{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/14276"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/14276","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Action Labeling in Images and Video","abstract":"Deep learning models that attempt to categorize visual content can benefit from being trained with additional information that may be, or may not be, available during deployment. To this end, this dissertation designed, developed, and evaluated methods inspired by the "Learning Using Privileged Information" framework, multimodal data fusion, and knowledge distillation to improve deep learning models' performance. These methods are assessed for the problems of: (i) recognizing carrying actions in "visible spectrum" and "near-infrared" images, as well as (ii) detecting questionable online video content. The experimental results demonstrated the effectiveness of the methods in four new datasets introduced within the context of this work to address the challenges of the problems mentioned above.","abstract_html":"Deep learning models that attempt to categorize visual content can benefit from being trained with additional information that may be, or may not be, available during deployment. To this end, this dissertation designed, developed, and evaluated methods inspired by the "Learning Using Privileged Information" framework, multimodal data fusion, and knowledge distillation to improve deep learning models' performance. These methods are assessed for the problems of: (i) recognizing carrying actions in "visible spectrum" and "near-infrared" images, as well as (ii) detecting questionable online video content. The experimental results demonstrated the effectiveness of the methods in four new datasets introduced within the context of this work to address the challenges of the problems mentioned above.","abstract_has_math":false,"creators":["Smailis, Christos"],"institution":"University of Houston","degree_name":"Doctor of Philosophy","degree_level":"Doctoral","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Kakadiaris, Ioannis A."],"committee_chairs":[],"committee_members":["Paliouras, George","Solorio, Thamar","Huang, Stephen"],"year":2022,"date_issued":"2022-05-11","date_published":"2022-05-11","updated_at":"2026-07-24T02:32:27Z","subjects":["Deep learning","LUPI","Multimodal data fusion","Knowledge distillation"],"languages":["eng"],"rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. UH Libraries has secured permission to reproduce any and all previously published materials contained in the work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/14276","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kakadiaris, Ioannis A."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Paliouras, George","Solorio, Thamar","Huang, Stephen"]},{"key":"dc:creator","label":"Author","values":["Smailis, Christos"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-05-26T15:55:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05-11"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep learning","LUPI","Multimodal data fusion","Knowledge distillation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. UH Libraries has secured permission to reproduce any and all previously published materials contained in the work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/14276"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Deep learning models that attempt to categorize visual content can benefit from being trained with additional information that may be, or may not be, available during deployment. To this end, this dissertation designed, developed, and evaluated methods inspired by the "Learning Using Privileged Information" framework, multimodal data fusion, and knowledge distillation to improve deep learning models' performance. These methods are assessed for the problems of: (i) recognizing carrying actions in "visible spectrum" and "near-infrared" images, as well as (ii) detecting questionable online video content. The experimental results demonstrated the effectiveness of the methods in four new datasets introduced within the context of this work to address the challenges of the problems mentioned above."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Action Labeling in Images and Video"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kakadiaris, Ioannis A."],"dc:contributor.committeemember":["Paliouras, George","Solorio, Thamar","Huang, Stephen"],"dc:creator":["Smailis, Christos"],"dc:date.accessioned":["2023-05-26T15:55:35Z"],"dc:date.issued":["2022-05-11"],"dc:description.abstract":["Deep learning models that attempt to categorize visual content can benefit from being trained with additional information that may be, or may not be, available during deployment. To this end, this dissertation designed, developed, and evaluated methods inspired by the "Learning Using Privileged Information" framework, multimodal data fusion, and knowledge distillation to improve deep learning models' performance. These methods are assessed for the problems of: (i) recognizing carrying actions in "visible spectrum" and "near-infrared" images, as well as (ii) detecting questionable online video content. The experimental results demonstrated the effectiveness of the methods in four new datasets introduced within the context of this work to address the challenges of the problems mentioned above."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/14276"],"dc:language.iso":["eng"],"dc:rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. UH Libraries has secured permission to reproduce any and all previously published materials contained in the work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"dc:subject":["Deep learning","LUPI","Multimodal data fusion","Knowledge distillation"],"dc:title":["Action Labeling in Images and Video"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:32:27Z"}