2026-09-19T16:10:07Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/120420 2023-09-05 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Gui, Liangyan 2023-05 application/pdf en text Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01 The student, Haomeng Zhang, accepted the attached license on 2023-04-25 at 16:09. The student, Haomeng Zhang, submitted this Thesis for approval on 2023-04-25 at 16:21. This Thesis was approved for publication on 2023-04-27 at 12:56. DSpace SAF Submission Ingestion Package generated from Vireo submission #19174 on 2023-09-01 at 17:14:55 Does the agent say what it sees: an analysis in 3D question answering Zhang, Haomeng 2023-04-27 Multi-modal Learning 3d Question Answering 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. Thesis eng https://hdl.handle.net/2142/120420 Copyright 2023 Haomeng Zhang M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science