLDA: maximum margin supervised topic models (2012, methodology): “Variational methods were successfully used to approximate the normalization factor (Wang et al., 2009), but they can be computationally expensive as we shall demonstrate in the experimental section.”
Transfer Sparse Coding for Robust Image Representation (2013, methodology): “Then following [19], we uniformly rescale all images to be 256 pixels in length, and extract 128-dimensional dense SIFT (DSIFT) features using the VLFeat open package [18].”
Max-margin Latent Dirichlet Allocation for Image Classification and Annotation (2011, methodology): “The performance measurements of sLDA shown in Table 2 are the published results reported in [20], it is important to remember that they are not directly comparable to other numbers in the tables, since they use different subsets of the datasets.”
Topic Modeling of Multimodal Data: An Autoregressive Approach (2014, methodology): “[9] proposed a supervised LDA formulation to tackle this problem.”