Abstract: The visual world is vast and varied, so learning is needed to reliably recognize what is where in images. In this talk, I will show how to reconcile learning with visual structure, to make the most of the data...
Abstract: The visual world is vast and varied, so learning is needed to reliably recognize what is where in images. In this talk, I will show how to reconcile learning with visual structure, to make the most of the data...
The Office of Diversity and Inclusive Community Development invites you to attend this powerful panel of women discussing their experiences in STEM. This event will provide participants with insight and best practices...
Title: Trust and Bias: Guiding Communication through Data Visualizations
Abstract: In this talk, I will demonstrate the practical application and the cognitive perception of data visualization in communication...
Unfortunately, the Office of Career Development & Professional Connections had to cancel the rescheduled Day 2 of the Career Blast. We encourage you to attend the In-Person Engineering Career Fair on Wednesday, March...
This panel is co-organized by the Computational Social Science Institute (CSSI), Institute for Social Science Research (ISSR), and Public Interest Technology Initiative (PIT @ UMass).
In a few short months, many...
Abstract: Policy gradient methods are a class of reinforcement learning algorithms that optimize a parametric policy by maximizing an objective function which directly measures the performance of the policy. Despite being...
Title: Robust Visual Understanding with Limited Supervision
Abstract: Over the past few years, a wide range of computer vision and natural language understanding models have been proposed for various perception...