Multimodal entity linking (MEL) is the task that consists of matching textual and visual mentions of entities in unstructured data to their corresponding entities in a knowledge base (KB). To be effective in large-scale practical settings, MEL systems must meet three objectives: high linking accuracy, computational efficiency, and storage efficiency, i.e., a compact yet efficient index of the KB. In this paper, we highlight that state-of-the-art systems fail to simultaneously satisfy these 3 requirements. To meet this three-fold objective, we propose FAST-MEL, a lightweight encoder-based MEL solution that relies on a novel and compact fixed-size vectorized representation of both the textual and visual information of each entity or mention. It matches the accuracy of the best systems but performs three orders of magnitude faster. It also consumes one order of magnitude less storage than the fastest systems.

Transferable adversarial images raise critical security concerns for computer vision systems in real-world, black-box attack scenarios. Although many transfer attacks have been proposed, existing research lacks a systematic and comprehensive evaluation. In this paper, we systemize transfer attacks into five categories around the general machine learning pipeline and provide the first comprehensive evaluation, with 23 representative attacks against 11 representative defenses, including the recent, transfer-oriented defense and the real-world Google Cloud Vision. In particular, we identify two main problems of existing evaluations: (1) for attack transferability, lack of intra-category analyses with fair hyperparameter settings, and (2) for attack stealthiness, lack of diverse measures. Our evaluation results validate that these problems have indeed caused misleading conclusions and missing points, and addressing them leads to new, consensus-challenging insights, such as (1) an early attack, DI, even outperforms all similar follow-up ones, (2) the state-of-the-art (white-box) defense, DiffPure, is even vulnerable to (black-box) transfer attacks, and (3) even under the same $L_{p}$Lp constraint, different attacks yield dramatically different stealthiness results regarding diverse imperceptibility metrics, finer-grained measures, and a user study. We hope that our analyses will serve as guidance on properly evaluating transferable adversarial images and advance the design of attacks and defenses.

Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Its extensions mostly focus on the definition of interpolation and the space (input or feature) where it takes place, while the augmentation process itself is less studied. In most methods, the number of generated examples is limited to the mini-batch size and the number of examples being interpolated is limited to two (pairs), in the input space. We make progress in this direction by introducing MultiMix, which generates an arbitrarily large number of interpolated examples beyond the mini-batch size and interpolates the entire mini-batch in the embedding space. Effectively, we sample on the entire convex hull of the mini-batch rather than along linear segments between pairs of examples. On sequence data, we further extend to Dense MultiMix. We densely interpolate features and target labels at each spatial location and also apply the loss densely. To mitigate the lack of dense labels, we inherit labels from examples and weight interpolation factors by attention as a measure of confidence. Overall, we increase the number of loss terms per mini-batch by orders of magnitude at little additional cost. This is only possible because of interpolating in the embedding space. We empirically show that our solutions yield significant improvement over state-of-the-art mixup methods on four different benchmarks, despite interpolation being only linear. By analyzing the embedding space, we show that the classes are more tightly clustered and uniformly spread over the embedding space, thereby explaining the improved behavior.

Mixup is a powerful data augmentation method that in-terpolates between two or more examples in the input or feature space and between the corresponding target labels. However, how to best interpolate images is not well defined. Recent mixup methods overlay or cut-and-paste two or more objects into one image, which needs care in selecting regions. Mixup has also been connected to autoencoders, because often autoencoders generate an image that continuously deforms into another. However, such images are typically of low quality. In this work, we revisit mixup from the deformation perspective and introduce AligtiMixup, where we geometrically align two images in the feature space. The correspondences allow us to interpolate between two sets of features, while keeping the locations of one set. Interestingly, this retains mostly the geometry or pose of one image and the appearance or texture of the other. We also show that an autoencoder can still improve representation learning under mixup, without the classifier ever seeing decoded images. AlignMixup outperforms state-of-the-art mixup methods on five different benchmarks. Code available at https://github.com/shashankvkt/AlignMixup_CVPR22.git

Machine learning systems are vulnerable to adversarial attack. By applying to the input object a small, carefully-designed perturbation, a classifier can be tricked into making an incorrect prediction. This phenomenon has drawn wide interest, with many attempts made to explain it. However, a complete understanding is yet to emerge. In this paper we adopt a slightly different perspective, still relevant to classification. We consider retrieval, where the output is a set of objects most similar to a user-supplied query object, corresponding to the set of k-nearest neighbors. We investigate the effect of adversarial perturbation on the ranking of objects with respect to a query. Through theoretical analysis, supported by experiments, we demonstrate that as the intrinsic dimensionality of the data domain rises, the amount of perturbation required to subvert neighborhood rankings diminishes, and the vulnerability to adversarial attack rises. We examine two modes of perturbation of the query: either `closer' to the target point, or `farther' from it. We also consider two perspectives: `query-centric', examining the effect of perturbation on the query's own neighborhood ranking, and `target-centric', considering the ranking of the query point in the target's neighborhood set. All four cases correspond to practical scenarios involving classification and retrieval.

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks in our everyday lives. When white-box attacks are almost always successful, it is typically only the distortion of the perturbations that matters in their evaluation. In this work, we argue that speed is important as well, especially when considering that fast attacks are required by adversarial training. Given more time, iterative methods can always find better solutions. We investigate this speed-distortion trade-off in some depth and introduce a new attack called boundary projection (BP) that improves upon existing methods by a large margin. Our key idea is that the classification boundary is a manifold in the image space: we therefore quickly reach the boundary and then optimize distortion on this manifold.

This paper proposes a framework for group membership protocols preventing the curious but honest server from reconstructing the enrolled biometric signatures and inferring the identity of querying clients. This framework learns the embedding parameters, group representations and assignments simultaneously. Experiments show the trade-off between security/privacy and verification/identification performances.

Abstract This paper investigates the visual quality of the adversarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artifacts. In this work, smoothing has a different meaning as it perceptually shapes the perturbation according to the visual content of the image to be attacked. The perturbation becomes locally smooth on the flat areas of the input image, but it may be noisy on its textured areas and sharp across its edges.This operation relies on Laplacian smoothing, well-known in graph signal processing, which we integrate in the attack pipeline. We benchmark several attacks with and without smoothing under a white box scenario and evaluate their transferability. Despite the additional constraint of smoothness, our attack has the same probability of success at lower distortion.

This paper proposes a group membership verification protocol preventing the curious but honest server from reconstructing the enrolled signatures and inferring the identity of querying clients. The protocol quantizes the signatures into discrete embeddings, making reconstruction difficult. It also aggregates multiple embeddings into representative values, impeding identification. Theoretical and experimental results show the trade-off between the security and the error rates.

In this demonstration, we present Exquisitor, a media explorer capable of learning user preferences in real-time during interactions with the 99.2 million images of YFCC100M. Exquisitor owes its efficiency to innovations in data representation, compression, and indexing. Exquisitor can complete each interaction round, including learning preferences and presenting the most relevant results, in less than 30 ms using only a single CPU core and modest RAM. In short, Exquisitor can bring large-scale interactive learning to standard desktops and laptops, and even high-end mobile devices.

Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering. However, since their convergence generally requires sample sizes (that is, neighborhood sizes) on the order of hundreds of points, existing ID estimation methods may have only limited usefulness for applications in which the data consists of many natural groups of small size. In this paper, we propose a local ID estimation strategy stable even for ‘tight’ localities consisting of as few as 20 sample points. The estimator applies MLE techniques over all available pairwise distances among the members of the sample, based on a recent extreme-value-theoretic model of intrinsic dimensionality, the Local Intrinsic Dimension (LID). Our experimental results show that our proposed estimation technique can achieve notably smaller variance, while maintaining comparable levels of bias, at much smaller sample sizes than state-of-the-art estimators.

The world has experienced phenomenal growth in data production and storage in recent years, much of which has taken the form of media files. At the same time, computing power has become abundant with multi-core machines, grids, and clouds. Yet it remains a challenge to harness the available power and move toward gracefully searching and retrieving from web-scale media collections. Several researchers have experimented with using automatically distributed computing frameworks, notably Hadoop and Spark, for processing multimedia material, but mostly using small collections on small computing clusters. In this article, we describe a prototype of a (near) web-scale throughput-oriented MM retrieval service using the Spark framework running on the AWS cloud service. We present retrieval results using up to 43 billion SIFT feature vectors from the public YFCC 100M collection, making this the largest high-dimensional feature vector collection reported in the literature. We also present a publicly available demonstration retrieval system, running on our own servers, where the implementation of the Spark pipelines can be observed in practice using standard image benchmarks, and downloaded for research purposes. Finally, we describe a method to evaluate retrieval quality of the ever-growing high-dimensional index of the prototype, without actually indexing a web-scale media collection.

Computing power has now become abundant with multi-core machines, grids and clouds, but it remains a challenge to harness the available power and move towards gracefully handling web-scale datasets. Several researchers have used automatically distributed computing frameworks, notably Hadoop and Spark, for processing multimedia material, but mostly using small collections on small clusters. In this paper, we describe the engineering process for a prototype of a (near) web-scale multimedia service using the Spark framework running on the AWS cloud service. We present experimental results using up to 43 billion SIFT feature vectors from the public YFCC 100M collection, making this the largest high-dimensional feature vector collection reported in the literature. The design of the prototype and performance results demonstrate both the flexibility and scalability of the Spark framework for implementing multimedia services.

In today's world of ever-increasing multimedia collections, dynamically and persistently maintaining high-dimensional indexes is imperative for industrial applications. Since HDD performance is the main bottleneck in index maintenance, we investigate the impact of SSD technology. We use the NV-tree to drive our analysis, as the only high-dimensional index in the literature which has seriously addressed updates. Our simulation model indicates that an index of 1.5 billion descriptors can be built dynamically on a high-end SSD in just over four hours of disk time, which is more than 500x faster than using a high-end HDD. Relatively small investment in the new SSD technology can thus make dynamic and persistent high-dimensional indexes very feasible.

The large dimensionality of modern image feature vectors, up to thousands of dimensions, is challenging the high dimensional indexing techniques. Traditional approaches fail at returning good quality results within a response time that is usable in practice. However, similarity search techniques inspired by the group testing framework have recently been proposed in an attempt to specifically defeat the curse of dimensionality. Yet, group testing does not scale and fails at indexing very large collections of images because its internal procedures analyze an excessively large fraction of the indexed data collection. This paper identifies these difficulties and proposes extensions to the group testing framework for similarity searches that allow to handle larger collections of feature vectors. We demonstrate that it can return high quality results much faster compared to state-of-the-art group testing strategies when indexing truly high-dimensional features that are indeed hardly indexable with traditional indexing approaches.

This work proposes a privacy-protection framework for an important application called outsourced media search. This scenario involves a data owner, a client, and an untrusted server, where the owner outsources a search service to the server. Due to lack of trust, the privacy of the client and the owner should be protected. The framework relies on multimedia hashing and symmetric encryption. It requires involved parties to participate in a privacy-enhancing protocol. Additional processing steps are carried out by the owner and the client: (i) before outsourcing low-level media features to the server, the owner has to one-way hash them, and partially encrypt each hash-value; (ii) the client completes the similarity search by re-ranking the most similar candidates received from the server. One-way hashing and encryption add ambiguity to data and make it difficult for the server to infer contents from database items and queries, so the privacy of both the owner and the client is enforced. The proposed framework realizes trade-offs among strength of privacy enforcement, quality of search, and complexity, because the information loss can be tuned during hashing and encryption. Extensive experiments demonstrate the effectiveness and the flexibility of the framework.

This paper is concerned with the estimation of a local measure of intrinsic dimensionality (ID) recently proposed by Houle. The local model can be regarded as an extension of Karger and Ruhl's expansion dimension to a statistical setting in which the distribution of distances to a query point is modeled in terms of a continuous random variable. This form of intrinsic dimensionality can be particularly useful in search, classification, outlier detection, and other contexts in machine learning, databases, and data mining, as it has been shown to be equivalent to a measure of the discriminative power of similarity functions. Several estimators of local ID are proposed and analyzed based on extreme value theory, using maximum likelihood estimation (MLE), the method of moments (MoM), probability weighted moments (PWM), and regularly varying functions (RV). An experimental evaluation is also provided, using both real and artificial data.

LSH is a popular framework to generate compact representations of multimedia data, which can be used for content based search. However, the performance of LSH is limited by its unsupervised nature and the underlying feature scale. In this work, we propose to improve LSH by incorporating two elements - supervised hash bit selection and multi-scale feature representation. First, a feature vector is represented by multiple scales. At each scale, the feature vector is divided into segments. The size of a segment is decreased gradually to make the representation correspond to a coarse-to-fine view of the feature. Then each segment is hashed to generate more bits than the target hash length. Finally the best ones are selected from the hash bit pool according to the notion of bit reliability, which is estimated by bit-level hypothesis testing.

We propose a privacy protection framework for large-scale content-based information retrieval. It offers two layers of protection. First, robust hash values are used as queries to prevent revealing original content or features. Second, the client can choose to omit certain bits in a hash value to further increase the ambiguity for the server. Due to the reduced information, it is computationally difficult for the server to know the client's interest. The server has to return the hash values of all possible candidates to the client. The client performs a search within the candidate list to find the best match. Since only hash values are exchanged between the client and the server, the privacy of both parties is protected. We introduce the concept oftunable privacy, where the privacy protection level can be adjusted according to a policy. It is realized through hash-based piecewise inverted indexing. The idea is to divide a feature vector into pieces and index each piece with a subhash value. Each subhash value is associated with an inverted index list. The framework has been extensively tested using a large image database. We have evaluated both retrieval performance and privacy-preserving performance for a particular content identification application. Two different constructions of robust hash algorithms are used. One is based on random projections; the other is based on the discrete wavelet transform. Both algorithms exhibit satisfactory performance in comparison with state-of-the-art retrieval schemes. The results show that the privacy enhancement slightly improves the retrieval performance. We consider the majority voting attack for estimating the query category and identification. Experiment results show that this attack is a threat when there are near-duplicates, but the success rate decreases with the number of omitted bits and the number of distinct items.

While the past decade has witnessed an unprecedented growth of data generated and collected all over the world, existing data management approaches lack the ability to address the challenges of Big Data. One of the most promising tools for Big Data processing is the MapReduce paradigm. Although it has its limitations, the MapReduce programming model has laid the foundations for answering some of the Big Data challenges. In this paper, we focus on Hadoop, the open-source implementation of the MapReduce paradigm. Using as case-study a Hadoop-based application, i.e., image similarity search, we present our experiences with the Hadoop framework when processing terabytes of data. The scale of the data and the application workload allowed us to test the limits of Hadoop and the efficiency of the tools it provides. We present a wide collection of experiments and the practical lessons we have drawn from our experience with the Hadoop environment. Our findings can be shared as best practices and recommendations to the Big Data researchers and practioners.

This paper presents a moderately secure but very efficient approximate nearest neighbors search. After detailing the threats pertaining to the `honest but curious' model, our approach starts from a state-of-the-art algorithm in the domain of approximate nearest neighbors search. We gradually develop mechanisms partially blocking the attacks threatening the original algorithm.

Most researchers working on high-dimensional indexing agree on the following three trends: (i) the size of the multimedia collections to index are now reaching millions if not billions of items, (ii) the computers we use every day now come with multiple cores and (iii) hardware becomes more available, thanks to easier access to Grids and/or Clouds. This paper shows how the Map-Reduce paradigm can be applied to indexing algorithms and demonstrates that great scalability can be achieved using Hadoop, a popular Map-Reduce-based framework. Dramatic performance improvements are not however guaranteed a priori: such frameworks are rigid, they severely constrain the possible access patterns to data and scares resource RAM has to be shared. Furthermore, algorithms require major redesign, and may have to settle for sub-optimal behavior. The benefits, however, are many: simplicity for programmers, automatic distribution, fault tolerance, failure detection and automatic re-runs and, last but not least, scalability. We share our experience of adapting a clustering-based high-dimensional indexing algorithm to the Map-Reduce model, and of testing it at large scale with Hadoop as we index 30 billion SIFT descriptors. We foresee that lessons drawn from our work could minimize time, effort and energy invested by other researchers and practitioners working in similar directions.

Content-Based Image Retrieval Systems (CBIRS) used in forensics related contexts require very good image recognition capabilities. Whereas the robustness criterion has been extensively covered by Computer Vision or Multimedia literature, none of these communities explored the security of CBIRS. Recently, preliminary studies have shown real systems can be deluded by applying transformations to images that are very specific to the SIFT local description scheme commonly used for recognition. The work presented in this paper adds one strategy for attacking images, and somehow enlarges the box of tools hackers can use for deluding systems. This paper shows how the orientation of keypoints can be tweaked, which in turn lowers matches since this deeply changes the final SIFT feature vectors. The method learns what visual patch should be applied to change the orientation of keypoints thanks to an SVM-based process. Experiments with a database made of 100,000 real world images confirms the effectiveness of this keypoint-orientation attacking scheme.

The performance of Content-Based Image Retrieval Systems (CBIRS) is typically evaluated via benchmarking their capacity to match images despite various generic distortions such as crops, rescalings or Picture in Picture (PiP) attacks, which are the most challenging. Distortions are made in a very generic manner, by applying a set of transformations that are completely independent from the systems later performing recognition tasks. Recently, studies have shown that exploiting the finest details of the various techniques used in a CBIRS offers the opportunity to create distortions that dramatically reduce the recognition performance. Such a security perspective is taken in this paper. Instead of creating generic PiP distortions, it proposes a creation scheme able to delude the recognition capabilities of a CBIRS that is representative of state of the art techniques as it relies on SIFT, high-dimensional k-nearest neighbors searches and geometrical robustification steps. Experiments using 100,000 real-world images confirm the effectiveness of these security-oriented PiP visual modifications.

Recent indexing techniques inspired by source coding have been shown successful to index billions of high-dimensional vectors in memory. In this paper, we propose an approach that re-ranks the neighbor hypotheses obtained by these compressed-domain indexing methods. In contrast to the usual post-verification scheme, which performs exact distance calculation on the short-list of hypotheses, the estimated distances are refined based on short quantization codes, to avoid reading the full vectors from disk. We have released a new public dataset of one billion 128 dimensional vectors and proposed an experimental setup to evaluate high dimensional indexing algorithms on a realistic scale. Experiments show that our method accurately and efficiently re-ranks the neighbor hypotheses using little memory compared to the full vectors representation.

This paper presents the NV-Tree (Nearest Vector Tree). It addresses the specific, yet important, problem of efficiently and effectively finding the approximate k-nearest neighbors within a collection of a few billion high-dimensional data points. The NV-Tree is a very compact index, as only six bytes are kept in the index for each high-dimensional descriptor. It thus scales extremely well when indexing large collections of high-dimensional descriptors. The NV-Tree efficiently produces results of good quality, even at such a large scale that the indices cannot be kept entirely in main memory any more. We demonstrate this with extensive experiments using a collection of 2.5 billion SIFT (Scale Invariant Feature Transform) descriptors.

It has never been so easy to take pictures, and personal image collections have never been so large. Unfortunately, most current photo browsers provide very limited support for effectively navigating image collections. This demonstration proposal describes PhotoCube, a personal image browser based on a multi-dimensional data model similar to the model used in OLAP applications. With PhotoCube, users can tag pictures, structure tags into various hierarchies, and browse images according to any possible perspective. We also describe three demonstration scenarios that show the power, flexibility and scalability of PhotoCube.

Video analysis using local descriptors requires a high-throughput descriptor creation process. This speed can be obtained from modern GPUs. In this paper, we adapt the computation of the Eff2 descriptors, a SIFT variant, to the GPU. We compare our GPU-Eff descriptors to SiftGPU and show that while both variants yield similar results, the GPU-Eff descriptors require significantly less processing time.

Many content-based retrieval systems (CBIRS) describe images using the SIFT local features because of their very robust recognition capabilities. While SIFT features proved to cope with a wide spectrum of general purpose image distortions, its security has not fully been assessed yet. In one of their scenario, Hsu et al. in [2] show that very specific anti-SIFT attacks can jeopardize the keypoint detection. These attacks can delude systems using SIFT targeting application such as image authentication and (pirated) copy detection.

Content-Based Image Retrieval (CBIR) has been recently used as a filtering mechanism against the piracy of multimedia contents. Many publications in the last few years have proposed very robust schemes where pirated contents are detected despite severe modifications. As none of these systems have addressed the piracy problem from a security perspective, it is time to check whether they are secure: Can pirates mount violent attacks against CBIR systems by carefully studying the technology they use? This paper is an initial analysis of the security flaws of the typical technology blocks used in state-of-the-art CBIR systems. It is so far too early to draw any definitive conclusion about their inherent security, but it motivates and encourages further studies on this topic.

A large portion of the video material available on the Internet is distributed illegally. In this demonstration we present Videntifier Forensic, a new law enforcement solution for automatically identifying videos and images. Videntifier Forensic is very robust and efficient, even at a very large scale. We encourage ACM Multimedia participants to bring original videos and modified (yet visually acceptable) copies to challenge the capabilities of the system.

Over the last two decades, much research effort has been spent on nearest neighbor search in high-dimensional data sets. Most of the approaches published thus far have, however, only been tested on rather small collections. When large collections have been considered, high-performance environments have been used, in particular systems with a large main memory. Accessing data on disk has largely been avoided because disk operations are considered to be too slow. It has been shown, however, that using large amounts of memory is generally not an economic choice. Therefore, we propose the NV-tree, which is a very efficient disk-based data structure that can give good approximate answers to nearest neighbor queries with a single disk operation, even for very large collections of high-dimensional data. Using a single NV-tree, the returned results have high recall but contain a number of false positives. By combining two or three NV-trees, most of those false positives can be avoided while retaining the high recall. Finally, we compare the NV-tree to Locality Sensitive Hashing, a popular method for epsilon-distance search. We show that they return results of similar quality, but the NV-tree uses many fewer disk reads.

It is well known that high-dimensional nearest-neighbor retrieval is very expensive. Many signal processing methods suffer from this computing cost. Dramatic performance gains can be obtained by using approximate search, such as the popular Locality-Sensitive Hashing. This paper improves LSH by performing an on-line selection of the most appropriate hash functions from a pool of functions. An additional improvement originates from the use of E& lattices for geometric hashing instead of one-dimensional random projections. A performance study based on state-of-the-art high-dimensional descriptors computed on real images shows that our improvements to LSH greatly reduce the search complexity for a given level of accuracy.

With the proliferation of high-speed internet access and the availability of cheap secondary storage, movie piracy has become a major problem. This demonstration paper describes the Eff2 Videntifier, a content-based system for large-scale automatic copyright enforcement of videos. The paper briefly describes the database and image processing techniques underlying the system. It also describes our proposed demonstration, which realistically simulate scenarios of copyright violations of movies.

Many photo agencies use the web to sell access to their image collections. Despite significant security measures, images may be stolen and distributed, making it necessary to detect copyright violations. This demonstration paper describes a content-based system for large-scale automatic copyright enforcement. The paper briefly describes the image description, indexing and retrieval algorithm that lie at the heart of the system. It also describes our proposed demonstration, which is a realistic scenario of copyright violations of a large image collection.

Computer vision researchers have recently proposed several local descriptor schemes. Due to lack of database support, however, these descriptors have only been evaluated using small image collections. Recently, we have developed the PvS-framework, which allows efficient querying of large local descriptor collections. In this paper, we use the PvSframework to study the scalability of local image descriptors. We propose a new local descriptor scheme and compare it to three other well known schemes. Using a collection of almost thirty thousand images, we show that the new scheme gives the best results in almost all cases. We then give two stop rules to reduce query processing time and show that in many cases only a few query descriptors must be processed to find matching images. Finally, we test our descriptors on a collection of over three hundred thousand images, resulting in over 200 million local descriptors, and show that even at such a large scale the results are still of high quality, with no change in query processing time.

It is known that all multi-dimensional index structures fail to accelerate content-based similarity searches when the feature vectors describing images are high-dimensional. It is possible to circumvent this problem by relying on approximate search-schemes trading-off result quality for reduced query execution time. Most approximate schemes, however, provide none or only complex control on the precision of the searches, especially when retrieving the k nearest neighbors (NNs) of query points.In contrast, this paper describes an approximate search scheme for high-dimensional databases where the precision of the search can be probabilistically controlled when retrieving the k NNs of query points. It allows a fine and intuitive control over this precision by setting at run time the maximum probability for a vector that would be in the exact answer set to be missed in the approximate set of answers eventually returned. This paper also presents a performance study of the implementation using real datasets showing its reliability and efficiency. It shows, for example, that our method is 6.72 times faster than the sequential scan when it handles more than 5 106 24-dimensional vectors, even when the probability of missing one of the true nearest neighbors is below 0.01.

We describe an efficient server-based algorithm for garbage collecting persistent object stores in a client-server environmnet. The algorithm is incremental and runs concurrently with client transactions. Unlike previous algorithms, it does not hold any transactional locks on data and does non require callbacks to clients. It is fault-tolerant, but performs very little logging. The algorithm has been designed to be integrated into existing systems, and therefore it works with standard implementation techniques such as Two-Phase Locking and Write-Ahead-Logging. In addition, it supports client-server performance optimizations such as client caching and flexible management of client buffers. We describe an implementation of the algorithm in the EXODUS storage manager and present the results of a performance study of the implementation.

Remote data access from disparate sources across a wide-area network such as the Internet is problematic due to the unpredictable nature of the communications medium and the lack of knowledge about the load and potential delays at remote sites. Traditional, static, query processing approaches break down in this environment because they are unable to adapt in response to unexpected delays. Query scrambling has been proposed to address this problem. Scrambling modifies query execution plans on-the-fly when delays are encountered during runtime. In its original formulation, scrambling was based on simple heuristics, which although providing good performance in many cases, were also shown to be susceptible to problems resulting from bad scrambling decisions. In this paper we address these shortcomings by investigating ways to exploit query optimization technology to aid in making intelligent scrambling choices. We propose three different approaches to using query optimization for scramblin...