Epitomic analysis of appearance and shape

By Nebojsa Jojic, Brendan J. Frey, Anitha Kannan. 2003

264 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, background): “3 - - Toyota Technological Institute at Chicago†, Ecole Centrale Paris‡ George Papandreou†, Iasonas Kokkinos‡(Papandreou, 2014; Papandreou et al., 2014; Jojic et al., 2003; Krizhevsky et al., 2012; Sermanet et al., 2013; Dubout and Fleuret, 2012; Iandola et al., 2014)”
View Synthesis by Appearance Flow (2016, background): “epitomes [32] as a generative model for a set of images.”
Internal statistics of a single natural image (2011, background): “Therefore, compact representations of patches (such as KSVD [1], Epitome [10] etc.”
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance (2018, background): “Despite this challenge several works in the previous decade aimed at learning shape/appearance factorizations in an unsupervised manner, exploring groupwise image alignment, [11,12,13,14].”
Deep Epitomic Convolutional Neural Networks (2014, methodology): “esults o n the MNIST and CIFAR-10 benchmarks with smaller deep epitomic networks trained from scratch on these small-image datasets. Related work Our model builds on the epitomic image representation [12], which was initially gearedtowards image andvideo modelingtasks. Single-leveldictionariesof ima”
Image segmentation evaluation: A survey of unsupervised methods (2008, methodology): “For instance, the image epitome [65] could be used to measure the similarity between regions.”
A Galaxy of Texture Features (2008, background): “(33) Steerable filters (− − −) The concept of steerable filters was first developed by Freeman and Adelson.”
Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection (2015, methodology): “For this we introduce the epitomic image representation [23] into the setting of DCNNs.”
Fields of Experts: a framework for learning image priors (2005, methodology): “[14] use a miniature version of an image or a set of images, called the epitome, to describe an image.”
Summarizing visual data using bidirectional similarity (2008, methodology): “, the windows in the building) by mapping repetitive patches in the source image to a few representative patches in the target image (as in “Epitome” [4, 7]), thus preserving their appearance at the original scale.”
Modeling Image Patches with a Generic Dictionary of Mini-epitomes (2014, unknown): “The epitomic image representation and the related idea of transformation invariant clustering were developed in [13, 15] and also used in [31] for texture modeling, but have not been applied before for learning generic visual dictionaries on large datasets and in the context of visual recognition ta”
Local adaptivity to variable smoothness for exemplar-based image denoising and representation (2005, background): “However, our ambition is not to learn generic image priors from a database of image patches as proposed in [82, 29, 41, 63].”
Location Recognition Using Prioritized Feature Matching (2010, background): “For instance, [16] uses epitomes [17] as compact representations of locations created from videos of different scenes.”
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling (2013, methodology): “They are alternatives to the superpixel or pixel representations used in most CRFs.”
The patch transform and its applications to image editing (2008, background): “Jojic et al. [13] and Kannan et al. [14] have developed " epitomes " and " jigsaws " , where overlapping patches from a smaller source image are used to generate a larger image.”
Discriminative learned dictionaries for local image analysis (2008, unknown): “age representations can be found in [10, 12].”
A Visual Vocabulary for Flower Classification (2006, methodology): “This intra-image grouping has some similarities to the Epitome representation of Jojic et al. [ 8 ], where an image is represented by a set of overlapping patches.”