{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/113820"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/113820","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning efficient temporal information in deep networks: From the viewpoints of applications and modeling","abstract":"The student, Cu Khoi-Nguyen Mac, submitted this Dissertation for approval on 2021-10-12 at 16:21.","abstract_html":"The student, Cu Khoi-Nguyen Mac, submitted this Dissertation for approval on 2021-10-12 at 16:21.","abstract_has_math":false,"creators":["Mac, Cu Khoi-Nguyen"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Do, Minh N","Forsyth, David A","Hasegawa-Johnson, Mark A","Schwing, Alexander G","Gupta, Saurabh"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-04-29T21:34:08Z","date_published":"2022-04-29T21:34:08Z","updated_at":"2026-07-22T22:24:53Z","subjects":["Engineering"],"languages":["en","eng"],"rights":["Copyright 2021 Cu Khoi Nguyen Mac"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/113820","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Do, Minh N","Forsyth, David A","Hasegawa-Johnson, Mark A","Schwing, Alexander G","Gupta, Saurabh"]},{"key":"dc:creator","label":"Author","values":["Mac, Cu Khoi-Nguyen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-04-29T21:34:08Z","2021-12","2021-10-13"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Cu Khoi Nguyen Mac"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/113820"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The student, Cu Khoi-Nguyen Mac, submitted this Dissertation for approval on 2021-10-12 at 16:21.","This Dissertation was approved for publication on 2021-10-13 at 14:43.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17158 on 2022-04-06 at 17:08:52","Made available in DSpace on 2022-04-29T21:34:08Z (GMT). No. of bitstreams: 2 MAC-DISSERTATION-2021.pdf: 13433948 bytes, checksum: 6574998763e0b38957a43b208c102249 (MD5) LICENSE.txt: 4212 bytes, checksum: 85b1f3ab20175c99b2ba1de678416498 (MD5) Previous issue date: 2021-10-13","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms","The student, Cu Khoi-Nguyen Mac, accepted the attached license on 2021-10-12 at 16:02.","With the introduction of deep learning, machine learning has dominated several technology areas, giving birth to high-performance applications that can even challenge human-level accuracy. However, the complexity of deep models is also exploding as a by-product of the revolution of machine learning. Such enormous model complexity has raised the new challenge of improving the efficiency in deep models to reduce deployment expense, especially for systems with high throughput demands or devices with limited power. The dissertation aims to improve the efficiency of temporal-sensitive deep models in four different directions. First, we develop a bandwidth extension mapping to avoid deploying multiple speech recognition systems corresponding to wideband and narrowband signals. Second, we apply a multi-modality approach to compensate for the performance of an excitement scoring system, where the input video sequences are aggressively down-sampled to reduce throughput. Third, we formulate the motion feature in the feature space by directly inducing the temporal information from intermediate layers of deep networks instead of relying on an additional optical flow stream. Finally, we model a spatiotemporal sampling network inspired by the human visual perception mechanism to reduce input frames and regions adaptively."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Learning efficient temporal information in deep networks: From the viewpoints of applications and modeling"]}]}],"canonical_facts":{"dc:contributor":["Do, Minh N","Forsyth, David A","Hasegawa-Johnson, Mark A","Schwing, Alexander G","Gupta, Saurabh"],"dc:creator":["Mac, Cu Khoi-Nguyen"],"dc:date":["2022-04-29T21:34:08Z","2021-12","2021-10-13"],"dc:description":["The student, Cu Khoi-Nguyen Mac, submitted this Dissertation for approval on 2021-10-12 at 16:21.","This Dissertation was approved for publication on 2021-10-13 at 14:43.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17158 on 2022-04-06 at 17:08:52","Made available in DSpace on 2022-04-29T21:34:08Z (GMT). No. of bitstreams: 2 MAC-DISSERTATION-2021.pdf: 13433948 bytes, checksum: 6574998763e0b38957a43b208c102249 (MD5) LICENSE.txt: 4212 bytes, checksum: 85b1f3ab20175c99b2ba1de678416498 (MD5) Previous issue date: 2021-10-13","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms","The student, Cu Khoi-Nguyen Mac, accepted the attached license on 2021-10-12 at 16:02.","With the introduction of deep learning, machine learning has dominated several technology areas, giving birth to high-performance applications that can even challenge human-level accuracy. However, the complexity of deep models is also exploding as a by-product of the revolution of machine learning. Such enormous model complexity has raised the new challenge of improving the efficiency in deep models to reduce deployment expense, especially for systems with high throughput demands or devices with limited power. The dissertation aims to improve the efficiency of temporal-sensitive deep models in four different directions. First, we develop a bandwidth extension mapping to avoid deploying multiple speech recognition systems corresponding to wideband and narrowband signals. Second, we apply a multi-modality approach to compensate for the performance of an excitement scoring system, where the input video sequences are aggressively down-sampled to reduce throughput. Third, we formulate the motion feature in the feature space by directly inducing the temporal information from intermediate layers of deep networks instead of relying on an additional optical flow stream. Finally, we model a spatiotemporal sampling network inspired by the human visual perception mechanism to reduce input frames and regions adaptively."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/113820"],"dc:language":["en","eng"],"dc:rights":["Copyright 2021 Cu Khoi Nguyen Mac"],"dc:subject":["Engineering"],"dc:title":["Learning efficient temporal information in deep networks: From the viewpoints of applications and modeling"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:53Z"}