{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/99513"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/99513","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Deep learning in sequential data analysis","abstract":"Deep learning has achieved great success in recent years in computer vision and its related areas. For core computer vision tasks such as image classification, image semantic segmentation, image super-resolution, and object detection from images, deep learning based methods outperform various traditional methods in terms of both accuracy and speed. While a myriad of deep learning based computer vision research projects are continuously pushing forward the frontier of computer vision further by improving the performance for image-level tasks, many recent investigations have begun to look into deep learning based methods for sequential data such as videos and medical image sequences. With the extra information from its additional sequential dimension, sequential data naturally raises an important and challenging question: How can we effectively and efficiently integrate such sequential information into existing successful and sophisticated image-based deep learning frameworks without building from scratch? In this dissertation we develop techniques and methods that enable us to incorporate sequential information into existing image-based deep learning frameworks for different computer vision tasks. More specifically, we propose advanced methods that successfully utilize both image-based deep learning models and sequential information for the super-resolution task using multi-slice computed tomography image sequences, and for the object detection and tracking task using multi-frame videos. We demonstrate how we integrate sequential information into modern image-based deep learning systems for these different tasks under different integration paradigms. Our experiments show that our proposed methods have significantly improved the performances compared with naive image-based methods, and achieved the new state-of-the-art for such sequential vision tasks.","abstract_html":"Deep learning has achieved great success in recent years in computer vision and its related areas. For core computer vision tasks such as image classification, image semantic segmentation, image super-resolution, and object detection from images, deep learning based methods outperform various traditional methods in terms of both accuracy and speed. While a myriad of deep learning based computer vision research projects are continuously pushing forward the frontier of computer vision further by improving the performance for image-level tasks, many recent investigations have begun to look into deep learning based methods for sequential data such as videos and medical image sequences. With the extra information from its additional sequential dimension, sequential data naturally raises an important and challenging question: How can we effectively and efficiently integrate such sequential information into existing successful and sophisticated image-based deep learning frameworks without building from scratch? In this dissertation we develop techniques and methods that enable us to incorporate sequential information into existing image-based deep learning frameworks for different computer vision tasks. More specifically, we propose advanced methods that successfully utilize both image-based deep learning models and sequential information for the super-resolution task using multi-slice computed tomography image sequences, and for the object detection and tracking task using multi-frame videos. We demonstrate how we integrate sequential information into modern image-based deep learning systems for these different tasks under different integration paradigms. Our experiments show that our proposed methods have significantly improved the performances compared with naive image-based methods, and achieved the new state-of-the-art for such sequential vision tasks.","abstract_has_math":false,"creators":["Shi, Honghui"],"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":["Huang, Thomas S.","Liang, Zhi-Pei","Hasegawa-Johnson, Mark","Yan, Shuicheng"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-03-13T17:35:49Z","date_published":"2018-03-13T17:35:49Z","updated_at":"2026-07-22T22:24:37Z","subjects":["Deep learning","Sequential data analysis","Visual recognition","Video object detection","Video object tracking"],"languages":["en"],"rights":["Copyright 2017 Honghui Shi"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/99513","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas S.","Liang, Zhi-Pei","Hasegawa-Johnson, Mark","Yan, Shuicheng"]},{"key":"dc:creator","label":"Author","values":["Shi, Honghui"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-03-13T17:35:49Z","2020-03-14T09:15:28Z","2017-12-05","2017-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"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":["Deep learning","Sequential data analysis","Visual recognition","Video object detection","Video object tracking"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2017 Honghui Shi"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/99513"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Deep learning has achieved great success in recent years in computer vision and its related areas. For core computer vision tasks such as image classification, image semantic segmentation, image super-resolution, and object detection from images, deep learning based methods outperform various traditional methods in terms of both accuracy and speed. While a myriad of deep learning based computer vision research projects are continuously pushing forward the frontier of computer vision further by improving the performance for image-level tasks, many recent investigations have begun to look into deep learning based methods for sequential data such as videos and medical image sequences. With the extra information from its additional sequential dimension, sequential data naturally raises an important and challenging question: How can we effectively and efficiently integrate such sequential information into existing successful and sophisticated image-based deep learning frameworks without building from scratch? In this dissertation we develop techniques and methods that enable us to incorporate sequential information into existing image-based deep learning frameworks for different computer vision tasks. More specifically, we propose advanced methods that successfully utilize both image-based deep learning models and sequential information for the super-resolution task using multi-slice computed tomography image sequences, and for the object detection and tracking task using multi-frame videos. We demonstrate how we integrate sequential information into modern image-based deep learning systems for these different tasks under different integration paradigms. Our experiments show that our proposed methods have significantly improved the performances compared with naive image-based methods, and achieved the new state-of-the-art for such sequential vision tasks.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2019-12-01","The student, Honghui Shi, accepted the attached license on 2017-12-05 at 09:43.","The student, Honghui Shi, submitted this Dissertation for approval on 2017-12-05 at 09:48.","This Dissertation was approved for publication on 2017-12-05 at 11:50.","DSpace SAF Submission Ingestion Package generated from Vireo submission #11851 on 2018-03-13 at 10:37:39","Made available in DSpace on 2018-03-13T17:35:49Z (GMT). No. of bitstreams: 2 SHI-DISSERTATION-2017.pdf: 8966931 bytes, checksum: f7ebaa0ce2ebb11664a08f629fe9bd99 (MD5) LICENSE.txt: 4208 bytes, checksum: d265a58770ecddde50f98f0b083e23db (MD5) Previous issue date: 2017-12-05","Embargo set by: Seth Robbins for item 105482 Lift date: 2020-03-13T17:36:05Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 105482 on 2020-03-14T09:15:28Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep learning in sequential data analysis"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas S.","Liang, Zhi-Pei","Hasegawa-Johnson, Mark","Yan, Shuicheng"],"dc:creator":["Shi, Honghui"],"dc:date":["2018-03-13T17:35:49Z","2020-03-14T09:15:28Z","2017-12-05","2017-12"],"dc:description":["Deep learning has achieved great success in recent years in computer vision and its related areas. For core computer vision tasks such as image classification, image semantic segmentation, image super-resolution, and object detection from images, deep learning based methods outperform various traditional methods in terms of both accuracy and speed. While a myriad of deep learning based computer vision research projects are continuously pushing forward the frontier of computer vision further by improving the performance for image-level tasks, many recent investigations have begun to look into deep learning based methods for sequential data such as videos and medical image sequences. With the extra information from its additional sequential dimension, sequential data naturally raises an important and challenging question: How can we effectively and efficiently integrate such sequential information into existing successful and sophisticated image-based deep learning frameworks without building from scratch? In this dissertation we develop techniques and methods that enable us to incorporate sequential information into existing image-based deep learning frameworks for different computer vision tasks. More specifically, we propose advanced methods that successfully utilize both image-based deep learning models and sequential information for the super-resolution task using multi-slice computed tomography image sequences, and for the object detection and tracking task using multi-frame videos. We demonstrate how we integrate sequential information into modern image-based deep learning systems for these different tasks under different integration paradigms. Our experiments show that our proposed methods have significantly improved the performances compared with naive image-based methods, and achieved the new state-of-the-art for such sequential vision tasks.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2019-12-01","The student, Honghui Shi, accepted the attached license on 2017-12-05 at 09:43.","The student, Honghui Shi, submitted this Dissertation for approval on 2017-12-05 at 09:48.","This Dissertation was approved for publication on 2017-12-05 at 11:50.","DSpace SAF Submission Ingestion Package generated from Vireo submission #11851 on 2018-03-13 at 10:37:39","Made available in DSpace on 2018-03-13T17:35:49Z (GMT). No. of bitstreams: 2 SHI-DISSERTATION-2017.pdf: 8966931 bytes, checksum: f7ebaa0ce2ebb11664a08f629fe9bd99 (MD5) LICENSE.txt: 4208 bytes, checksum: d265a58770ecddde50f98f0b083e23db (MD5) Previous issue date: 2017-12-05","Embargo set by: Seth Robbins for item 105482 Lift date: 2020-03-13T17:36:05Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 105482 on 2020-03-14T09:15:28Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/99513"],"dc:language":["en"],"dc:rights":["Copyright 2017 Honghui Shi"],"dc:subject":["Deep learning","Sequential data analysis","Visual recognition","Video object detection","Video object tracking"],"dc:title":["Deep learning in sequential data analysis"],"dc:type":["text"],"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":"2026-07-22T22:24:37Z"}