In "Learning to Name Objects," the authors offer a method to determine a basic-level category name for an object in an image.David Forsyth From Communications of the ACM | March 2016
This paper looks at the problem of predicting category labels that mimic how human observers would name objects.Vicente Ordonez, Wei Liu, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg From Communications of the ACM | March 2016
An important contribution of "Answering Enumeration Queries with the Crowd" is the observation that by using the crowd for the collection of new data, we are departing...Tova Milo From Communications of the ACM | January 2016
Hybrid human/computer database systems promise to greatly expand the usefulness of query processing by incorporating the crowd. Such systems raise many implementation...Beth Trushkowsky, Tim Kraska, Michael J. Franklin, Purnamrita Sarkar From Communications of the ACM | January 2016
Can a computer automatically discover and tell us what makes Paris look so much like Paris? "What Makes Paris Look Like Paris?" offers a creative, inspiring new...Noah Snavely From Communications of the ACM | December 2015
Given a large repository of geo-tagged imagery, we seek to automatically find visual elements, for example windows, balconies, and street signs, that are most distinctive...Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros From Communications of the ACM | December 2015
"Geometric Tools for Exploring Manifolds of Light Transport Paths" presents a technique to address the challenging problems of light transport.Frédo Durand From Communications of the ACM | November 2015
We provide a geometric solution to the longstanding problem of light simulations by representing light paths as points in an abstract high-dimensional configuration...Wenzel Jakob, Steve Marschner From Communications of the ACM | November 2015
The authors of "Guided Exploration of Physically Valid Shapes for Furniture Design" have found a way to provide the user with instant feedback on how to fix unstable...Marc Alexa From Communications of the ACM | September 2015
The authors propose an interactive design framework for the efficient and intuitive exploration of geometrically and physically valid shapes.Nobuyuki Umentani, Takeo Igarashi, Niloy J. Mitra From Communications of the ACM | September 2015
Specialization improves energy-efficiency in computing but only makes economic sense if there is significant demand. A balance can often be found by designing...Trevor Mudge From Communications of the ACM | April 2015
We present the Convolution Engine (CE) — a programmable processor specialized for the convolution-like data-flow prevalent in computational photography, computer...Wajahat Qadeer, Rehan Hameed, Ofer Shacham, Preethi Venkatesan, Christos Kozyrakis, Mark Horowitz From Communications of the ACM | April 2015
In "Local Laplacian Filters," Paris et al. made a surprising move. They chose to build a system on the Laplacian pyramid, which is a very simple multiscale representation...Edward Adelson From Communications of the ACM | March 2015
In this paper, we demonstrate that state-of-the-art edge-aware filters can be achieved with standard Laplacian pyramids.Sylvain Paris, Samuel W. Hasinoff, Jan Kautz From Communications of the ACM | March 2015
"Neural Acceleration for General-Purpose Approximate Programs" demonstrates the significant advantages in cost, power, and latency through approximate computing...Ravi Nair From Communications of the ACM | January 2015
This paper describes a new approach that uses machine learning-based transformations to accelerate approximation-tolerant programs.Hadi Esmaeilzadeh, Adrian Sampson, Luis Ceze, Doug Burger From Communications of the ACM | January 2015
For years, graphics programs have simulated fabric as a collection of fibers, requiring tweaks to algorithms for each new fabric. "Building Volumetric Appearance...Szymon Rusinkiewicz From Communications of the ACM | November 2014
Visualizing and rendering cloth has been an important area of graphics research for decades. This paper proposes a new approach to acquiring volume models, based...Shuang Zhao, Wenzel Jakob, Steve Marschner, Kavita Bala From Communications of the ACM | November 2014
"Dissection: A New Paradigm for Solving Bicomposite Search Problems," by Itai Dinur, Orr Dunkelman, Nathan Keller, and Adi Shamir, presents an elegant new algorithm...Bart Preneel From Communications of the ACM | October 2014
In this paper, we introduce the new notion of bicomposite search problems, and show that they can be solved with improved combinations of time and space complexities...Itai Dinur, Orr Dunkelman, Nathan Keller, Adi Shamir From Communications of the ACM | October 2014