Portrait of Jason Corso, Assistant Professor of Computer Science and Engineering, inside his lab

Photographer: Douglas Levere

Jason Corso

By | | No Comments

The Corso group’s main research thrust is high-level computer vision and its relationship to human language, robotics and data science. They primarily focus on problems in video understanding such as video segmentation, activity recognition, and video-to-text; methodology, models leveraging cross-model cues to learn structured embeddings from large-scale data sources as well as graphical models emphasizing structured prediction over large-scale data sources are their emphasis. From biomedicine to recreational video, imaging data is ubiquitous. Yet, imaging scientists and intelligence analysts are without an adequate language and set of tools to fully tap the information-rich image and video. His group works to provide such a language.  His long-term goal is a comprehensive and robust methodology of automatically mining, quantifying, and generalizing information in large sets of projective and volumetric images and video to facilitate intelligent computational and robotic agents that can natural interact with humans and within the natural world.

Relating visual content to natural language requires models at multiple scales and emphases; here we model low-level visual content, high-level ontological information, and these two are glued together with an adaptive graphical structure at the mid-level.

Relating visual content to natural language requires models at multiple scales and emphases; here we model low-level visual content, high-level ontological information, and these two are glued together with an adaptive graphical structure at the mid-level.

ortiz-small

Luis E. Ortiz

By | | No Comments

The study of large complex systems of structured strategic interaction, such as economic, social, biological, financial, or large computer networks, provides substantial opportunities for fundamental computational and scientific contributions. My research focuses on problems emerging from the study of systems involving the interaction of a large number of “entities,” which is my way of abstractly and generally capturing individuals, institutions, corporations, biological organisms, or even the individual chemical components of which they are made (e.g., proteins and DNA). Current technology has facilitated the collection and public availability of vasts amounts of data, particularly capturing system behavior at fine levels of granularity. In my group, we study behavioral data of strategic nature at big data levels. One of our main objectives is to develop computational tools for data science, and in particular learning large-population models from such big sources of behavioral data that we can later use to study, analyze, predict and alter future system behavior at a variety of scales, and thus improve the overall efficiency of real-world complex systems (e.g., the smart grid, social and political networks, independent security and defense systems, and microfinance markets, to name a few).

levina-small

Liza Levina

By | | No Comments

Liza Levina and her group work on various questions arising in the statistical analysis of large and complex data, especially networks and graphs. Our current focus is on developing rigorous and computationally efficient statistical inference on realistic models for networks. Current directions include community detection problems in networks (overlapping communities, networks with additional information about the nodes and edges, estimating the number of communities), link prediction (networks with missing or noisy links, networks evolving over time), prediction with data connected by a network (e.g., the role of friendship networks in the spread of risky behaviors among teenagers), and statistical analysis of samples of networks with applications to brain imaging, especially fMRI data from studies of mental health).

honglak_lee-small

Honglak Lee

By | | No Comments

Dr. Lee’s research interests lie in machine learning and its applications to artificial intelligence. In particular, he focuses on deep learning and representation learning, which aims to learn an abstract representation of the data by a hierarchical and compositional structure. His research also spans over related topics, such as graphical models, optimization, and large-scale learning. Specific application areas include computer vision, audio recognition, robotics, text modeling, and healthcare.

balzano-small

Laura Balzano

By | | No Comments

Professor Balzano and her students investigate problems in statistical signal processing and optimization, particularly dealing with large and messy data. Her applications typically have missing, corrupted, and uncalibrated data as well as heterogeneous data in terms of sensors, sensor quality, and scale in both time and space. Her theoretical interests involve classes of non-convex problems that include Principal Components Analysis (or the Singular Value Decomposition) and many interesting variants such as PCA with sparse or structured principal components, orthogonality and non-negativity constraints, and even categorical data or human preference data. She concentrates on fast gradient methods and related optimization methods that are scalable to real-time operation and massive data. Her work provides algorithmic and statistical guarantees for these algorithms on the aforementioned non-convex problems, and she focuses carefully on assumptions that are realistic for the relevant applications. She has worked in the areas of online algorithms, real-time computer vision, compressed sensing and matrix completion, network inference, and sensor networks.

Real-time dynamic background tracking and foreground separation. At time t = 101, the virtual camera slightly pans to right 20 pixels. We show how GRASTA quickly adapts to the new subspace by t = 125. The first row is the original video frame; the middle row is the tracked background; the bottom row is the separated foreground.

Real-time dynamic background tracking and foreground separation. At time t = 101, the virtual camera slightly pans to right 20 pixels. We show how GRASTA quickly adapts to the new subspace by t = 125. The first row is the original video frame; the middle row is the tracked background; the bottom row is the separated foreground.