Carnegie Mellon University

About: Carnegie Mellon University is a education organization based out in Pittsburgh, Pennsylvania, United States. It is known for research contribution in the topics: Computer science & Robot. The organization has 36317 authors who have published 104359 publications receiving 5975734 citations. The organization is also known as: CMU & Carnegie Mellon.

Evaluating bag-of-visual-words representations in scene classification

Abstract: Based on keypoints extracted as salient image patches, an image can be described as a "bag of visual words" and this representation has been used in scene classification. The choice of dimension, selection, and weighting of visual words in this representation is crucial to the classification performance but has not been thoroughly studied in previous work. Given the analogy between this representation and the bag-of-words representation of text documents, we apply techniques used in text categorization, including term weighting, stop word removal, feature selection, to generate image representations that differ in the dimension, selection, and weighting of visual words. The impact of these representation choices to scene classification is studied through extensive experiments on the TRECVID and PASCAL collection. This study provides an empirical basis for designing visual-word representations that are likely to produce superior classification performance.

Scientific Discovery: Computational Explorations of the Creative Processes

Abstract: Scientific discovery is often regarded as romantic and creative -- and hence unanalyzable -- whereas the everyday process of verifying discoveries is sober and more suited to analysis. Yet this fascinating exploration of how scientific work proceeds argues that however sudden the moment of discovery may seem, the discovery process can be described and modeled. Using the methods and concepts of contemporary information-processing psychology (or cognitive science) the authors develop a series of artificial-intelligence programs that can simulate the human thought processes used to discover scientific laws. The programs -- BACON, DALTON, GLAUBER, and STAHL -- are all largely data-driven, that is, when presented with series of chemical or physical measurements they search for uniformities and linking elements, generating and checking hypotheses and creating new concepts as they go along. Scientific Discovery examines the nature of scientific research and reviews the arguments for and against a normative theory of discovery; describes the evolution of the BACON programs, which discover quantitative empirical laws and invent new concepts; presents programs that discover laws in qualitative and quantitative data; and ties the results together, suggesting how a combined and extended program might find research problems, invent new instruments, and invent appropriate problem representations. Numerous prominent historical examples of discoveries from physics and chemistry are used as tests for the programs and anchor the discussion concretely in the history of science.

Time Discounting for Primary Rewards

Abstract: Previous research, involving monetary rewards, found that limbic reward-related areas show greater activity when an intertemporal choice includes an immediate reward than when the options include only delayed rewards. In contrast, the lateral prefrontal and parietal cortex (areas commonly associated with deliberative cognitive processes, including future planning) respond to intertemporal choices in general but do not exhibit sensitivity to immediacy (McClure et al., 2004). The current experiments extend these findings to primary rewards (fruit juice or water) and time delays of minutes instead of weeks. Thirsty subjects choose between small volumes of drinks delivered at precise times during the experiment (e.g., 2 ml now vs 3 ml in 5 min). Consistent with previous findings, limbic activation was greater for choices between an immediate reward and a delayed reward than for choices between two delayed rewards, whereas the lateral prefrontal cortex and posterior parietal cortex responded similarly whether choices were between an immediate and a delayed reward or between two delayed rewards. Moreover, relative activation of the two sets of brain regions predicts actual choice behavior. A second experiment finds that when the delivery of all rewards is offset by 10 min (so that the earliest available juice reward in any choice is 10 min), no differential activity is observed in limbic reward-related areas for choices involving the earliest versus only more delayed rewards. We discuss implications of this finding for differences between primary and secondary rewards.

The representation, recognition, and locating of 3-d objects

Abstract: The problem of recognizing and locating rigid objects in 3-D space is important for applications of robotics and naviga tion. We analyze the task requirements in terms of what information needs to be represented, how to represent it, what kind of paradigms can be used to process it, and how to implement the paradigms. We describe shape surfaces by curves and patches, which we represent by linear primitives, such as points, lines, and planes. Next we describe algo rithms to construct this representation from range data. We then propose the paradigm of recognizing objects while locat ing them. We analyze the basic constraint of rigidity that can be exploited, which we implement as a prediction and verifi cation scheme that makes efficient use of the representation. Results are presented for data obtained from a laser range finder, but both the shape representation and the matching algorithm are general and can be used for other types of data, such as ultrasound, stereo, and tactile.

Project Aura: toward distraction-free pervasive computing

Abstract: The most precious resource in a computer system is no longer its processor, memory, disk, or network, but rather human attention. Aura aims to minimize distractions on a user's attention, creating an environment that adapts to the user's context and needs. Aura is specifically intended for pervasive computing environments involving wireless communication, wearable or handheld computers, and smart spaces. Human attention is an especially scarce resource in such environments, because the user is often preoccupied with walking, driving, or other real-world interactions. In addition, mobile computing poses difficult challenges such as intermittent and variable-bandwidth connectivity, concern for battery life, and the client resource constraints that weight and size considerations impose. To accomplish its ambitious goals, research in Aura spans every system level: from the hardware, through the operating system, to applications and end users. Underlying this diversity of concerns, Aura applies two broad concepts. First, it uses proactivity, which is a system layer's ability to anticipate requests from a higher layer. In today's systems, each layer merely reacts to the layer above it. Second, Aura is self-tuning: layers adapt by observing the demands made on them and adjusting their performance and resource usage characteristics accordingly. Currently, system-layer behavior is relatively static. Both of these techniques will help lower demand for human attention.