Xerox (France)

Smalltalk-80 is the classic standard Smalltalk language as described in Smalltalk-80: The Language and Its Implementation by Goldberg and Robson. This book is commonly called “the Blue Booki. Squeak implements the dialect of Smalltalk described in this book, but has a different implementation. Overview of the Smalltalk Language Smalltalk is a general purpose, high level programming language. It was the first original “purei object oriented language, but not the first to use the object oriented concept, which is credited to Simula 67. The explosive growth of Object Oriented Programming (OOP) technologies began in the early 1980's, with Smalltalk's introduction. Behind it was the idea that the individual human user should be the most important component of any computing system, and that programming should be a natural extension of thinking, and also a dynamic and evolutionary process consistent with the model of human learning activity. In Smalltalk, these ideas are embodied in a framework for human-computer communication. In a sense, Smalltalk is yet another language like C and Pascal, and programs can be written in Smalltalk that have the look and feel of such conventional languages. The difference lies * in the amount of code that can be reduced, * less cryptic syntax, * and code that is easier to handle for application maintenance and enhancement. But Smalltalk's most powerful feature is easy code reuse. Smalltalk makes reuse of programs, routines, and subroutines (methods) far easier. Though procedural languages allow reuse too, it is harder to do, and much easier to cheat. It is no surprise that Smalltalk is relatively easy to learn, mainly due to its simple syntax and semantics, as well as few concepts. Objects, classes, messages, and methods form the basis of programming in Smalltalk. The general methodology to use Smalltalk The notion of human-computer interface also results in Smalltalk promoting the development of safer systems. Errors in Smalltalk may be viewed as objects telling users that confusion exists as to how to perform a desired function.

and group activities is critical to successful collaboration and is commonly supported in CSCW systems by active, information generation mechanisms separate from the shared workspace. These mechanisms pena~ise information providers, presuppose relevance to the recipient, and make access difficult, We discuss a study of shared editor use which suggests that awareness information provided and exploited passively through the shared workspace, allows users to move smoothly between close and loose collaboration, and to assign and coordinate work dynamically. Passive awareness mechanisms promise effective support for collaboration requiring this sort of behaviour, whilst avoiding problems with active approaches.

This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections. We formulate this problem in terms of finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube, and propose a simple and efficient alternating minimization algorithm to accomplish this task. This algorithm, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). The resulting binary codes significantly outperform several other state-of-the-art methods. We also show that further performance improvements can result from transforming the data with a nonlinear kernel mapping prior to PCA or CCA. Finally, we demonstrate an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.

This paper describes a "superset" of operations that can be applied to URI. It consists of both a grammar and a description of basic functionality for URI. To understand what is a valid URI, both the grammar and the associated description have to be studied. Some of the functionality described is not applicable to all URI schemes, and some operations are only possible when certain media types are retrieved using the URI, regardless of the scheme used.

Within the field of pattern classification, the Fisher kernel is a powerful framework which combines the strengths of generative and discriminative approaches. The idea is to characterize a signal with a gradient vector derived from a generative probability model and to subsequently feed this representation to a discriminative classifier. We propose to apply this framework to image categorization where the input signals are images and where the underlying generative model is a visual vocabulary: a Gaussian mixture model which approximates the distribution of low-level features in images. We show that Fisher kernels can actually be understood as an extension of the popular bag-of-visterms. Our approach demonstrates excellent performance on two challenging databases: an in-house database of 19 object/scene categories and the recently released VOC 2006 database. It is also very practical: it has low computational needs both at training and test time and vocabularies trained on one set of categories can be applied to another set without any significant loss in performance.

This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.

gaver.europarc @ rx.xerox.com Ecological approaches to psychology suggest succinct accounts ofeasily-used artifacts. Affordances are properties of the world that are compatible with and relevant for people’s interactions. When affordances are perceptible, they offer a direct link between perception and action; hidden and false affordances lead to mistakes. Complex actions can be understood in terms of groups of affordances that are sequential in time or nested in space, and in terms of the abilities of different media to reveal them. I illustrate this discussion with several examples of interface techniques, and suggest that the concept of affordances can provide a useful tool for user-centered analyses of technologies.

This work presents a new perspective on characterizing the similarity between elements of a database or, more generally, nodes of a weighted and undirected graph. It is based on a Markov-chain model of random walk through the database. More precisely, we compute quantities (the average commute time, the pseudoinverse of the Laplacian matrix of the graph, etc.) that provide similarities between any pair of nodes, having the nice property of increasing when the number of paths connecting those elements increases and when the "length" of paths decreases. It turns out that the square root of the average commute time is a Euclidean distance and that the pseudoinverse of the Laplacian matrix is a kernel matrix (its elements are inner products closely related to commute times). A principal component analysis (PCA) of the graph is introduced for computing the subspace projection of the node vectors in a manner that preserves as much variance as possible in terms of the Euclidean commute-time distance. This graph PCA provides a nice interpretation to the "Fiedler vector," widely used for graph partitioning. The model is evaluated on a collaborative-recommendation task where suggestions are made about which movies people should watch based upon what they watched in the past. Experimental results on the MovieLens database show that the Laplacian-based similarities perform well in comparison with other methods. The model, which nicely fits into the so-called "statistical relational learning" framework, could also be used to compute document or word similarities, and, more generally, it could be applied to machine-learning and pattern-recognition tasks involving a relational database

This paper presents the use of B-splines as a tool in various digital signal processing applications. The theory of B-splines is briefly reviewed, followed by discussions on B-spline interpolation and B-spline filtering. Computer implementation using both an efficient software viewpoint and a hardware method are discussed. Finally, experimental results are presented for illustrative purposes in two-dimensional image format. Applications to image and signal processing include interpolation, smoothing, filtering, enlargement, and reduction.

Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning method, and validate our approach by building and publicly releasing a new video dataset, called "Virtual KITTI", automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow. We provide quantitative experimental evidence suggesting that (i) modern deep learning algorithms pre-trained on real data behave similarly in real and virtual worlds, and (ii) pre-training on virtual data improves performance. As the gap between real and virtual worlds is small, virtual worlds enable measuring the impact of various weather and imaging conditions on recognition performance, all other things being equal. We show these factors may affect drastically otherwise high-performing deep models for tracking.

Inference of individual ancestry coefficients, which is important for population genetic and association studies, is commonly performed using computer-intensive likelihood algorithms. With the availability of large population genomic data sets, fast versions of likelihood algorithms have attracted considerable attention. Reducing the computational burden of estimation algorithms remains, however, a major challenge. Here, we present a fast and efficient method for estimating individual ancestry coefficients based on sparse nonnegative matrix factorization algorithms. We implemented our method in the computer program sNMF and applied it to human and plant data sets. The performances of sNMF were then compared to the likelihood algorithm implemented in the computer program ADMIXTURE. Without loss of accuracy, sNMF computed estimates of ancestry coefficients with runtimes ∼10-30 times shorter than those of ADMIXTURE.

With the ever-expanding volume of visual content available, the ability to organize and navigate such content by aesthetic preference is becoming increasingly important. While still in its nascent stage, research into computational models of aesthetic preference already shows great potential. However, to advance research, realistic, diverse and challenging databases are needed. To this end, we introduce a new large-scale database for conducting Aesthetic Visual Analysis: AVA. It contains over 250,000 images along with a rich variety of meta-data including a large number of aesthetic scores for each image, semantic labels for over 60 categories as well as labels related to photographic style. We show the advantages of AVA with respect to existing databases in terms of scale, diversity, and heterogeneity of annotations. We then describe several key insights into aesthetic preference afforded by AVA. Finally, we demonstrate, through three applications, how the large scale of AVA can be leveraged to improve performance on existing preference tasks.

article Free Access Share on The Dexter hypertext reference model Authors: Frank Halasz Xerox, Palo Alto, CA Xerox, Palo Alto, CAView Profile , Mayer Schwartz Tektronix, Inc., Beaverton, OR Tektronix, Inc., Beaverton, ORView Profile , Editors: Kaj Grønbæk View Profile , Randall H. Trigg View Profile Authors Info & Claims Communications of the ACMVolume 37Issue 2Feb. 1994pp 30–39https://doi.org/10.1145/175235.175237Published:01 February 1994Publication History 524citation2,414DownloadsMetricsTotal Citations524Total Downloads2,414Last 12 Months82Last 6 weeks11 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

We are investigating ways in which media space technologies can support distributed work groups through access to information that supports general awareness. Awareness involves knowing who is “around”, what activities are occurring, who is talking with whom; it provides a view of one another in the daily work environments. Awareness may lead to informal interactions, spontaneous connections, and the development of shared cultures—all important aspects of maintaining working relationships which are denied to groups distributed across multiple sites.

Everyday listening is the experience of hearing events in the world rather than sounds per se. In this paper, I take an ecological approach to everyday listening in order to overcome constraints on its study implied by more traditional approaches. In particular, I am concerned with developing a new framework for describing sound in terms of audible source attributes. An examination of the continuum of structured energy from event to audition suggests that sound conveys information about events at locations in an environment. Qualitative descriptions of the physics of sound-producing events, complemented by protocol studies, suggest a tripartite division of sound-producing events into those involving vibrating solids, gasses, or liquids. Within each of these categories, basic level events are defined by the simple interactions that can cause these materials to sound, while more complex events can be described in terms of temporal patterning, compound, or hybrid sources. The results of these investigations are used to create a map of sound-producing events and their attributes useful in guiding further exploration.

Adaptation to local environments often occurs through natural selection acting on a large number of loci, each having a weak phenotypic effect. One way to detect these loci is to identify genetic polymorphisms that exhibit high correlation with environmental variables used as proxies for ecological pressures. Here, we propose new algorithms based on population genetics, ecological modeling, and statistical learning techniques to screen genomes for signatures of local adaptation. Implemented in the computer program "latent factor mixed model" (LFMM), these algorithms employ an approach in which population structure is introduced using unobserved variables. These fast and computationally efficient algorithms detect correlations between environmental and genetic variation while simultaneously inferring background levels of population structure. Comparing these new algorithms with related methods provides evidence that LFMM can efficiently estimate random effects due to population history and isolation-by-distance patterns when computing gene-environment correlations, and decrease the number of false-positive associations in genome scans. We then apply these models to plant and human genetic data, identifying several genes with functions related to development that exhibit strong correlations with climatic gradients.

Design Space Analysis is an approach to representing design rationale. It uses a semiformal notation, called QOC (Questions, Options, and Criteria), to represent the design space around an artifact. The main constituents of QOC are Questions identifying key design issues, Options providing possible answers to the Questions, and Criteria for assessing and comparing the Options. Design Space Analysis also takes account of justifications for the design (and possible alternative designs) that reflect considerations such as consistency, models and analogies, and relevant data and theory. A Design Space Analysis does not produce a record of the design process but is instead a coproduct of design and has to be constructed alongside the artifact itself. Our work is motivated by the notion that a Design Space Analysis will repay the investment in its creation by supporting both the original process of design and subsequent work on redesign and reuse by (a) providing an explicit representation to aid reasoning about the design and about the consequences of changes to it and (b) serving as a vehicle for communication, for example, among members of the design team or among the original designers and later maintainers of a system. Our work to date emphasises the nature of the QOC representation over processes for creating it, so these claims serve as goals rather than objectives we have achieved. This article describes the elements of Design Space Analysis and illustrates them by reference to analyses of existing designs and to studies of the concepts and arguments used by designers during design discussions.

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function that measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. Label embedding enjoys a built-in ability to leverage alternative sources of information instead of or in addition to attributes, such as, e.g., class hierarchies or textual descriptions. Moreover, label embedding encompasses the whole range of learning settings from zero-shot learning to regular learning with a large number of labeled examples.

The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by what makes it different from other images. One drawback of the Fisher vector is that it is high-dimensional and, as opposed to the BOV, it is dense. The resulting memory and computational costs do not make Fisher vectors directly amenable to large-scale retrieval. Therefore, we compress Fisher vectors to reduce their memory footprint and speed-up the retrieval. We compare three binarization approaches: a simple approach devised for this representation and two standard compression techniques. We show on two publicly available datasets that compressed Fisher vectors perform very well using as little as a few hundreds of bits per image, and significantly better than a very recent compressed BOV approach.

Attributes are an intermediate representation, which enables parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function which measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. The label embedding framework offers other advantages such as the ability to leverage alternative sources of information in addition to attributes (e.g. class hierarchies) or to transition smoothly from zero-shot learning to learning with large quantities of data.