News and Notes Archive
January, 16, 2020
ToMCAT. A collaboration between the Information School (INFO), Computer Science (CS), and Family Studies and Human Development (FSHD) has been awarded a large grant to develop a theory of mind-based cognitive architecture for teams (ToMCAT). The grant ($7.5M, for 48 months) is part of the DARPA Artificial Social Intelligence for Successful Teams (ASIST) program. The PI/Co-PIs collaborating on this project are: Adarsh Pyarelal (PI), Kobus Barnard, Emily Butler, Clayton Morrison, Rebecca Sharp, Mihai Surdeanu, and Marco Antonio Valenzuela-Escarcega. Data collection for the project will take place in the Lang Laboratory, housed in the Frances McClelland Institute for Children, Youth and Families in the Norton School of Family & Consumer Science.
The goal of the project is to build artificially intelligent agents that understand both the social and goal-oriented aspects of teams in mission-like scenarios (e.g., search-and-rescue missions), and are able to reason about possible interventions. The agent, ToMCAT, needs to model human players' affect and beliefs about the situation and about each other's affect and beliefs (theory of mind). We will ground this work in extensive measurements of humans interacting in small teams, that will include audio, video, eye tracking, electrocardiography (EKG), electroencephalography (EEG), functional near-infrared spectroscopy (fNIRS), and self report. The participants will execute missions within a Minecraft environment with one, two, three, or four human players interacting with the ToMCAT agent.
Research areas. One unique aspect of this project is that we will use simultaneous EEG and fNIRS brain recording from all human team members to further our understanding of social coordination in teams. We expect the series of experiments will provide a large amount of very unique data. ToMCAT's evolving theories of mind will be implemented using dynamic Bayesian networks interacting with latent low-level data representation provided by neural networks. In addition, we will need to understand dialogue as indicative of affect, plans, and mission goals. Finally, ToMCAT will need to both understand team plans and also create its own plans.
Further information is available on the project web site ml4ai.github.io/tomcat . This project started Nov 1, 2019. As we move forward, we will update this website regularly.
- August 2019
The IVILAB welcomes incoming PhD student Paulo Ricardo da Silva Soares.
- February 21, 2019
Congratulations to Jianbo Shao who successfully defended his dissertation on "Computational methods for improving fiber bundle imaging systems".
- August 2018
The IVILAB welcomes four incoming PhD students, Marina Kiseleva, Simon Swenson, Manujinda Wathugala, and Aryan Zarei.
- July 03, 2018
Congratulations to Ernesto Brau and Jinyan Guan, Tanya Jeffries, and Kobus Barnard for getting their paper "Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular video," accepted to ECCV 2018.
Modeling the world. A collaboration between CS, the information school (INFO), and Harvard Medical School has been awarded a grant to study inferring causal models for geopolitical events. The grant ($4.6M, for 36 months) is part of the DARPA world modelers program. The goal of the project is to build causal models for the evolution of geopolitical concepts such as food security in eastern Africa. These models are informed by text which are read using NLP, as well as available data for potentially relevant factors and effects such as food production, weather, war, and migration.
Further information about our Delphi software for building models from text and data is available at ml4ai.github.io/delphi .
- July 11, 2016
Congratulations to Kyle Simek for getting his paper "Branching Gaussian Processes with Applications to Spatiotemporal Reconstruction of 3D Trees," accepted to ECCV 2016. His coauthors are Ravishankar Palanivelu and Kobus Barnard.
- April 22, 2016
IVILAB lead, Kobus Barnard, has finally finished his book “Computational methods for integrating vision and language,” (Synthesis Lectures on Computer Vision, April 2016, 227 pages, Morgan & Claypool)
- April 19, 2016
Congratulations to four IVILAB students for successfully defending their dissertations in the period from April 14 to April 19. In chronological order:
Andrew Predoehl: A Statistical Model of Recreational Trails
Kyle Simek: Branching Gaussian Process Models for Computer Vision
Jinyan Guan: Bayesian Generative Modeling for Complex Dynamical Systems
Yekaterina Kharitonova: Geometry of Presentation Videos and slides, and the Semantic Linking of Instructional Content (SLIC) System
- Feb 20, 2016
IVILAB in the wildcat (UA student newspaper). Click here to see the article.
- Dec 1, 2015
[Now filled]. We are pleased to announce a PostDoc position for the Big Mechanism project. Please refer to the official UA job announcement linked here for details. If you are interested, please apply soon. We hope to make offers mid December.
- May 1, 2015
Congratulations to Jinyan Gaun for getting her paper "Moderated and Drifting Linear Dynamical Systems" accepted to ICML. Her coauthors are Kyle Simek, Ernesto Brau, Clay Morrison, Emily Butler, and Kobus Barnard.
- April 27, 2015
Congratulations to Warren Smith for his successful defense of his Masters thesis in statistics.
- November 8-9, 2014
The IVILAB CompTIES research group hosted a very successful workshop on computational social interaction. This was held at Biosphere 2 near Tucson Arizona. We are very thankful for NSF support for this workshop. For more information please visit the workshop webpage.
July 15, 2014
A collaboration between CS, SISTA, MCB, and CS at UIC has been awarded a grant to study inferring biological pathways relevant to cancer from academic articles. The grant ($3.6M, for 42 months) is part of the recently introduced Big Mechanism program (DARPA). From the Big Mechanism program web site: "Although the domain of the Big Mechanism program is cancer biology, the overarching goal of the program is to develop technologies for a new kind of science in which research is integrated more or less immediately---automatically or semi-automatically---into causal, explanatory models of unprecedented completeness and consistency. Cancer pathways are just one example of causal, explanatory models."
In this work we will develop methods to extract relations that form building blocks of pathways from cancer biology papers (the "reading" task), assembling what is read into pathways ("assembly task") under the constraint that the pathways are runnable, and visualize extracted pathways. In other words, we aim to extract big mechanism under the constraint that it has to be a machine. Challenges include that context (e.g., chemical environment) heavily influences pathway "execution", the many layers of abstraction that biologists need to describe what is going on, and many natural language processing difficulties. We expect to contribute to natural language processing, data science (specifically with respect to causality and explanation), and cancer bioinformatics.
- April, 17, 2014
Congratulations to Kyle Simek, for being selected as a Galileo Circle Scholar.
- April, 09, 2014
Congratulations to Yekaterina Kharitonova, for being selected for a very prestigious Generation Google Scholorship. From the scholarship website: "The Generation Google Scholarship was established to help aspiring computer scientists excel in technology and become leaders in the field. Selected students will receive 10,000 USD (for those studying in the US) or 5,000 CAD (for those studying in Canada) for the 2014-2015 school year." Way to go Kate!
- Friday, December 13, 2013
Congratulations to Ernesto Brau for successfully defending his dissertation entitled "Bayesian data association for temporal scene understanding".
- August 29, 2013
Congratulations to Ernesto Brau, Jinyan Guan, Kyle Simek, Luca del Pero, Colin Dawson, and Kobus Barnard, for getting their paper "Bayesian 3D tracking from monocular video" accepted to ICCV'13.
- August 2013
The Interdisciplinary Computational Intelligence (ICI) seminar for the 13/14 academic year officially starts August 30. It is being held Fridays at 1:30 in GS 906. Everyone is welcome to attend. This semester we will have a broad range of content, much of it generally accessible. For information about all upcoming and past seminars, including discussion and electronic prints, visit the seminar website. If you would like email announcements, please join the "compvision" listserv by clicking here.
- July 23, 2013
The interdisciplinary CompTIES (computational temporal interpersonal emotion systems) project has just been awarded a three year NSF grant. This is in collaboration between Emily Butler (PI, Family Studies and Human Development), Kobus Barnard (IVILAB / CS), Clay Morrison (IVILAB / SISTA), Matthias Mehl (Psychology), and the NSF funded iPlant project. This research will bring theory-driven Bayesian modeling and inference into the domain of temporal emotional interactions within personal relationships. It will also develop a shared computational infrastructure for researchers in this domain in collaboration with iPlant. For more details, see the project website compties.org, or the project abstract.
- July 2013
Congratulations to Luca Del Pero who is now officially "Doctor Del Pero," having successfully defended his dissertation in May, and who has now formally graduated with the PHD degree. Luca will be joining the University of Edinburgh as a Postdoc with Vitto Ferrari starting early October.
- April 18, 2013
Congratulations to Jinyan Guan, for being selected as a Galileo Circle Scholar.
- February 24, 2013
Congratulations to Andrew Predoehl and Kobus Barnard for getting their paper, "A Statistical Model for Recreational Trails in Aerial Images" accepted to CVPR'13.
- February 24, 2013
Congratulations to Luca Del Pero Kobus Barnard and undergraduates Joshua Bowdish, Emily Hartley, and Bonnie Kermgard for getting their paper, "Understanding Bayesian rooms using composite 3D object models" accepted to CVPR'13.
- July 31, 2012
Congratulations to PHD students Yekaterina (Kate) Kharitonova, Qiyam Tung, Kobus Barnard, and undergraduate Alexander Danehy for getting their paper, "Client-side backprojection of presentation slides into educational video," accepted to ACM MM'12.
- March 5, 2012
Congratulations to Luca Del Pero, Yekaterina (Kate) Kharitonova, and Colin Dawson for being selected as Galileo Circle Scholars. More on the six Galileo Circle recipients associated with SISTA.
- February 26, 2012
Congratulations to Luca Del Pero, Kobus Barnard, and undergraduates Joshua Bowdish, Daniel Fried, Bonnie Kermgard, and Emily Hartley for getting their paper, "Bayesian geometric modeling of indoor scenes," accepted to CVPR'12.
- January 1, 2012
Bayesian Modeling and Inference course for spring 2012
- Spring 2011
New course for spring 2011 : Bayesian modeling and inference
- March 2010
First year PHD student Jinyan Guan has won a prestigious Microsoft Research Graduate Woman's Scholarship. Jinyan will be receiving one of ten such scholarships awarded across North America. In 2010 there were 109 applicants.
Jinyan is interested in computer vision, and how it related to human vision, especially with respect to representing, understanding, and recognizing 3D objects. She is part of the computer vision group, led by Kobus Barnard.