2026-09-23T00:50:15Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/110702 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Schwing, Alexander G Schwing, Alexander G Hasegawa-Johnson, Mark Do, Minh N Forsyth, David Yeh, Raymond A 2021-09-17T02:34:38Z 2021-09-17T02:34:38Z 2023-09-17T02:34:57Z 2021-04-21 2021-05 In this work, we study models which explicitly capture and learn structures from data. For the task of supervised and unsupervised textual grounding, we propose a unified framework which links words to image concepts. A parameter between each word and image concept is learned and the learned parameters are easily interpretable. Next, for the task of generative modeling of multi-agent trajectories, we design models which share parameters based on the relationship between agents in the system to achieve permutation equivariance. This representation is particularly suitable in a multi-agent setting where the identity of the agents is unknown. We achieve better performance than conventional fully connected deep nets. Lastly, we present a framework on how to learn equivariance properties from data; this framework is based on learning how to share parameters in a model. We provide analysis on Gaussian vectors in terms on mean squared error criterion and empirically show that our approach can recover shift and permutation equivariances. Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-05-01 The student, Raymond Yeh, accepted the attached license on 2021-04-19 at 20:56. The student, Raymond Yeh, submitted this Dissertation for approval on 2021-04-19 at 21:08. This Dissertation was approved for publication on 2021-04-21 at 13:45. DSpace SAF Submission Ingestion Package generated from Vireo submission #16432 on 2021-09-16 at 17:04:03 Made available in DSpace on 2021-09-17T02:34:38Z (GMT). No. of bitstreams: 2 YEH-DISSERTATION-2021.pdf: 15431474 bytes, checksum: d271456ac1cb85a7f87549186098b914 (MD5) LICENSE.txt: 4208 bytes, checksum: 608b27144ec36d500db761844ed0482a (MD5) Previous issue date: 2021-04-21 Embargo set by: Seth Robbins for item 118545 Lift date: 2023-09-17T02:34:57Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system U of I Only application/pdf http://hdl.handle.net/2142/110702 en Copyright 2021 Raymond Yeh machine learning computer vision Extracting and learning structures from data text Thesis Electrical & Computer Eng Electrical & Computer Engr University of Illinois at Urbana-Champaign Dissertation Ph.D.