{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/42191"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/42191","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Toward ontological visual understanding","abstract":"Lack of human prior knowledge is one of the main reasons that the semantic gap still remains when it comes to automatic multimedia understanding. One difference between the human cognition system and state-of-the-art machine vision algorithms is that the former possesses and uses high-level semantic knowledge, or ontology. In this thesis, we present our work on image-level annotation and album-level event recognition, both emphasizing the ontological structure among concepts including object, scene, and event. The inference and learning make use of mutual relations among these concepts, and are general for any concept and initial concept recognition. Our experiments show that the proposed frameworks are able to perform the respective visual recognition tasks better than other methods that are also based on middle-level recognition with or without ontology, and better than methods based purely on low-level features, thus validating the use of ontology in recognizing high-level and abstract concepts.","abstract_html":"Lack of human prior knowledge is one of the main reasons that the semantic gap still remains when it comes to automatic multimedia understanding. One difference between the human cognition system and state-of-the-art machine vision algorithms is that the former possesses and uses high-level semantic knowledge, or ontology. In this thesis, we present our work on image-level annotation and album-level event recognition, both emphasizing the ontological structure among concepts including object, scene, and event. The inference and learning make use of mutual relations among these concepts, and are general for any concept and initial concept recognition. Our experiments show that the proposed frameworks are able to perform the respective visual recognition tasks better than other methods that are also based on middle-level recognition with or without ontology, and better than methods based purely on low-level features, thus validating the use of ontology in recognizing high-level and abstract concepts.","abstract_has_math":false,"creators":["Tsai, Shen-Fu"],"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.","Han, Jiawei","Hasegawa-Johnson, Mark A.","Liang, Zhi-Pei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013-02-03T19:27:24Z","date_published":"2013-02-03T19:27:24Z","updated_at":"2026-07-22T22:25:33Z","subjects":["Visual understanding","ontology","machine learning","pattern recognition"],"languages":["en"],"rights":["Copyright 2012 Shen-Fu Tsai"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/42191","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas S.","Han, Jiawei","Hasegawa-Johnson, Mark A.","Liang, Zhi-Pei"]},{"key":"dc:creator","label":"Author","values":["Tsai, Shen-Fu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2013-02-03T19:27:24Z","2012-12"]},{"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":["Visual understanding","ontology","machine learning","pattern recognition"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2012 Shen-Fu Tsai"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/42191"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Lack of human prior knowledge is one of the main reasons that the semantic gap still remains when it comes to automatic multimedia understanding. One difference between the human cognition system and state-of-the-art machine vision algorithms is that the former possesses and uses high-level semantic knowledge, or ontology. In this thesis, we present our work on image-level annotation and album-level event recognition, both emphasizing the ontological structure among concepts including object, scene, and event. The inference and learning make use of mutual relations among these concepts, and are general for any concept and initial concept recognition. Our experiments show that the proposed frameworks are able to perform the respective visual recognition tasks better than other methods that are also based on middle-level recognition with or without ontology, and better than methods based purely on low-level features, thus validating the use of ontology in recognizing high-level and abstract concepts.","Item withdrawn by Alexis Thompson (athmpsn1@illinois.edu) on 2012-08-06T14:17:16Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Tsai_ShenFu.pdf: 3271697 bytes, checksum: 741b86669b81d53a73f4b2474b1a0b39 (MD5)","Made available in DSpace on 2013-02-03T19:27:24Z (GMT). No. of bitstreams: 2 Shen-Fu_Tsai.pdf: 3271697 bytes, checksum: 741b86669b81d53a73f4b2474b1a0b39 (MD5) license.txt: 4060 bytes, checksum: d0ee1fdbc024df6c97665fe8f1f5c590 (MD5)"]},{"key":"dc:title","label":"Title","values":["Toward ontological visual understanding"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas S.","Han, Jiawei","Hasegawa-Johnson, Mark A.","Liang, Zhi-Pei"],"dc:creator":["Tsai, Shen-Fu"],"dc:date":["2013-02-03T19:27:24Z","2012-12"],"dc:description":["Lack of human prior knowledge is one of the main reasons that the semantic gap still remains when it comes to automatic multimedia understanding. One difference between the human cognition system and state-of-the-art machine vision algorithms is that the former possesses and uses high-level semantic knowledge, or ontology. In this thesis, we present our work on image-level annotation and album-level event recognition, both emphasizing the ontological structure among concepts including object, scene, and event. The inference and learning make use of mutual relations among these concepts, and are general for any concept and initial concept recognition. Our experiments show that the proposed frameworks are able to perform the respective visual recognition tasks better than other methods that are also based on middle-level recognition with or without ontology, and better than methods based purely on low-level features, thus validating the use of ontology in recognizing high-level and abstract concepts.","Item withdrawn by Alexis Thompson (athmpsn1@illinois.edu) on 2012-08-06T14:17:16Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Tsai_ShenFu.pdf: 3271697 bytes, checksum: 741b86669b81d53a73f4b2474b1a0b39 (MD5)","Made available in DSpace on 2013-02-03T19:27:24Z (GMT). No. of bitstreams: 2 Shen-Fu_Tsai.pdf: 3271697 bytes, checksum: 741b86669b81d53a73f4b2474b1a0b39 (MD5) license.txt: 4060 bytes, checksum: d0ee1fdbc024df6c97665fe8f1f5c590 (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/42191"],"dc:language":["en"],"dc:rights":["Copyright 2012 Shen-Fu Tsai"],"dc:subject":["Visual understanding","ontology","machine learning","pattern recognition"],"dc:title":["Toward ontological visual understanding"],"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":"2026-07-22T22:25:33Z"}