Mediamill: Searching Multimedia Archives Based on Learned Semantics

Abstract-In this paper, we argue to learn dissimilarity for interactive search in content based image retrieval. In literature, dissimilarity is often learned via the feature space by feature selection, feature weighting or by adjusting the parameters of a function of the features. Other than existing techniques, we use feedback to adjust the dissimilarity space independent of feature space. This has the great advantage that it manipulates dissimilarity directly. To create a dissimilarity space, we use the method proposed by Pekalska and Duin, selecting a set of images called prototypes and computing distances to those prototypes for all images in the collection. After the user gives feedback, we apply active learning with a one-class support vector machine to decide the movement of images such that relevant images stay close together while irrelevant ones are pushed away (the work of Guo et al.). The dissimilarity space is then adjusted accordingly. Results on a Corel dataset of 10000 images and a TrecVid collection of 43907 keyframes show that our proposed approach is not only intuitive, it also significantly improves the retrieval performance.Index Terms-Active learning, dissimilarity learning, interactive image search, visualization.

show abstract

“…Finally, we have implemented an interactive search system, based on the proposed methodology (part of the MediaMill search system [29]). Fig.…”

Section: Discussionmentioning

confidence: 99%

Interactive Search by Direct Manipulation of Dissimilarity Space

Nguyen

Worring

Smeulders

2007

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…Object recognition based on local features has proven to be robust to clutter and occlusion. From our experience, the suggested approach seems fairly robust to these effects [16,4,22]. However, a thorough evaluation remains a point of future research.…”

Section: Discussionmentioning

confidence: 99%

“…Although the assumptions underlying our method seem restricted -smoothly varying surfaces, photometrically constraint by a simple reflectance model-, we applied the method successfully a) on a large collection of objects (this paper); b) under different imaging conditions (this paper); c) under severe JPEG compression (this paper); d) in MPEG compressed video retrieval (TRECVID [4,22] top rank performance); e) real-time recognition of over a hundred objects by a Sony Aibo robodog [16]. Achieving these results requires highly robust and discriminative features.…”

Section: Discussionmentioning

confidence: 99%

Compact Object Descriptors from Local Colour Invariant Histograms

Geusebroek

2006

Procedings of the British Machine Vision Conference 2006

View full text Add to dashboard Cite

Much emphasis has recently been placed on the detection and recognition of locally (weak) affine invariant region descriptors for object recognition. In this paper, we take recognition one step further by developing features for non-planar objects. We consider the description of objects with locally smoothly varying surface. For this class of objects, colour invariant histogram matching has proven to be very encouraging. However, matching many local colour cubes is computationally demanding. We propose a compact colour descriptor, which we call Wiccest, requiring only 12 numbers to locally capture colour and texture information. The Wiccest features are shown to be fairly insensitive to photometric effects like shadow, shading, and illumination colour. Moreover, we demonstrate the features to be applicable to highly compressed images while retaining discriminative power.

show abstract

“…Moreover, recent extensions to Parallel-Horus, that allow for services-based multimedia Grid computing, have been applied successfully in large-scale distributed systems, involving hundreds of massively communicating compute resources covering our entire globe [1]. Real-time and off-line applications implemented with this extended system have resulted in a 'best technical demo award' at ACM Multimedia 2005 [11] and a 'most visionary research award' at AAAI 2007 [12]. Also, Parallel-Horus has been used in our prize-winning contribution to the First IEEE International Scalable Computing Challenge at CCGrid 2008 (Lyon, France) [13].…”

Section: Parallel-horusmentioning

confidence: 99%

Adaptive Parallel Householder Bidiagonalization

Liu

Seinstra²

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.With the increasing use of large image and video archives and high-resolution multimedia data streams in many of today's research and application areas, there is a growing need for multimedia-oriented high-performance computing. As a consequence, a need for algorithms, methodologies, and tools that can serve as support in the (automatic) parallelization of multimedia applications is rapidly emerging.This paper discusses the parallelization of Householder bidiagonalization, a matrix factorization method which is an integral part of full Singular Value Decomposition (SVD) -an important algorithm for many multimedia problems. Householder bidiagonalization is hard to parallelize efficiently because the total number of matrix elements taking part in the calculations reduces during runtime. To overcome the growing negative performance impact of load imbalances and overprovisioning of compute resources, we apply adaptive runtime techniques of periodic matrix remapping and process reduction for improved performance. Results show that our adaptive parallel execution approach provides a significant improvement in efficiency, even when applying a set of compute resources which is (initially) very large.

show abstract

Mediamill: Searching Multimedia Archives Based on Learned Semantics

Cited by 20 publications

References 1 publication

Interactive Search by Direct Manipulation of Dissimilarity Space

Interactive Search by Direct Manipulation of Dissimilarity Space

Compact Object Descriptors from Local Colour Invariant Histograms

Adaptive Parallel Householder Bidiagonalization

Contact Info

Product

Resources

About