Finding iconic images

@article{Berg2009FindingII,
  title={Finding iconic images},
  author={Tamara L. Berg and Alexander C. Berg},
  journal={2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops},
  year={2009},
  pages={1-8}
}
  • Tamara L. Berg, A. Berg
  • Published 2009
  • Computer Science
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
We demonstrate that is it possible to automatically find representative example images of a specified object category. These canonical examples are perhaps the kind of images that one would show a child to teach them what, for example a horse is - images with a large object clearly separated from the background. Given a large collection of images returned by a web search for an object category, our approach proceeds without any user supplied training data for the category. First images are… Expand
Identifying and learning visual attributes for object recognition
  • K. Wan, S. Roy
  • Computer Science
  • 2010 IEEE International Conference on Image Processing
  • 2010
TLDR
This work proposes an attribute centric approach for visual object recognition, and introduces a novel algorithm that iteratively refines these distributions of patches over the attributes by a nearest-neighbor attribute classifier. Expand
Automatic Ranking of Images on the Web
We propose a new way to automatically find representative images of a specified object category. Given a large collection of images returned by a web search for an object category, our approachExpand
What makes an Image Iconic? A Fine-Grained Case Study
TLDR
An exhaustive list of properties that are intuitively related to iconicity and measure their correlation with these iconicity ratings are considered and a direct iconicity predictor is proposed that approaches human performance. Expand
Visual Discovery of Landmarks and their Details in Large-Scale Image Collections
TLDR
This thesis presents the Hierarchical Iconoid Shift algorithm that, instead of a flat clustering, produces a hierarchy of clusters, where each cluster represents a building sub-structure, and proposes efficient parallel algorithms for performing this mode search. Expand
Learning about Canonical Views from Internet Image Collections
TLDR
Man manually finds the most common view in the results returned by Internet search engines when queried with the objects used in psychophysical experiments and presents strong evidence against the two most prominent formal theories of canonical views and provides novel constraints for new theories. Expand
Automatic Attribute Discovery and Characterization from Noisy Web Data
TLDR
This work focuses on discovering attributes and their visual appearance, and is as agnostic as possible about the textual description, and characterizes attributes according to their visual representation: global or local, and type: color, texture, or shape. Expand
Automatic Evaluation of Iconic Image Retrieval based on Colour, Shape, and Texture
TLDR
A simple probabilistic model is built that assumes that an image is generated from latent intents representing shape, texture, and colour, which enables us to estimate the relevance score of each image and thereby compute graded relevance measures for any image search engine result page. Expand
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs
This paper presents an approach for modeling landmark sites such as the Statue of Liberty based on large-scale contaminated image collections gathered from the Internet. Our system combines 2DExpand
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of sceneExpand
Measuring the Objectness of Image Windows
TLDR
A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, and uses objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
Animals on the Web
  • Tamara L. Berg, D. Forsyth
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
This work demonstrates a method for identifying images containing categories of animals using a clustering method applied to text on web pages and shows unequivocal evidence that visual information improves performance for this task. Expand
Discovering objects and their location in images
TLDR
This work treats object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics, and develops a model developed in the statistical text literature: probabilistic latent semantic analysis (pLSA). Expand
Computing iconic summaries of general visual concepts
  • R. Raguram, S. Lazebnik
  • Computer Science
  • 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2008
TLDR
Results on four large-scale datasets demonstrate the ability of the approach to discover plausible themes and recurring visual motifs for challenging abstract concepts such as ldquoloverdquo and ldQuobeautyrDquo. Expand
Unsupervised discovery of visual object class hierarchies
TLDR
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. Expand
Learning object categories from Google's image search
TLDR
A new model, TSI-pLSA, is developed, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner, and can handle the high intra-class variability and large proportion of unrelated images returned by search engines. Expand
Clustering art
TLDR
This work extends a recently developed method for learning the semantics of image databases using text and pictures and uses WordNet to provide semantic grouping information and to help disambiguate word senses, as well as emphasize the hierarchical nature of semantic relationships. Expand
One-shot learning of object categories
TLDR
It is found that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully. Expand
Scene Summarization for Online Image Collections
TLDR
This work proposes a solution to the problem of scene summarization by examining the distribution of images in the collection to select a set of canonical views to form the scene summary, using clustering techniques on visual features. Expand
Names and faces.
TLDR
By incorporating simple n atural language techniques, this work is able to improve its name assignment significantly and use two mode ls of word context, a naive Bayes model and a maximum entropy model to create an accurately labeled set of faces. Expand
Learning to Detect a Salient Object
  • Tie Liu, Zejian Yuan, +4 authors H. Shum
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
TLDR
A set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, are proposed to describe a salient object locally, regionally, and globally. Expand
...
1
2
3
4
5
...