{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/115463"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/115463","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Exploiting relations among output variables for prediction and forecasting","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","abstract_has_math":false,"creators":["Graber, Colin G"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Schwing, Alexander","Forsyth, David","Hoiem, Derek","Firman, Michael"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:24:54Z","subjects":["machine learning","computer vision","structured output prediction","trajectory prediction","panoptic segmentation","panoptic segmentation forecasting"],"languages":["en","eng"],"rights":["Copyright 2022 Colin Graber"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/115463","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander","Forsyth, David","Hoiem, Derek","Firman, Michael"]},{"key":"dc:creator","label":"Author","values":["Graber, Colin G"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-05","2022-04-15"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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":["machine learning","computer vision","structured output prediction","trajectory prediction","panoptic segmentation","panoptic segmentation forecasting"]}]},{"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 2022 Colin Graber"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/115463"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","The student, Colin Graber, accepted the attached license on 2022-04-15 at 09:51.","The student, Colin Graber, submitted this Dissertation for approval on 2022-04-15 at 09:59.","This Dissertation was approved for publication on 2022-04-15 at 15:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17696 on 2022-11-11 at 13:15:18","In this work, we develop new approaches to model the relationships between problem variables and demonstrate that exploiting these relationships leads to improved performance for prediction and forecasting tasks. For structured output prediction, we describe a model which merges classical graphical model-based structured prediction methods with deep energy network-based approaches. We show that combining the strengths of these two approaches allows for improved performance over using them individually. Next, we introduce an approach for multi-entity trajectory prediction tasks which explicitly predicts the relationships between the entities at every point in time and uses these to select the model parameters used to forecast their future states. We show that predicting dynamic relations can lead to improved trajectory prediction performance over using a static relation graph. After this, we introduce the panoptic segmentation forecasting task and develop an initial approach to model this task. This approach functions by decomposing the scene into moving foreground components and static background components, modeling the motion of each separately. Finally, we show that introducing additional interaction modeling to the previous framework, both between all foreground instances and between foreground and background objects, leads to improved task performance and more consistent panoptic segmentation forecasts."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Exploiting relations among output variables for prediction and forecasting"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander","Forsyth, David","Hoiem, Derek","Firman, Michael"],"dc:creator":["Graber, Colin G"],"dc:date":["2022-05","2022-04-15"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","The student, Colin Graber, accepted the attached license on 2022-04-15 at 09:51.","The student, Colin Graber, submitted this Dissertation for approval on 2022-04-15 at 09:59.","This Dissertation was approved for publication on 2022-04-15 at 15:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17696 on 2022-11-11 at 13:15:18","In this work, we develop new approaches to model the relationships between problem variables and demonstrate that exploiting these relationships leads to improved performance for prediction and forecasting tasks. For structured output prediction, we describe a model which merges classical graphical model-based structured prediction methods with deep energy network-based approaches. We show that combining the strengths of these two approaches allows for improved performance over using them individually. Next, we introduce an approach for multi-entity trajectory prediction tasks which explicitly predicts the relationships between the entities at every point in time and uses these to select the model parameters used to forecast their future states. We show that predicting dynamic relations can lead to improved trajectory prediction performance over using a static relation graph. After this, we introduce the panoptic segmentation forecasting task and develop an initial approach to model this task. This approach functions by decomposing the scene into moving foreground components and static background components, modeling the motion of each separately. Finally, we show that introducing additional interaction modeling to the previous framework, both between all foreground instances and between foreground and background objects, leads to improved task performance and more consistent panoptic segmentation forecasts."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/115463"],"dc:language":["en","eng"],"dc:rights":["Copyright 2022 Colin Graber"],"dc:subject":["machine learning","computer vision","structured output prediction","trajectory prediction","panoptic segmentation","panoptic segmentation forecasting"],"dc:title":["Exploiting relations among output variables for prediction and forecasting"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:54Z"}