• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Tools

Sorted by:
Try your query at:
Semantic Scholar Scholar Academic
Google Bing DBLP
Results 1 - 10 of 278
Next 10 →

Y.: Using web co-occurrence statistics for improving image categorization. arXiv preprint arXiv:1312.5697

by Samy Bengio, Jeff Dean, Dumitru Erhan, Eugene Ie, Quoc Le, Andrew Rabinovich, Jon Shlens, Yoram Singer , 2013
"... Object recognition and localization are important tasks in computer vision. The focus of this work is the incorporation of contextual information in order to im-prove object recognition and localization. For instance, it is natural to expect not to see an elephant to appear in the middle of an ocean ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
of an ocean. We consider a sim-ple approach to encapsulate such common sense knowledge using co-occurrence statistics from web documents. By merely counting the number of times nouns (such as elephants, sharks, oceans, etc.) co-occur in web documents, we obtain a good estimate of expected co-occurrences

Object categorization by learned universal visual dictionary

by J. Winn, A. Criminisi, T. Minka - IN ICCV , 2005
"... This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class models are automatically learned from a set of training images. The method is simple and extremely fast, making it suitable ..."
Abstract - Cited by 302 (8 self) - Add to MetaCart
This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class models are automatically learned from a set of training images. The method is simple and extremely fast, making

Graph Cut based Inference with Co-occurrence Statistics

by Lubor Ladicky, Chris Russell, Pushmeet Kohli, Philip H. S. Torr, Oxford Brookes
"... Abstract. Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily ..."
Abstract - Cited by 100 (13 self) - Add to MetaCart
to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

by Thomas Mensink, Efstratios Gavves, Cees G. M. Snoek
"... In this paper we aim for zero-shot classification, that is visual recognition of an unseen class by using knowl-edge transfer from known classes. Our main contribution is COSTA, which exploits co-occurrences of visual concepts in images for knowledge transfer. These inter-dependencies arise naturall ..."
Abstract - Cited by 5 (0 self) - Add to MetaCart
In this paper we aim for zero-shot classification, that is visual recognition of an unseen class by using knowl-edge transfer from known classes. Our main contribution is COSTA, which exploits co-occurrences of visual concepts in images for knowledge transfer. These inter-dependencies arise

Detection Evolution with Multi-Order Contextual Co-occurrence

by Guang Chen, Yuanyuan Ding, Jing Xiao, Tony X. Han
"... Context has been playing an increasingly important role to improve the object detection performance. In this paper we propose an effective representation, Multi-Order Contextual co-Occurrence (MOCO), to implicitly model the high level context using solely detection responses from a baseline object d ..."
Abstract - Cited by 14 (0 self) - Add to MetaCart
Context has been playing an increasingly important role to improve the object detection performance. In this paper we propose an effective representation, Multi-Order Contextual co-Occurrence (MOCO), to implicitly model the high level context using solely detection responses from a baseline object

Resolving Referential Ambiguity on the Web Using Higher Order Co-occurrences in

by unknown authors
"... Abstract — Retrieving information about famous personalities is a common task among internet users. Finding information from web search engines becomes difficult when those people are referred by other names on the web because information about people in the web pages exist using their alias names. ..."
Abstract - Add to MetaCart
compared to the previous approach we propose a system which extracts aliases by not only considering the first order co-occurrences but also the higher order co-occurrences among the anchor texts for a given name and alias which will help in the expansion of a query for retrieval of relevant results

Random Projections of Residuals as an Alternative to Co-occurrences in Steganalysis

by Vojtěch Holub, Jessica Fridrich, Tomáš Denemark
"... Today, the most reliable detectors of steganography in empirical cover sources, such as digital images coming from a known source, are built using machine-learning by representing images with joint distributions (co-occurrences) of neighboring noise residual samples computed using local pixel predic ..."
Abstract - Add to MetaCart
Today, the most reliable detectors of steganography in empirical cover sources, such as digital images coming from a known source, are built using machine-learning by representing images with joint distributions (co-occurrences) of neighboring noise residual samples computed using local pixel

Tagging and Retrieving Images with Co-Occurrence Models: from Corel to Flickr

by Nikhil Garg, Daniel Gatica-perez
"... This paper presents two models for content-based automatic image annotation and retrieval in web image repositories, based on the co-occurrence of tags and visual features in the images. In particular, we show how additional measures can be taken to address the noisy and limited tagging problems, in ..."
Abstract - Add to MetaCart
This paper presents two models for content-based automatic image annotation and retrieval in web image repositories, based on the co-occurrence of tags and visual features in the images. In particular, we show how additional measures can be taken to address the noisy and limited tagging problems

A Study of Approaches to Hypertext Categorization

by Yiming Yang, Sean Slattery, Rayid Ghani - Journal of Intelligent Information Systems , 2002
"... . Hypertext poses new research challenges for text classification. Hyperlinks, HTML tags, category labels distributed over linked documents, and meta data extracted from related web sites all provide rich information for classifying hypertext documents. How to appropriately represent that informatio ..."
Abstract - Cited by 116 (4 self) - Add to MetaCart
if the classifier is not sufficiently robust in discriminating informative words from noisy ones. It is also evident in our results that extracting meta data (when available) from related web sites can be extremely useful for improving classification accuracy. Finally, the relative performance of the classifiers

Different approaches for extracting information from the co-occurrence matrix

by Loris Nanni, Sheryl Brahnam, Stefano Ghidoni, Emanuele Menegatti, Tonya Barrier - PLOS ONE , 2013
"... In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different stra ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different
Next 10 →
Results 1 - 10 of 278
Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University