Kernel Codebooks for Scene Categorization

Gemert, Jan C. van; Geusebroek, Jan‐Mark; Veenman, Cor J.; Smeulders, A.W.M.

doi:10.1007/978-3-540-88690-7_52

Cited by 447 publications

(307 citation statements)

References 22 publications

Supporting

Mentioning

300

Contrasting

Unclassified

Order By: Relevance

“…Moreover, in K-means clustering the centers are almost exclusively around the denser regions in high dimensional feature space and thus fail to decode other informative regions. For the above mentioned reasons, some other proposed approaches recommend the use of RAdius-Based Clustering (RABC) to generate discrete visual codebook [11,18]. RABC sequentially seeks to detect new clusters by finding local maxima of the density and clustering all data points within a fixed radius r. Thereby, the clusters centroid represents the local maximum density and all clustered points are assigned to the new cluster.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

A generic framework for semantic video indexing based on visual concepts/contexts detection

Elleuch

Ammar

Alimi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

Providing a semantic access to video data requires the development of concept detectors. However, semantic concepts detection is a hard task due to the large intra-class and the small inter-class variability of content. Moreover, semantic concepts co-occur together in various contexts and their occurrence may vary from one to another. Thus, it is interesting to exploit this knowledge in order to achieve satisfactory performances. In this paper we present a generic semantic video indexing scheme, called SVI_REGIMVid. It is based on three levels of analysis. The first level (level1) focuses on low-level processing such as video shot boundary/ key-frame detection, annotation tools, key-points detection and visual features extraction tools. The second level (level2) aims to build the semantic models for supervised learning of concepts/contexts. The third level (level3) enriches the semantic interpretation of concepts/ contexts by exploiting fuzzy knowledge. The obtained experimental results are promising for a semantic concept/context detection process.

show abstract

Section: Related Work and Backgroundmentioning

confidence: 99%

A generic framework for semantic video indexing based on visual concepts/contexts detection

Elleuch

Ammar

Alimi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Spatial pyramids [8] was a major breakthrough in this direction; it incorporates spatial information by computing BoW representations for different image regions at different scales and concatenating these representations and finally uses a pyramid matching kernel [19] for classification. Almost everything in the book -from kernels [4][5][6][7] to sparsity [20] to local codes [6] has been attempted to enhance the power of these low level representations [21].…”

Section: Beyond Bag Of Wordsmentioning

confidence: 99%

“…Over the years, much research has gone into improving the performance of models that employ BoW representations. Non-linear SVMs, specialized kernels of different kinds [4][5][6][7], and spatial pyramids [8] have all contributed to the success of these representations. Most of these approaches tend to increase the overall image representation size.…”

Section: Introductionmentioning

confidence: 99%

Learning Hierarchical Bag of Words Using Naive Bayes Clustering

Chandra

Kumar²,

Jawahar

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. Image analysis tasks such as classification, clustering, detection, and retrieval are only as good as the feature representation of the images they use. Much research in computer vision is focused on finding better or semantically richer image representations. Bag of visual Words (BoW) is a representation that has emerged as an effective one for a variety of computer vision tasks. BoW methods traditionally use low level features. We have devised a strategy to use these low level features to create "higher level" features by making use of the spatial context in images. In this paper, we propose a novel hierarchical feature learning framework that uses a Naive Bayes Clustering algorithm to convert a 2-D symbolic image at one level to a 2-D symbolic image at the next level with richer features. On two popular datasets, Pascal VOC 2007 and Caltech 101, we empirically show that classification accuracy obtained from the hierarchical features computed using our approach is significantly higher than the traditional SIFT based BoW representation of images even though our image representations are more compact.

show abstract

“…The descriptors with reduced dimensionality are clustered with k-means to learn codewords [5]. The soft assignment scheme in [10] is then exploited to generate a histogram for each image as its representation. Finally, the two distance functions are applied to the histograms to build kernels.…”

Section: Pascal Voc2007mentioning

confidence: 99%

ℓ<inf>p</inf> norm multiple kernel Fisher discriminant analysis for object and image categorisation

Yan

Mikolajczyk

Barnard

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

In this paper, we generalise multiple kernel Fisher discriminant analysis (MK-FDA) such that the kernel weights can be regularised with an p norm for any p ≥ 1, in contrast to existing MK-FDA that uses either l1 or l2 norm. We present formulations for both binary and multiclass cases and solve the associated optimisation problems efficiently with semi-infinite programming. We show on three object and image categorisation benchmarks that by learning the intrinsic sparsity of a given set of base kernels using a validation set, the proposed p MK-FDA outperforms its fixed-norm counterparts, and is capable of producing stateof-the-art performance. Moreover, we show that our p MK-FDA outperforms the p multiple kernel support vector machine ( p MK-SVM) which has been recently proposed. Based on this observation and our experience with single kernel FDA and SVM, we argue that the almost century-old FDA is still a strong competitor of the popular SVM.

show abstract

Kernel Codebooks for Scene Categorization

Abstract: You will be contacted as soon as possible.

Cited by 447 publications

References 22 publications

A generic framework for semantic video indexing based on visual concepts/contexts detection

A generic framework for semantic video indexing based on visual concepts/contexts detection

Learning Hierarchical Bag of Words Using Naive Bayes Clustering

ℓ<inf>p</inf> norm multiple kernel Fisher discriminant analysis for object and image categorisation

Contact Info

Product

Resources

About

Kernel Codebooks for Scene Categorization

Abstract: You will be contacted as soon as possible.

Cited by 447 publications

References 22 publications

A generic framework for semantic video indexing based on visual concepts/contexts detection

A generic framework for semantic video indexing based on visual concepts/contexts detection

Learning Hierarchical Bag of Words Using Naive Bayes Clustering

&#x2113;<inf>p</inf> norm multiple kernel Fisher discriminant analysis for object and image categorisation

Contact Info

Product

Resources

About

ℓ<inf>p</inf> norm multiple kernel Fisher discriminant analysis for object and image categorisation