Generalized histogram intersection kernel for image recognition

Boughorbel, Sabri; Tarel, Jean-Philippe; Boujemaa, Nozha

doi:10.1109/icip.2005.1530353

Cited by 74 publications

(48 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 3, KCCA had the top performance. Best results were achieved with a chisquare radial basis function kernel 4 for images, a histogram intersection kernel for text [65], [66], and regularization constants ¼ 10% on TVGraz and ¼ 50% on Wikipedia. To verify the importance of modeling correlations, we considered two alternative representations.…”

Section: Correlation Matchingmentioning

confidence: 99%

On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval

Pereira

Coviello

Doyle

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

391

213

View full text Add to dashboard Cite

Abstract-The problem of cross-modal retrieval from multimedia repositories is considered. This problem addresses the design of retrieval systems that support queries across content modalities, for example, using an image to search for texts. A mathematical formulation is proposed, equating the design of cross-modal retrieval systems to that of isomorphic feature spaces for different content modalities. Two hypotheses are then investigated regarding the fundamental attributes of these spaces. The first is that low-level cross-modal correlations should be accounted for. The second is that the space should enable semantic abstraction. Three new solutions to the cross-modal retrieval problem are then derived from these hypotheses: correlation matching (CM), an unsupervised method which models cross-modal correlations, semantic matching (SM), a supervised technique that relies on semantic representation, and semantic correlation matching (SCM), which combines both. An extensive evaluation of retrieval performance is conducted to test the validity of the hypotheses. All approaches are shown successful for text retrieval in response to image queries and vice versa. It is concluded that both hypotheses hold, in a complementary form, although evidence in favor of the abstraction hypothesis is stronger than that for correlation.

show abstract

Section: Correlation Matchingmentioning

confidence: 99%

On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval

Pereira

Coviello

Doyle

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

391

213

View full text Add to dashboard Cite

show abstract

“…1) (Generalized) histogram intersection kernel: The generalized histogram intersection kernel [19] is defined as…”

Section: Non-linear Additive Classifiersmentioning

confidence: 99%

Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Lampert

Blaschko

Hofmann

2009

IEEE Trans. Pattern Anal. Mach. Intell.

317

335

View full text Add to dashboard Cite

Abstract-Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object's location one can take a sliding window approach, but this strongly increases the computational cost, because the classifier or similarity function has to be evaluated over a large set of candidate subwindows.In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in constrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest neighbor classifiers based on the χ 2 -distance. We demonstrate state-ofthe-art localization performance of the resulting systems on the UIUC Cars dataset, the PASCAL VOC 2006 dataset and in the PASCAL VOC 2007 competition.

show abstract

“…We compare only to KLSH [11], since it is the only one dealing with any Mercer kernel. We used a 10K subset of ImageNet-BOF with a Chi Square kernel and Wikipedia-HSV dataset with a Generalized Histogram Intersection kernel (GHI, [1]). Results of Figure 5 confirm that RMMH outperforms KLSH.…”

Section: Kernel Spacesmentioning

confidence: 99%