The Department of Computer Science has a distinguished track record of academic excellence and major achievement in an increasingly vital field that is expanding at a rapid pace. Faculty research is published in the most prominent venues and recognized by significant citations and awards, both national and international. BA, MS, and PhD students are recruited for internships and positions by such industry-leading firms as Motorola Labs, Google, and Microsoft, and are also recruited as PhD students, postdoctoral researchers, and tenure-track professors by some of the best computer science departments in the country.
Department chair: Mark Crovella
Campus address: 111 Cummington Mall, Room 138
All materials in OpenBU are subject to Title 17 of the U.S. Code.
Collections in this community
(2017)First-order methods play a central role in large-scale machine learning. Even though many variations exist, each suited to a particular problem, almost all such methods fundamentally rely on two types of algorithmic steps: ...
(2017)Image and video analysis is often a crucial step in the study of animal behavior and kinematics. Often these analyses require that the position of one or more animal landmarks are annotated (marked) in numerous images. The ...
(2016-05-01)We demonstrate the usefulness of surroundedness for eye fixation prediction by proposing a Boolean Map based Saliency model (BMS). In our formulation, an image is characterized by a set of binary images, which are generated ...
Do less and achieve more: Training CNNs for action recognition utilizing action images from the Web (2017-08)Recently, attempts have been made to collect millions of videos to train Convolutional Neural Network (CNN) models for action recognition in videos. However, curating such large-scale video datasets requires immense human ...
(2016-01-01)Multidimensional scaling (MDS) is a class of projective algorithms traditionally used in Euclidean space to produce twoor three-dimensional visualizations of datasets of multidimensional points or point distances. More ...
(SPRINGER, 2017-09-01)We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately ...
(Springer International Publishing, 2016)We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation ...
(2016)We aim at detecting salient objects in unconstrained images. In unconstrained images, the number of salient objects (if any) varies from image to image, and is not given. We present a salient object detection system that ...
(IEEE, 2017-01-01)Building robust classifiers trained on data susceptible to group or subject-specific variations is a challenging pattern recognition problem. We develop hierarchical Bayesian neural networks to capture subject-specific ...