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

CiteSeerX logo

Advanced Search Include Citations

Tools

Sorted by:
Try your query at:
Semantic Scholar Scholar Academic
Google Bing DBLP
Results 1 - 10 of 2,226
Next 10 →

Visual categorization with bags of keypoints

by Gabriella Csurka, Christopher R. Dance, Lixin Fan, Jutta Willamowski, Cédric Bray - In Workshop on Statistical Learning in Computer Vision, ECCV , 2004
"... Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors of im ..."
Abstract - Cited by 1005 (14 self) - Add to MetaCart
Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors

Empowering Visual Categorization With the GPU

by Koen E. A. van de Sande, Theo Gevers, Cees G. M. Snoek , 2011
"... Visual categorization is important to manage large collections of digital images and video, where textual metadata is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe ..."
Abstract - Cited by 22 (7 self) - Add to MetaCart
Visual categorization is important to manage large collections of digital images and video, where textual metadata is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe

Accelerating Visual Categorization with the GPU

by Koen E. A. van de Sande, Theo Gevers, Cees G. M. Snoek , 2010
"... Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a sever ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a

Adapted vocabularies for generic visual categorization

by Florent Perronnin, Christopher Dance, Gabriela Csurka, Marco Bressan - In ECCV , 2006
"... Abstract. Several state-of-the-art Generic Visual Categorization (GVC) systems are built around a vocabulary of visual terms and characterize images with one histogram of visual word counts. We propose a novel and practical approach to GVC based on a universal vocabulary, which describes the content ..."
Abstract - Cited by 108 (5 self) - Add to MetaCart
Abstract. Several state-of-the-art Generic Visual Categorization (GVC) systems are built around a vocabulary of visual terms and characterize images with one histogram of visual word counts. We propose a novel and practical approach to GVC based on a universal vocabulary, which describes

Visual categorization with aerial photographs

by Robert Lloyd, Michael E. Hodgson, Audrey Stokes - Annals of the Association of American Geographers , 2002
"... This article investigates how people process information from aerial photographs to categorize locations. Three cognitive experiments were conducted with human subjects viewing a series of aerial photographs and categorizing the land use for target locations. Reaction time, accuracy, and confidence ..."
Abstract - Cited by 5 (1 self) - Add to MetaCart
were considered as dependent variables related to the success of the categorization process. The first experiment considered two categories of land use, the relative size of the visual field, and two rounds of unsupervised learning. Subjects were more successful categorizing higher-order land

Social negative bootstrapping for visual categorization

by Xirong Li, Cees G. M. Snoek, Marcel Worring, Arnold W. M. Smeulders - In ICMR , 2011
"... To learn classifiers for many visual categories, obtaining labeled training examples in an efficient way is crucial. Since a classifier tends to misclassify negative examples which are visually similar to positive examples, inclusion of such informative negatives should be stressed in the learning p ..."
Abstract - Cited by 10 (7 self) - Add to MetaCart
. On a popular visual categorization benchmark our precision at 20 increases by 34%, compared to baselines trained on randomly sampled negatives. We achieve more accurate visual categorization without the need of manually labeling any negatives.

Visual Categorization with Negative Examples for Free

by Xirong Li, Cees G. M. Snoek
"... Automatic visual categorization is critically dependent on labeled examples for supervised learning. As an alternative to traditional expert labeling, social-tagged multimedia is becoming a novel yet subjective and inaccurate source of learning examples. Different from existing work focusing on coll ..."
Abstract - Cited by 5 (3 self) - Add to MetaCart
Automatic visual categorization is critically dependent on labeled examples for supervised learning. As an alternative to traditional expert labeling, social-tagged multimedia is becoming a novel yet subjective and inaccurate source of learning examples. Different from existing work focusing

Bootstrapping Visual Categorization with Relevant Negatives

by Xirong Li, Cees G. M. Snoek, Senior Member, Marcel Worring, Dennis Koelma
"... Abstract—Learning classifiers for many visual concepts is important for image categorization and retrieval. As a classifier tends to misclassify negative examples which are visually similar to positive ones, inclusion of such misclassified and thus relevant negatives should be stressed during learni ..."
Abstract - Cited by 9 (3 self) - Add to MetaCart
Abstract—Learning classifiers for many visual concepts is important for image categorization and retrieval. As a classifier tends to misclassify negative examples which are visually similar to positive ones, inclusion of such misclassified and thus relevant negatives should be stressed during

Learning and using taxonomies for fast visual categorization

by Gregory Griffin, Pietro Perona - In CVPR
"... The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously Ncat = 104−105 visual categories requires sub-linear classification costs. We explore algorithms for automatically building classific ..."
Abstract - Cited by 56 (3 self) - Add to MetaCart
The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously Ncat = 104−105 visual categories requires sub-linear classification costs. We explore algorithms for automatically building

Comparing compact codebooks for visual categorization

by Jan C. van Gemert, Cees G. M. Snoek , Cor J. Veenman , Arnold W. M. Smeulders, et al. - COMPUTER VISION AND IMAGE UNDERSTANDING 114 (2010) 450–462 , 2010
"... ..."
Abstract - Cited by 23 (7 self) - Add to MetaCart
Abstract not found
Next 10 →
Results 1 - 10 of 2,226
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