Communications of the ACM
Latest Research
From Communications of the ACM
Technical Perspective: Where Do People Draw Lines?
Computer graphics once focused exclusively on realism. The field eventually broadened to include other pictorial...
From Communications of the ACM
Where Do People Draw Lines?
This paper presents the results of a study in which artists made line drawings intended to convey specific 3D shapes.
From Communications of the ACM
Wherefore Art Thou R3579X?: Anonymized Social Networks, Hidden Patterns, and Structural Steganography
In a social network, nodes correspond to people or other social entities, and edges correspond to social links between them. We describe a family of attacks such...
From Communications of the ACM
Technical Perspective: A Perfect 'Match'
In a breakthrough contribution, the authors of the paper that follows have developed an efficient way to find approximate nearest neighbors for the case of database...
From Communications of the ACM
The Patchmatch Randomized Matching Algorithm For Image Manipulation
This paper presents a new randomized algorithm for quickly finding approximate nearest neighbor matches between image patches. Our algorithm offers substantial...
From Communications of the ACM
Technical Perspective: Power Efficiency as the #1 Design Constraint
Moore's Law, and associated observations by Bob Dennard, describe key technical...
From Communications of the ACM
Understanding Sources of Ineffciency in General-Purpose Chips
To better understand what improvement in processor efficiency is possible, we quantify the performance and energy overheads of a 720p HD H.264 encoder running on...
From Communications of the ACM
Technical Perspective: A Better Way to Learn Features
A typical machine learning program uses weighted combinations of features to discriminate between classes or to predict...
From Communications of the ACM
Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks (DBNs); however, scaling such models to full...
From Communications of the ACM
Technical Perspective: Visual Reconstruction
Nearly 460,000 Flickr pictures were used to create detailed three-dimensional geometry and colors of famous landmarks and...
From Communications of the ACM
Building Rome in a Day
We present a system that can reconstruct 3D geometry from large, unorganized collections of photographs. Our experimental results demonstrate that it is possible...
From Communications of the ACM
Self-Similarity-Based Image Denoising
The search for efficient image denoising methods is still a valid challenge at the crossing of functional analysis and statistics. In spite of the sophistication...
From Communications of the ACM
Technical Perspective: Images Everywhere Looking For Models
About 5,000 images per minute are uploaded to the photo-sharing site http://www.flickr.com/; over...
From Communications of the ACM
Technical Perspective: Complex Financial Products: Caveat Emptor
CDOs are examples of financial derivatives, with a value that depends on the underlying assets with which they are linked. These kinds of complex financial products...
From Communications of the ACM
Computational Complexity and Information Asymmetry in Financial Products
Securitization of cash flows using financial derivatives transformed the financial industry over the last three decades. Derivatives...
From Communications of the ACM
DRAM Errors in the Wild: A Large-Scale Field Study
While a large body of work exists on DRAM in lab conditions, little has been reported on real DRAM failures in large production clusters. In this paper, we analyze...
From Communications of the ACM
Technical Perspective: DRAM Errors in the Wild
In order to advance the field, knowledge of the types of memory errors at the system level, their frequencies, and conditions that exacerbate or are unrelated to...
From Communications of the ACM
The Sequence Memoizer
The sequence memoizer is a new hierarchical Bayesian model for discrete sequence data that captures long range dependencies and power-law characteristics, while...
From Communications of the ACM
Technical Perspective: Markov Meets Bayes
The history of probabilistic sequence models dates back to Markov at the turn of the last century. Though informed by decades of research...
From Communications of the ACM