Select a calendar:
Filter February Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for February
-
PhD Thesis Proposal - Hexiang Hu
Tue, Feb 16, 2021 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title of the Presentation:
Understanding Language in Perception and Embodiment
Committee: Fei Sha (Chair); Jay Kuo, Joseph Lim, Jesse Thomason, Robin Jia
Abstract:
Neural networks have made impressive progress in Natural Langauge Processing, which positively influenced many real-world tasks. Despite their success, language learners are often constrained as they are exposed only to the text world (from curated corpus or the internet). Consequently, language learners can not associate the learned distributional semantics with their appearance and affordance in the physical world. In this thesis proposal, I discuss approaches that learn to understand the language in the context of the visual dynamic world, which associate the hierarchical language expressions (such as word, phrase, sentence, and paragraph) with dynamic visual content (such as image and video). Moreover, I also discuss the future directions to understand the language in the embodied environment.
Link to the virtual meeting: https://usc.zoom.us/j/99351730951WebCast Link: https://usc.zoom.us/j/99351730951
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal - Victor Ardulov
Thu, Feb 25, 2021 @ 09:00 AM - 10:30 AM
Thomas Lord Department of Computer Science
University Calendar
Title: Control Theoretic Framework for Measuring, Modeling, and Regulating Human Interaction
Committee:
Shrikanth Narayanan (chair)
Fei Sha
Gale Lucas
David Traum
Tom D Lyon
abstract:
Human interaction is a vital component to a persons' development and well-being. These interactions enable us to over come obstacles and find resolutions that an individual might not be able to. This subject is particularly well studied in the domains of human psychology, where human behavior is diagnostically categorized and the interaction can be utilized in order to improve somebody's health.
Prior work has explored the use of computational models of human behavior to aide in the diagnostic assessment of behavioral patterns. Most recently, novel machine learning methods and access data has invited the to study the dynamics of human interaction on a more granular time-resolution. These dynamics have been used to identify specific moments during interactions that are relevant to the over all assessment of a individuals behavior with respect to their interlocutor. By reformulating this system from the perspective of an operator that can be controlled, it invites the possibility to predict how an individual would react to a specific input from their partner, which itself lends the opportunity to plan out interventions and probes more effectively.
This thesis proposal presents a formulation of human interaction as a control theoretic problem and demonstrates how these frameworks can be utilized to gain insight into improving desired outcomes. In support of the thesis, we will present the application of these techniques to the domain of child forensic interviewing.
Presentation on: February 25th 9 a.m. join via Zoom: https://usc.zoom.us/j/93374500380?pwd=ZHh6UDVXV0NTei9OS3h6TlZCeitDUT09
WebCast Link: https://usc.zoom.us/j/93374500380?pwd=ZHh6UDVXV0NTei9OS3h6TlZCeitDUT09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
