Signature quadratic form distances for content-based similarity

Beecks, Christian; Uysal, Merih Seran; Seidl, Thomas

doi:10.1145/1631272.1631391

Cited by 43 publications

(28 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Signature Quadratic Form Distance (SQFD) [3,5] is an adaptive distance-based similarity measure for the comparison of feature signatures, generalizing the classic vectorial Quadratic Form Distance (QFD) [12]. It is defined as follows.…”

Section: Signature Quadratic Form Distancementioning

confidence: 99%

“…In general, a feature signature of an image is a set consisting of multiple local image features, where the length of a feature signature is not fixed (to distinguish images of different complexities). However, the comparison of feature signatures requires more sophisticated and computationally expensive adaptive distance measures [4], such as the Earth Mover's Distance (EMD) [28] or the Signature Quadratic Form Distance (SQFD) [3,5]. In this paper, we focus on the latter, as the SQFD shows higher retrieval quality [4], higher stability [2], and lower time complexity compared to the EMD (O(n 2 ) vs. O(n 4 )).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining CPU and GPU architectures for fast similarity search

Kruliš

Skopal

Lokoč

et al. 2012

Distrib Parallel Databases

Self Cite

View full text Add to dashboard Cite

The Signature Quadratic Form Distance on feature signatures represents a flexible distance-based similarity model for effective content-based multimedia retrieval. Although metric indexing approaches are able to speed up query processing by two orders of magnitude, their applicability to large-scale multimedia databases containing billions of images is still a challenging issue. In this paper, we propose a parallel approach that balances the utilization of CPU and many-core GPUs for efficient similarity search with the Signature Quadratic Form Distance. In particular, we show how to process multiple distance computations and other parts of the search procedure in parallel, achieving maximal performance of the combined CPU/GPU system. The experimental evaluation demonstrates that our approach implemented on a common workstation with 2 GPU cards outperforms traditional parallel implementation on a high-end 48-core NUMA server in terms of efficiency almost by an order of magnitude. If we consider also the price of the high-end server that is ten times higher than that of the GPU workstation then, based on price/performance ratio, the GPU-based similarity search beats the CPU-based solution by almost two orders of magnitude. Although proposed for the SQFD, our approach of fast GPU-based simiCommunicated by: Kaushik Chakrabarti.M. Kruliš · T. Skopal ( ) · J. Lokoč

show abstract

Section: Signature Quadratic Form Distancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combining CPU and GPU architectures for fast similarity search

Kruliš

Skopal

Lokoč

et al. 2012

Distrib Parallel Databases

Self Cite

View full text Add to dashboard Cite

show abstract

“…The signature quadratic form distance [1] is a contextfree distance that has proven to be effective in the image retrieval domain. In addition, in this algorithm, we build a feature set composed of normalized local descriptors.…”

Section: Partial Shape Retrieval With Spin Images and Signature Quadrmentioning

confidence: 99%

A benchmark of simulated range images for partial shape retrieval

et al. 2014

View full text Add to dashboard Cite

In this paper, we address the evaluation of algorithms for partial shape retrieval using a large-scale simulated benchmark of partial views which are used as queries. Since the scanning of real objects is a time-consuming task, we create a simulation that generates a set of views from a target model and at different levels of complexity (amount of missing data). In total, our benchmark contains 7,200 partial views. Furthermore, we propose the use of weighted effectiveness measures based on the complexity of a query. With these characteristics, we aim at jointly evaluating the effectiveness, efficiency and robustness of existing algorithms. As a result of our evaluation, we found that a combination of methods provides the best effectiveness, mainly due to the

show abstract

“…If D(V q , V r ) is smaller than a prespecified threshold ζ video , then we assume that V q is a near-duplicate of V r . (5) represents the semantic dissimilarity between two video shots, measured using SQFD [10] [11]:…”

Section: Matching Of Semantic Video Signaturesmentioning

confidence: 99%

Towards a better understanding of model-free semantic concept detection for annotation and near-duplicate video clip detection

Min

Choi

Neve

et al. 2011

2011 18th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

Given the observation that content transformations tend to preserve semantic information, we demonstrated in previous research that model-free semantic concept detection can be successfully leveraged for identifying NDVCs. In this paper, we seek a better understanding of the usefulness of model-free semantic concept detection for both the task of annotation and NDVC detection. In particular, through extensive experiments, we demonstrate that the problem of detecting semantic concepts for the goal of identifying NDVCs is more relaxed than the problem of detecting semantic concepts for annotation purposes: whereas incorrectly detected semantic concepts negatively affect the effectiveness of annotation, they do not negatively affect the effectiveness of NDVC detection, as long as the same incorrect semantic concepts are detected for both the reference and near-duplicate video clips. This observation has practical implications for the design of a video management system that makes use of model-free semantic concept detection for both the purpose of annotation and NDVC detection.

show abstract

Signature quadratic form distances for content-based similarity

Cited by 43 publications

References 9 publications

Combining CPU and GPU architectures for fast similarity search

Combining CPU and GPU architectures for fast similarity search

A benchmark of simulated range images for partial shape retrieval

Towards a better understanding of model-free semantic concept detection for annotation and near-duplicate video clip detection

Contact Info

Product

Resources

About