Results 1 - 10
of
100
Aggregating local descriptors into a compact image representation
"... 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.
Iterative quantization: A procrustean approach to learning binary codes
- In Proc. of the IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR
, 2011
"... This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient alternating minimization scheme for finding a rotation of zerocentered data so as to minimize the quantization error of mapping t ..."
Abstract
-
Cited by 157 (6 self)
- Add to MetaCart
This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient alternating minimization scheme for finding a rotation of zerocentered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube. This method, dubbed iterative quantization (ITQ), has connections to multi-class spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). Our experiments show that the resulting binary coding schemes decisively outperform several other state-of-the-art methods. 1.
Distributed Representations of Sentences and Documents
- In NAACL HLT
"... Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the order-ing of the words ..."
Abstract
-
Cited by 93 (1 self)
- Add to MetaCart
(Show Context)
Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the order-ing of the words and they also ignore semantics of the words. For example, “powerful, ” “strong” and “Paris ” are equally distant. In this paper, we propose Paragraph Vector, an unsupervised algo-rithm that learns fixed-length feature representa-tions from variable-length pieces of texts, such as sentences, paragraphs, and documents. Our algo-rithm represents each document by a dense vec-tor which is trained to predict words in the doc-ument. Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models. Empirical results show that Para-graph Vectors outperform bag-of-words models as well as other techniques for text representa-tions. Finally, we achieve new state-of-the-art re-sults on several text classification and sentiment analysis tasks. 1.
A.: Blocks that shout: Distinctive parts for scene classification
, 2013
"... The automatic discovery of distinctive parts for an ob-ject or scene class is challenging since it requires simulta-neously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and effective method to do so. We ad-dress this ..."
Abstract
-
Cited by 52 (1 self)
- Add to MetaCart
(Show Context)
The automatic discovery of distinctive parts for an ob-ject or scene class is challenging since it requires simulta-neously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and effective method to do so. We ad-dress this problem by learning parts incrementally, starting from a single part occurrence with an Exemplar SVM. In this manner, additional part instances are discovered and aligned reliably before being considered as training exam-ples. We also propose entropy-rank curves as a means of evaluating the distinctiveness of parts shareable between categories and use them to select useful parts out of a set of candidates. We apply the new representation to the task of scene cat-egorisation on the MIT Scene 67 benchmark. We show that our method can learn parts which are significantly more in-formative and for a fraction of the cost, compared to previ-ous part-learning methods such as Singh et al. [28]. We also show that a well constructed bag of words or Fisher vector model can substantially outperform the previous state-of-the-art classification performance on this data. 1.
Multi-Scale Orderless Pooling of Deep Convolutional Activation Features
"... Abstract. Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of ..."
Abstract
-
Cited by 32 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN). This scheme extracts CNN activa-tions for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. The resulting MOP-CNN representation can be used as a generic feature for either supervised or unsupervised recognition tasks, from im-age classification to instance-level retrieval; it consistently outperforms global CNN activations without requiring any joint training of prediction layers for a particular target dataset. In absolute terms, it achieves state-of-the-art results on the challenging SUN397 and MIT Indoor Scenes clas-sification datasets, and competitive results on ILSVRC2012/2013 classi-fication and INRIA Holidays retrieval datasets. 1
Mobile Visual Search
- IEEE SIGNAL PROCESSING MAGAZINE, SPECIAL ISSUE ON MOBILE MEDIA SEARCH
"... MOBILE phones have evolved into powerful image and video processing devices, equipped with highresolution cameras, color displays, and hardware-accelerated graphics. They are increasingly also equipped with GPS, and connected to broadband wireless networks. All this enables a new class of applicatio ..."
Abstract
-
Cited by 26 (7 self)
- Add to MetaCart
MOBILE phones have evolved into powerful image and video processing devices, equipped with highresolution cameras, color displays, and hardware-accelerated graphics. They are increasingly also equipped with GPS, and connected to broadband wireless networks. All this enables a new class of applications which use the camera phone to initiate search queries about objects in visual proximity to the user (Fig 1). Such applications can be used, e.g., for identifying products, comparison shopping, finding information about movies, CDs, real estate, print media or artworks. First deployments of such systems include Google Goggles [1], Nokia Point and Find [2], Kooaba [3], Ricoh iCandy [4], [5], [6] and Amazon Snaptell [7]. Mobile image retrieval applications pose a unique set of challenges. What part of the processing should be performed
Local Descriptors encoded by Fisher Vectors for
"... Abstract. This paper proposes a new descriptor for person reidentification building on the recent advances of Fisher Vectors. Specifically, a simple vector of attributes consisting in the pixel coordinates, its intensity as well as the first and second-order derivatives is computed for each pixel of ..."
Abstract
-
Cited by 20 (0 self)
- Add to MetaCart
(Show Context)
Abstract. This paper proposes a new descriptor for person reidentification building on the recent advances of Fisher Vectors. Specifically, a simple vector of attributes consisting in the pixel coordinates, its intensity as well as the first and second-order derivatives is computed for each pixel of the image. These local descriptors are turned into Fisher Vectors before being pooled to produce a global representation of the image. The so-obtained Local Descriptors encoded by Fisher Vector (LDFV) have been validated through experiments on two person re-identification benchmarks (VIPeR and ETHZ), achieving state-of-the-art performance on both datasets. 1 Introduction and related works In recent years, person re-identification in unconstrained conditions have attracted more and more research interest. Person re-identification consists in recognizing an individual through different images (e.g. coming from cameras in a distributed network or from the same camera at different time). The key issue
To aggregate or not to aggregate: Selective match kernels for image search
- ICCV- INTERNATIONAL CONFERENCE ON COMPUTER VISION
, 2013
"... This paper considers a family of metrics to compare images based on their local descriptors. It encompasses the VLAD descriptor and matching techniques such as Hamming Embedding. Making the bridge between these approaches leads us to propose a match kernel that takes the best of existing techniques ..."
Abstract
-
Cited by 20 (7 self)
- Add to MetaCart
(Show Context)
This paper considers a family of metrics to compare images based on their local descriptors. It encompasses the VLAD descriptor and matching techniques such as Hamming Embedding. Making the bridge between these approaches leads us to propose a match kernel that takes the best of existing techniques by combining an aggregation procedure with a selective match kernel. Finally, the representation underpinning this kernel is approximated, providing a large scale image search both precise and scalable, as shown by our experiments on several benchmarks.
Contextual Weighting for Vocabulary Tree based Image Retrieval
"... In this paper we address the problem of image retrieval from millions of database images. We improve the vocabulary tree based approach by introducing contextual weighting of local features in both descriptor and spatial domains. Specifically, we propose to incorporate efficient statistics of neighb ..."
Abstract
-
Cited by 19 (1 self)
- Add to MetaCart
(Show Context)
In this paper we address the problem of image retrieval from millions of database images. We improve the vocabulary tree based approach by introducing contextual weighting of local features in both descriptor and spatial domains. Specifically, we propose to incorporate efficient statistics of neighbor descriptors both on the vocabulary tree and in the image spatial domain into the retrieval. These contextual cues substantially enhance the discriminative power of individual local features with very small computational overhead. We have conducted extensive experiments on benchmark datasets, i.e., theUKbench, Holidays, and our new Mobile dataset, which show that our method reaches state-of-the-art performance with much less computation. Furthermore, the proposed method demonstrates excellent scalability in terms of both retrieval accuracy and efficiency on large-scale experiments using 1.26 million images from the ImageNet database as distractors. 1.
