Scene categorization using topic model based hierarchical conditional random fields
Vikram Garg,Ehtesham Hassan,Santanu Chaudhury,M. Gopal +3 more
- pp 206-212
Reads0
Chats0
TLDR
A novel hierarchical framework for scene categorization is proposed using Conditional Random Fields in a hierarchical setting for discovering the global context of latent topics extracted by Latent Dirichlet Allocation.Abstract:
We propose a novel hierarchical framework for scene categorization. The scene representation is defined by latent topics extracted by Latent Dirichlet Allocation. The interaction of these topics across scene categories is learned by probabilistic graphical modelling. We use Conditional Random Fields in a hierarchical setting for discovering the global context of these topics. The learned random fields are further used for categorization of a new scene. The experimental results of the proposed framework is presented on standard datasets and on image collection obtained from the internet.read more
Citations
More filters
Journal ArticleDOI
A hierarchical retrieval approach for automatically generating assembly instructions
TL;DR: In this paper , a hierarchical retrieval approach for automatic generation of assembly instructions based on previously used technical instruction cards is proposed, which significantly improves the quality of new assembly instructions and the speed of generation.
References
More filters
Proceedings ArticleDOI
A Bayesian hierarchical model for learning natural scene categories
Li Fei-Fei,Pietro Perona +1 more
TL;DR: This work proposes a novel approach to learn and recognize natural scene categories by representing the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning.
Proceedings ArticleDOI
Simultaneous image classification and annotation
TL;DR: A new probabilistic model for jointly modeling the image, its class label, and its annotations is developed, which derives an approximate inference and estimation algorithms based on variational methods, as well as efficient approximations for classifying and annotating new images.
Proceedings ArticleDOI
Learning hierarchical models of scenes, objects, and parts
TL;DR: Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available and this hierarchical probabilistic model is extended to scenes containing multiple objects.
Proceedings ArticleDOI
Unsupervised discovery of visual object class hierarchies
TL;DR: This work proposes to group visual objects using a multi-layer hierarchy tree that is based on common visual elements by adapting to the visual domain the generative hierarchical latent Dirichlet allocation (hLDA) model previously used for unsupervised discovery of topic hierarchies in text.
Journal ArticleDOI
Learning Conditional Random Fields for Classification of Hyperspectral Images
Ping Zhong,Runsheng Wang +1 more
TL;DR: An efficient local method to train the conditional random field (CRF) and a strategy to combine the independently trained models to obtain final CRF model that is competitive with the most recent results in hyperspectral image classification.
Related Papers (5)
Local–class–shared–topic latent Dirichlet allocation based scene classification
Chao Huang,Wang Luo,Yurui Xie +2 more
Randomized Probabilistic Latent Semantic Analysis for Scene Recognition
Erik Rodner,Joachim Denzler +1 more