{"id":{"repo_id":"iupui","oai_identifier":"oai:scholarworks.indianapolis.iu.edu:1805/33375"},"canonical_url":"https://search.dev.ndltd.org/etd/iupui/oai:scholarworks.indianapolis.iu.edu:1805/33375","repository":{"repo_id":"iupui","name":"IUPUI","base_url":"https://scholarworks.indianapolis.iu.edu/server/oai/request"},"display":{"title":"Deep Image Processing with Spatial Adaptation and Boosted Efficiency & Supervision for Accurate Human Keypoint Detection and Movement Dynamics Tracking","abstract":"This thesis aims to design and develop the spatial adaptation approach through spatial transformers to improve the accuracy of human keypoint recognition models. We have studied different model types and design choices to gain an accuracy increase over models without spatial transformers and analyzed how spatial transformers increase the accuracy of predictions. A neural network called Widenet has been leveraged as a specialized network for providing the parameters for the spatial transformer. Further, we have evaluated methods to reduce the model parameters, as well as the strategy to enhance the learning supervision for further improving the performance of the model. Our experiments and results have shown that the proposed deep learning framework can effectively detect the human key points, compared with the baseline methods. Also, we have reduced the model size without significantly impacting the performance, and the enhanced supervision has improved the performance. This study is expected to greatly advance the deep learning of human key points and movement dynamics.","abstract_html":"This thesis aims to design and develop the spatial adaptation approach through spatial transformers to improve the accuracy of human keypoint recognition models. We have studied different model types and design choices to gain an accuracy increase over models without spatial transformers and analyzed how spatial transformers increase the accuracy of predictions. A neural network called Widenet has been leveraged as a specialized network for providing the parameters for the spatial transformer. Further, we have evaluated methods to reduce the model parameters, as well as the strategy to enhance the learning supervision for further improving the performance of the model. Our experiments and results have shown that the proposed deep learning framework can effectively detect the human key points, compared with the baseline methods. Also, we have reduced the model size without significantly impacting the performance, and the enhanced supervision has improved the performance. This study is expected to greatly advance the deep learning of human key points and movement dynamics.","abstract_has_math":false,"creators":["Dai, Chao Yang"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Zhang, Qingxue"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-05","date_published":"2023-05","updated_at":"2026-07-24T02:40:13Z","subjects":["Computer Vision","Artificial Intelligence","Human Keypoint Estimation","Deep Learning","Spatial Transformers"],"languages":["en"],"rights":["Attribution 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://dx.doi.org/10.7912/C2/3165"],"render_values":[{"text":"http://dx.doi.org/10.7912/C2/3165","href":"http://dx.doi.org/10.7912/C2/3165","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/1805/33375","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Zhang, Qingxue"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["King, Brian S.","Fang, Shiaofen"]},{"key":"dc:creator","label":"Author","values":["Dai, Chao Yang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-05-31T16:21:08Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-05-31T16:21:08Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-05"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Vision","Artificial Intelligence","Human Keypoint Estimation","Deep Learning","Spatial Transformers"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1805/33375","http://dx.doi.org/10.7912/C2/3165"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Indiana University-Purdue University Indianapolis (IUPUI)"]},{"key":"dc:description.abstract","label":"Abstract","values":["This thesis aims to design and develop the spatial adaptation approach through spatial transformers to improve the accuracy of human keypoint recognition models. We have studied different model types and design choices to gain an accuracy increase over models without spatial transformers and analyzed how spatial transformers increase the accuracy of predictions. A neural network called Widenet has been leveraged as a specialized network for providing the parameters for the spatial transformer. Further, we have evaluated methods to reduce the model parameters, as well as the strategy to enhance the learning supervision for further improving the performance of the model. Our experiments and results have shown that the proposed deep learning framework can effectively detect the human key points, compared with the baseline methods. Also, we have reduced the model size without significantly impacting the performance, and the enhanced supervision has improved the performance. This study is expected to greatly advance the deep learning of human key points and movement dynamics."]},{"key":"dc:title","label":"Title","values":["Deep Image Processing with Spatial Adaptation and Boosted Efficiency & Supervision for Accurate Human Keypoint Detection and Movement Dynamics Tracking"]}]}],"canonical_facts":{"dc:contributor.advisor":["Zhang, Qingxue"],"dc:contributor.other":["King, Brian S.","Fang, Shiaofen"],"dc:creator":["Dai, Chao Yang"],"dc:date.accessioned":["2023-05-31T16:21:08Z"],"dc:date.available":["2023-05-31T16:21:08Z"],"dc:date.issued":["2023-05"],"dc:description":["Indiana University-Purdue University Indianapolis (IUPUI)"],"dc:description.abstract":["This thesis aims to design and develop the spatial adaptation approach through spatial transformers to improve the accuracy of human keypoint recognition models. We have studied different model types and design choices to gain an accuracy increase over models without spatial transformers and analyzed how spatial transformers increase the accuracy of predictions. A neural network called Widenet has been leveraged as a specialized network for providing the parameters for the spatial transformer. Further, we have evaluated methods to reduce the model parameters, as well as the strategy to enhance the learning supervision for further improving the performance of the model. Our experiments and results have shown that the proposed deep learning framework can effectively detect the human key points, compared with the baseline methods. Also, we have reduced the model size without significantly impacting the performance, and the enhanced supervision has improved the performance. This study is expected to greatly advance the deep learning of human key points and movement dynamics."],"dc:identifier.uri":["https://hdl.handle.net/1805/33375","http://dx.doi.org/10.7912/C2/3165"],"dc:language.iso":["en"],"dc:rights":["Attribution 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["Computer Vision","Artificial Intelligence","Human Keypoint Estimation","Deep Learning","Spatial Transformers"],"dc:title":["Deep Image Processing with Spatial Adaptation and Boosted Efficiency & Supervision for Accurate Human Keypoint Detection and Movement Dynamics Tracking"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T02:40:13Z"}