Does the agent say what it sees: an analysis in 3D question answering
Zhang, Haomeng
Loading…
Permalink
https://hdl.handle.net/2142/120420
Description
Title
Does the agent say what it sees: an analysis in 3D question answering
Author(s)
Zhang, Haomeng
Issue Date
2023-04-27
Director of Research (if dissertation) or Advisor (if thesis)
Gui, Liangyan
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
Multi-modal Learning
3D Question Answering
Abstract
The emerging research topic of 3D Question and Answering involves complex challenges such as semantic language understanding, 3D scene comprehension, and establishing correspondence between language and target objects. In this thesis, I conduct a comprehensive analysis on the state-of-the-art 3D Question Answering benchmark model, ScanQA, by comparing the effectiveness of various auxiliary tasks, identifying limitations in current evaluation methods, and conducting additional ablation studies on the visual component. The findings and potential future directions for the 3D Question Answering task are discussed to assist researchers in their ongoing investigations.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.