Select a calendar:
Filter December Events by Event Type:
Events for December 13, 2022
Tue, Dec 13, 2022 @ 09:00 AM - 11:00 PM
Thomas Lord Department of Computer Science
PhD Candidate: Wenxuan Zhou
Title: Relation Extraction: Models, Robustness, and Generalization
Chair: Muhao Chen
Committee members: Laurent Itti, Jonathan May, Tianshu Sun, Robin Jia
Abstract: With large amounts of digital text generated every day, it is important to extract structured knowledge automatically from the text. Relation extraction (RE), as one essential step of the solution, aims at identifying relationships among entities in a given piece of text. In this thesis proposal, I will present my work during my Ph.D. on RE from three perspectives: (1) designing effective RE models based on pretrained language models; (2) Improving the robustness of RE models, especially against entity bias; and (3) building data-efficient RE models in low-resource scenarios, which is important for real-world applications. After these, I will introduce my ongoing work and future directions for RE.
WebCast Link: : https://usc.zoom.us/j/6915039300
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
Tue, Dec 13, 2022 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Ye Tian, Postdoctoral Scholar, Ming Hsieh Dept of ECE, USC
Talk Title: Improved Cardiac MRI leveraging Spiral bSSFP at 0.55T
Abstract: Magnetic Resonance Imaging is a non-invasive, radiation-free medical imaging modality that can provide functional and structural assessments of the cardiovascular system. MRI has trended towards higher field strength and stronger gradient performance which has benefitted high-resolution static imaging of the nervous and musculoskeletal systems. It has not had the same revolutionary impact on imaging of the cardiovascular system, which is constantly in motion, and where image quality is dominated by artifact. Recently, there has been an increasing interest in low-field (< 1.5T) MRI configurations, which are expected to benefit dynamic MRI applications. Low-field systems provide lower susceptibility, lower acoustic noise, lower specific absorption rate, and favorably scaled relaxivities (lower T1 and longer T2/T2*), which open new opportunities.
In this talk, I will present several recent projects focused on improved cardiac MRI at 0.55T. I utilize a prototype whole-body 0.55T MRI (MAGNETOM Aera, Siemens Healthineers) at the Dynamic Imaging Science Center, and variations of spiral balanced steady-state free precession (bSSFP) pulse sequences to achieve imaging that is impossible or extremely difficult at traditional MRI field strengths. These applications include 1) contrast-optimal simultaneous multi-slice imaging of cardiac function, 2) fetal cardiac function and great vessel anatomy evaluation, and 3) dynamic T1-weighted imaging for myocardial perfusion assessment.
Biography: Ye Tian is currently a Postdoctoral Scholar at the University of Southern California and a 0.55T MRI physicist in the Dynamic Imaging Science Center (DISC), working with Professor Krishna Nayak. He completed his Ph.D. training at the University of Utah in September 2019. His research interests include real-time imaging, first-pass myocardial perfusion, simultaneous multi-slice imaging, and novel pulse sequences for cardiovascular assessment at 0.55T.
Host: Dr. Richard Leahy, email@example.com
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher