{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/60155"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/60155","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Weighted geometric grammars for object detection in context","abstract":"This thesis addresses the problem of detecting objects in images of complex scenes. Strong patterns exist in the types and spatial arrangements of objects that occur in scenes, and we seek to exploit these patterns to improve detection performance. We introduce a novel formalism-weighted geometric grammars (WGGs)-for flexibly representing and recognizing combinations of objects and their spatial relationships in scenes. We adapt the structured perceptron algorithm to parameter learning in WGG models, and develop a set of original clustering-based algorithms for structure learning. We then demonstrate empirically that WGG models, with parameters and structure learned automatically from data, can outperform a standard object detector. This thesis also contributes three new fully-labeled datasets, in two domains, to the scene understanding community.","abstract_html":"This thesis addresses the problem of detecting objects in images of complex scenes. Strong patterns exist in the types and spatial arrangements of objects that occur in scenes, and we seek to exploit these patterns to improve detection performance. We introduce a novel formalism-weighted geometric grammars (WGGs)-for flexibly representing and recognizing combinations of objects and their spatial relationships in scenes. We adapt the structured perceptron algorithm to parameter learning in WGG models, and develop a set of original clustering-based algorithms for structure learning. We then demonstrate empirically that WGG models, with parameters and structure learned automatically from data, can outperform a standard object detector. This thesis also contributes three new fully-labeled datasets, in two domains, to the scene understanding community.","abstract_has_math":false,"creators":["Lippow, Margaret Aycinena"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Leslie Pack Kaelbling and Tomáis Lozano-Pérez."],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010","date_published":"2010","updated_at":"2026-07-22T22:21:13Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/60155","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Leslie Pack Kaelbling and Tomáis Lozano-Pérez."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Lippow, Margaret Aycinena"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2010-12-06T17:30:52Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2010-12-06T17:30:52Z"]},{"key":"dc:date.issued","label":"Date","values":["2010"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/60155"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 155-161)."]},{"key":"dc:description.abstract","label":"Abstract","values":["This thesis addresses the problem of detecting objects in images of complex scenes. Strong patterns exist in the types and spatial arrangements of objects that occur in scenes, and we seek to exploit these patterns to improve detection performance. We introduce a novel formalism-weighted geometric grammars (WGGs)-for flexibly representing and recognizing combinations of objects and their spatial relationships in scenes. We adapt the structured perceptron algorithm to parameter learning in WGG models, and develop a set of original clustering-based algorithms for structure learning. We then demonstrate empirically that WGG models, with parameters and structure learned automatically from data, can outperform a standard object detector. This thesis also contributes three new fully-labeled datasets, in two domains, to the scene understanding community."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Weighted geometric grammars for object detection in context"]}]}],"canonical_facts":{"dc:contributor.advisor":["Leslie Pack Kaelbling and Tomáis Lozano-Pérez."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:creator":["Lippow, Margaret Aycinena"],"dc:date.accessioned":["2010-12-06T17:30:52Z"],"dc:date.available":["2010-12-06T17:30:52Z"],"dc:date.issued":["2010"],"dc:description":["Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 155-161)."],"dc:description.abstract":["This thesis addresses the problem of detecting objects in images of complex scenes. Strong patterns exist in the types and spatial arrangements of objects that occur in scenes, and we seek to exploit these patterns to improve detection performance. We introduce a novel formalism-weighted geometric grammars (WGGs)-for flexibly representing and recognizing combinations of objects and their spatial relationships in scenes. We adapt the structured perceptron algorithm to parameter learning in WGG models, and develop a set of original clustering-based algorithms for structure learning. We then demonstrate empirically that WGG models, with parameters and structure learned automatically from data, can outperform a standard object detector. This thesis also contributes three new fully-labeled datasets, in two domains, to the scene understanding community."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/60155"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Weighted geometric grammars for object detection in context"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:13Z"}