2026-09-22T11:18:25Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/100977 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Lazebnik, Svetlana Lazebnik, Svetlana Hockenmaier, Julia Hoiem, Derek Brown, Matthew Plummer, Bryan A. 2018-09-04T20:27:05Z 2018-09-04T20:27:05Z 2018-04-16 2018-05 Grounding language in images has shown it can help improve performance on many image-language tasks. To spur research on this topic, this dissertation introduces a new dataset which provides the ground truth annotations of the location of noun phrase chunks in image captions. I begin by introducing a constituent task termed phrase localization, where the goal is to localize an entity known to exist in an image when provided with a natural language query. To address this task, I introduce a model which learns a set of models, each of which capture a different concept which is useful in our task. These concepts can be predefined, such as attributes gleamed from the adjectives, as well as those which are automatically learned in a single-end-to-end neural network. I also address the more challenging detection style task, where the goal is to localize a phrase and determine if it is associated with an image. Multiple applications of the models presented in this work demonstrate their value beyond the phrase localization task. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms The student, Bryan Plummer, accepted the attached license on 2018-04-14 at 05:42. The student, Bryan Plummer, submitted this Dissertation for approval on 2018-04-14 at 05:57. This Dissertation was approved for publication on 2018-04-16 at 11:21. DSpace SAF Submission Ingestion Package generated from Vireo submission #12248 on 2018-08-31 at 17:12:23 Made available in DSpace on 2018-09-04T20:27:05Z (GMT). No. of bitstreams: 3 PLUMMER-DISSERTATION-2018.pdf: 9214167 bytes, checksum: 7c4ec584f104360a0a99ea9a290b5a09 (MD5) grounding-natural-language.zip: 8908155 bytes, checksum: 79b1f7c90322e047fc2559c7486ab3c1 (MD5) LICENSE.txt: 4210 bytes, checksum: 398aac9d4dcb281c202797929dc1603f (MD5) Previous issue date: 2018-04-16 application/pdf http://hdl.handle.net/2142/100977 en Copyright 2018 Bryan A. Plummer Computer Vision, Natural Language Processing, Phrase Grounding Grounding natural language phrases in images and video text text Computer Science Computer Science University of Illinois at Urbana-Champaign Dissertation Ph.D.