{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/101155"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/101155","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Stacked dense-hourglass networks for human pose estimation","abstract":"Convolutional Neural Networks (CNNs) are driving major advances in many computer vision tasks, including the problem of 2D single-person pose estimation. For this task, the Stacked Hourglass Networks (Stack-HgNets) is one of the state-of-the-art architecture that uses residual modules extensively as the basic building block. The residual modules are well recognized for creating shortcut connections, skipping one or more layers which allows information and gradients to flow more effectively through a deep network without vanishing. In this work, we build on the Stack-HgNets and introduce the Stacked Dense-Hourglass Networks (Stack-DenseHgNets). They use dense blocks instead of the residual modules as the basic building block. The dense blocks create more direct connections between each layer and its subsequent successors, granting later filters the access to all the preceding feature-maps inside the same block. Therefore, dense blocks serve as the upgraded substitution for the residual modules. We evaluate the Stack-DenseHgNets on the popular human pose estimation benchmark dataset and compare its performance to the original Stack-HgNets. Using fewer parameters, the Stack-DenseHgNets obtains a performance competitive to the state-of-the-art results on the MPII Human Pose Dataset.","abstract_html":"Convolutional Neural Networks (CNNs) are driving major advances in many computer vision tasks, including the problem of 2D single-person pose estimation. For this task, the Stacked Hourglass Networks (Stack-HgNets) is one of the state-of-the-art architecture that uses residual modules extensively as the basic building block. The residual modules are well recognized for creating shortcut connections, skipping one or more layers which allows information and gradients to flow more effectively through a deep network without vanishing. In this work, we build on the Stack-HgNets and introduce the Stacked Dense-Hourglass Networks (Stack-DenseHgNets). They use dense blocks instead of the residual modules as the basic building block. The dense blocks create more direct connections between each layer and its subsequent successors, granting later filters the access to all the preceding feature-maps inside the same block. Therefore, dense blocks serve as the upgraded substitution for the residual modules. We evaluate the Stack-DenseHgNets on the popular human pose estimation benchmark dataset and compare its performance to the original Stack-HgNets. Using fewer parameters, the Stack-DenseHgNets obtains a performance competitive to the state-of-the-art results on the MPII Human Pose Dataset.","abstract_has_math":false,"creators":["Wang, Dongbo"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Schwing, Alexander"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-04T20:34:02Z","date_published":"2018-09-04T20:34:02Z","updated_at":"2026-07-22T22:24:38Z","subjects":["Stacked Hourglass Networks","DenseNets","Pose Estimation"],"languages":["en"],"rights":["Copyright 2018 Dongbo Wang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/101155","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander"]},{"key":"dc:creator","label":"Author","values":["Wang, Dongbo"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-04T20:34:02Z","2020-09-05T09:15:23Z","2018-04-12","2018-05"]},{"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":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["Stacked Hourglass Networks","DenseNets","Pose Estimation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Dongbo Wang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/101155"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Convolutional Neural Networks (CNNs) are driving major advances in many computer vision tasks, including the problem of 2D single-person pose estimation. For this task, the Stacked Hourglass Networks (Stack-HgNets) is one of the state-of-the-art architecture that uses residual modules extensively as the basic building block. The residual modules are well recognized for creating shortcut connections, skipping one or more layers which allows information and gradients to flow more effectively through a deep network without vanishing. In this work, we build on the Stack-HgNets and introduce the Stacked Dense-Hourglass Networks (Stack-DenseHgNets). They use dense blocks instead of the residual modules as the basic building block. The dense blocks create more direct connections between each layer and its subsequent successors, granting later filters the access to all the preceding feature-maps inside the same block. Therefore, dense blocks serve as the upgraded substitution for the residual modules. We evaluate the Stack-DenseHgNets on the popular human pose estimation benchmark dataset and compare its performance to the original Stack-HgNets. Using fewer parameters, the Stack-DenseHgNets obtains a performance competitive to the state-of-the-art results on the MPII Human Pose Dataset.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-05-01","The student, Dongbo Wang, accepted the attached license on 2018-04-11 at 20:07.","The student, Dongbo Wang, submitted this Thesis for approval on 2018-04-11 at 20:15.","This Thesis was approved for publication on 2018-04-12 at 10:30.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12202 on 2018-08-31 at 17:18:31","Made available in DSpace on 2018-09-04T20:34:02Z (GMT). No. of bitstreams: 2 WANG-THESIS-2018.pdf: 3521887 bytes, checksum: 999f774a115b2745e0fd5845b41c511e (MD5) LICENSE.txt: 4208 bytes, checksum: ed795599099446ac1bf1b62459188f6c (MD5) Previous issue date: 2018-04-12","Embargo set by: Seth Robbins for item 107238 Lift date: 2020-09-04T20:34:13Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107238 Lift date: 2020-09-04T20:37:00Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107238 Lift date: 2020-09-04T20:42:08Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 107238 on 2020-09-05T09:15:23Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Stacked dense-hourglass networks for human pose estimation"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander"],"dc:creator":["Wang, Dongbo"],"dc:date":["2018-09-04T20:34:02Z","2020-09-05T09:15:23Z","2018-04-12","2018-05"],"dc:description":["Convolutional Neural Networks (CNNs) are driving major advances in many computer vision tasks, including the problem of 2D single-person pose estimation. For this task, the Stacked Hourglass Networks (Stack-HgNets) is one of the state-of-the-art architecture that uses residual modules extensively as the basic building block. The residual modules are well recognized for creating shortcut connections, skipping one or more layers which allows information and gradients to flow more effectively through a deep network without vanishing. In this work, we build on the Stack-HgNets and introduce the Stacked Dense-Hourglass Networks (Stack-DenseHgNets). They use dense blocks instead of the residual modules as the basic building block. The dense blocks create more direct connections between each layer and its subsequent successors, granting later filters the access to all the preceding feature-maps inside the same block. Therefore, dense blocks serve as the upgraded substitution for the residual modules. We evaluate the Stack-DenseHgNets on the popular human pose estimation benchmark dataset and compare its performance to the original Stack-HgNets. Using fewer parameters, the Stack-DenseHgNets obtains a performance competitive to the state-of-the-art results on the MPII Human Pose Dataset.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-05-01","The student, Dongbo Wang, accepted the attached license on 2018-04-11 at 20:07.","The student, Dongbo Wang, submitted this Thesis for approval on 2018-04-11 at 20:15.","This Thesis was approved for publication on 2018-04-12 at 10:30.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12202 on 2018-08-31 at 17:18:31","Made available in DSpace on 2018-09-04T20:34:02Z (GMT). No. of bitstreams: 2 WANG-THESIS-2018.pdf: 3521887 bytes, checksum: 999f774a115b2745e0fd5845b41c511e (MD5) LICENSE.txt: 4208 bytes, checksum: ed795599099446ac1bf1b62459188f6c (MD5) Previous issue date: 2018-04-12","Embargo set by: Seth Robbins for item 107238 Lift date: 2020-09-04T20:34:13Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107238 Lift date: 2020-09-04T20:37:00Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107238 Lift date: 2020-09-04T20:42:08Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 107238 on 2020-09-05T09:15:23Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/101155"],"dc:language":["en"],"dc:rights":["Copyright 2018 Dongbo Wang"],"dc:subject":["Stacked Hourglass Networks","DenseNets","Pose Estimation"],"dc:title":["Stacked dense-hourglass networks for human pose estimation"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:38Z"}