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

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations

Near duplicate image detection: min-hash and tf-idf weighting,” in BMVC, (2008)

by O Chum, J Philbin, A Zisserman
Add To MetaCart

Tools

Sorted by:
Results 1 - 10 of 130
Next 10 →

Computer Vision: Algorithms and Applications

by Richard Szeliski , 2010
"... ..."
Abstract - Cited by 252 (2 self) - Add to MetaCart
Abstract not found

Aggregating local descriptors into a compact image representation

by Herve Jegou, Matthijs Douze, Cordelia Schmid, Patrick Perez
"... We address the problem of image search on a very large scale, where three constraints have to be considered jointly: the accuracy of the search, its efficiency, and the memory usage of the representation. We first propose a simple yet efficient way of aggregating local image descriptors into a vecto ..."
Abstract - Cited by 226 (19 self) - Add to MetaCart
We address the problem of image search on a very large scale, where three constraints have to be considered jointly: the accuracy of the search, its efficiency, and the memory usage of the representation. We first propose a simple yet efficient way of aggregating local image descriptors into a vector of limited dimension, which can be viewed as a simplification of the Fisher kernel representation. We then show how to jointly optimize the dimension reduction and the indexing algorithm, so that it best preserves the quality of vector comparison. The evaluation shows that our approach significantly outperforms the state of the art: the search ac-curacy is comparable to the bag-of-features approach for an image representation that fits in 20 bytes. Searching a 10 million image dataset takes about 50ms.

Kernelized locality-sensitive hashing for scalable image search

by Brian Kulis, Kristen Grauman - IEEE International Conference on Computer Vision (ICCV , 2009
"... Fast retrieval methods are critical for large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance functions into a low-dimensional Hamming space where items can be efficiently searched. However, existing methods do not apply ..."
Abstract - Cited by 163 (5 self) - Add to MetaCart
Fast retrieval methods are critical for large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance functions into a low-dimensional Hamming space where items can be efficiently searched. However, existing methods do not apply for high-dimensional kernelized data when the underlying feature embedding for the kernel is unknown. We show how to generalize locality-sensitive hashing to accommodate arbitrary kernel functions, making it possible to preserve the algorithm’s sub-linear time similarity search guarantees for a wide class of useful similarity functions. Since a number of successful image-based kernels have unknown or incomputable embeddings, this is especially valuable for image retrieval tasks. We validate our technique on several large-scale datasets, and show that it enables accurate and fast performance for example-based object classification, feature matching, and content-based retrieval. 1.

Aggregating local image descriptors into compact codes

by Herve Jegou, Florent Perronnin, Matthijs Douze, Jorge Sanchez, Patrick Pérez , Cordelia Schmid , 2011
"... ..."
Abstract - Cited by 127 (14 self) - Add to MetaCart
Abstract not found

Large-scale image retrieval with compressed Fisher vectors

by Florent Perronnin, Yan Liu, Jorge Sánchez, Hervé Poirier - IN: CVPR PERRONNIN F, SÁNCHEZ J, LIU Y (2010B) LARGE-SCALE , 2010
"... The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by ..."
Abstract - Cited by 100 (8 self) - Add to MetaCart
The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by what makes it different from other images. One drawback of the Fisher vector is that it is high-dimensional and, as opposed to the BOV, it is dense. The resulting memory and computational costs do not make Fisher vectors directly amenable to large-scale retrieval. Therefore, we compress Fisher vectors to reduce their memory footprint and speed-up the retrieval. We compare three binarization approaches: a simple approach devised for this representation and two standard compression techniques. We show on two publicly available datasets that compressed Fisher vectors perform very well using as little as a few hundreds of bits per image, and significantly better than a very recent compressed BOV approach.

Geometric min-Hashing: Finding a (Thick) Needle in a Haystack

by Ondrej Chum , Michal Perd’och, Jiri Matas - CVPR 2009 , 2009
"... We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric information is used both to construct repeatable hash keys and to increase th ..."
Abstract - Cited by 93 (1 self) - Add to MetaCart
We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric information is used both to construct repeatable hash keys and to increase the discriminability of the description. Each hash key combines visual appearance (visual words) with semi-local geometric information. Compared with the state-of-the-art min-Hash, the proposed method has both higher recall (probability of collision for hashes on the same object) and lower false positive rates (random collisions). The advantages of Geometric min-Hashing approach are most pronounced in the presence of viewpoint and scale change, significant occlusion or small physical overlap of the viewing fields. We demonstrate the power of the proposed method on small object discovery in a large unordered collection of images and on a large scale image clustering problem.

Fast Realistic Multi-Action Recognition using Mined Dense Spatio-temporal Features

by Andrew Gilbert, John Illingworth, Richard Bowden
"... Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it is not necessarily optimal in terms of class separability and classification. This paper proposes a novel approach that u ..."
Abstract - Cited by 57 (4 self) - Add to MetaCart
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it is not necessarily optimal in terms of class separability and classification. This paper proposes a novel approach that uses very dense corner features that are spatially and temporally grouped in a hierarchical process to produce an overcomplete compound feature set. Frequently reoccurring patterns of features are then found through data mining, designed for use with large data sets. The novel use of the hierarchical classifier allows real time operation while the approach is demonstrated to handle camera motion, scale, human appearance variations, occlusions and background clutter. The performance of classification, outperforms other state-of-the-art action recognition algorithms on the three datasets; KTH, multi-KTH, and realworld movie sequences containing broad actions. Multiple action localisation is performed, though no groundtruth localisation data is required, using only weak supervision of class labels for each training sequence. The realworld movie dataset contain complex realistic actions from movies, the approach outperforms the published accuracy on this dataset and also achieves real time performance. 1.
(Show Context)

Citation Context

...o be the most descriptive for the learnt actions, however, it is possible that the sparsity disregards important discriminatory information. Building on the success of data mining within other fields =-=[20, 6, 2]-=-, we propose to use data mining within the action recognition field to allow a multi stage classifier to be learnt from a large set of simple features. Initially a very localised neighbourhood groupin...

Packing bag-of-features

by Hervé Jégou, Matthijs Douze, Cordelia Schmid - in ICCV , 2009
"... One of the main limitations of image search based on bag-of-features is the memory usage per image. Only a few million images can be handled on a single machine in reasonable response time. In this paper, we first evaluate how the memory usage is reduced by using lossless index compression. We then ..."
Abstract - Cited by 55 (9 self) - Add to MetaCart
One of the main limitations of image search based on bag-of-features is the memory usage per image. Only a few million images can be handled on a single machine in reasonable response time. In this paper, we first evaluate how the memory usage is reduced by using lossless index compression. We then propose an approximate representation of bag-of-features obtained by projecting the corresponding histogram onto a set of pre-defined sparse projection functions, producing several image descriptors. Coupled with a proper indexing structure, an image is represented by a few hundred bytes. A distance expectation criterion is then used to rank the images. Our method is at least one order of magnitude faster than standard bag-of-features while providing excellent search quality. 1.
(Show Context)

Citation Context

... its speed [9, 11], the post-processing based on a global spatial geometric verification [10], the matching distance of descriptors [4] as well as the efficiency and compactness of the representation =-=[1, 2]-=-. The main advantages of the BOF representation are 1) its compactness, i.e., reduced storage requirements and 2) the rapidity of search due to an inverted file system. In detail, instead of storing a...

Image retrieval with geometry-preserving visual phrases

by Yimeng Zhang, Zhaoyin Jia, Tsuhan Chen - in CVPR, 2011
"... The most popular approach to large scale image re-trieval is based on the bag-of-visual-word (BoV) represen-tation of images. The spatial information is usually re-introduced as a post-processing step to re-rank the retrieved images, through a spatial verification like RANSAC. Since the spatial veri ..."
Abstract - Cited by 52 (1 self) - Add to MetaCart
The most popular approach to large scale image re-trieval is based on the bag-of-visual-word (BoV) represen-tation of images. The spatial information is usually re-introduced as a post-processing step to re-rank the retrieved images, through a spatial verification like RANSAC. Since the spatial verification techniques are computationally ex-pensive, they can be applied only to the top images in the initial ranking. In this paper, we propose an approach that can encode more spatial information into BoV representa-tion and that is efficient enough to be applied to large-scale databases. Other works pursuing the same purpose have proposed exploring the word co-occurrences in the neigh-borhood areas. Our approach encodes more spatial in-formation through the geometry-preserving visual phrases (GVP). In addition to co-occurrences, the GVP method also captures the local and long-range spatial layouts of the words. Our GVP based searching algorithm increases little memory usage or computational time compared to the BoV method. Moreover, we show that our approach can also be integrated to the min-hash method to improve its retrieval accuracy. The experiment results on Oxford 5K and Flicker 1M dataset show that our approach outperforms the BoV method even following a RANSAC verification. 1.
(Show Context)

Citation Context

...e popular min-hash method to further improve the efficiency of searching with GVP, because the min-hash method reduces memory usage and increases the search efficiency. The traditional minhash method =-=[4, 6]-=- is based on the BoV model. Our approach increases its retrieval accuracy by adding spatial information without increasing the computational cost. In this line of work, we are related to [3] and [2]. ...

Spherical hashing

by Jae-pil Heo, Youngwoon Lee, Junfeng He, Shih-fu Chang, Sung-eui Yoon - In Proc. IEEE Conf , 2012
"... Many binary code encoding schemes based on hashing have been actively studied recently, since they can provide efficient similarity search, especially nearest neighbor search, and compact data representations suitable for handling large scale image databases in many computer vision problems. Existin ..."
Abstract - Cited by 34 (3 self) - Add to MetaCart
Many binary code encoding schemes based on hashing have been actively studied recently, since they can provide efficient similarity search, especially nearest neighbor search, and compact data representations suitable for handling large scale image databases in many computer vision problems. Existing hashing techniques encode highdimensional data points by using hyperplane-based hashing functions. In this paper we propose a novel hyperspherebased hashing function, spherical hashing, to map more spatially coherent data points into a binary code compared to hyperplane-based hashing functions. Furthermore, we propose a new binary code distance function, spherical Hamming distance, that is tailored to our hyperspherebased binary coding scheme, and design an efficient iterative optimization process to achieve balanced partitioning of data points for each hash function and independence between hashing functions. Our extensive experiments show that our spherical hashing technique significantly outperforms six state-of-the-art hashing techniques based on hyperplanes across various image benchmarks of sizes ranging from one to 75 million of GIST descriptors. The performance gains are consistent and large, up to 100 % improvements. The excellent results confirm the unique merits of the proposed idea in using hyperspheres to encode proximity regions in high-dimensional spaces. Finally, our method is intuitive and easy to implement. 1.
(Show Context)

Citation Context

... chosen independently from the input points. Locality-Sensitive Hashing (LSH) [11] is one of the most widely known techniques in this category. This technique is extended to various hashing functions =-=[3, 1, 13, 2, 20]-=-. Recent research attentions have been shifted to developing data-dependent techniques to consider the distribution of data points and design better hashing functions. Notable examples include spectra...

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