{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/102966"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/102966","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Semantic amodal video segmentation using a synthetic dataset","abstract":"In this work, we provide tools for annotating both object category and shot transitions for a new semantic modal instance-level object segmentation dataset. This new dataset provides ample opportunities to train models for instance-level segmentation, both modal and amodal. Moreover, in this work, we also present results for instance-level segmentation using ResNet-based DeepLab, a state-of-the-art semantic image segmentation model. We also develop a new semantic amodal instance-level video segmentation model based on DeepLab for the aforementioned dataset. Our model for amodal segmentation operates on a per-frame basis, and the model is guided by the modal mask estimated from the current frame and from previous frames delineating the object of interest. We demonstrate the efficacy of the proposed model on the new dataset.","abstract_html":"In this work, we provide tools for annotating both object category and shot transitions for a new semantic modal instance-level object segmentation dataset. This new dataset provides ample opportunities to train models for instance-level segmentation, both modal and amodal. Moreover, in this work, we also present results for instance-level segmentation using ResNet-based DeepLab, a state-of-the-art semantic image segmentation model. We also develop a new semantic amodal instance-level video segmentation model based on DeepLab for the aforementioned dataset. Our model for amodal segmentation operates on a per-frame basis, and the model is guided by the modal mask estimated from the current frame and from previous frames delineating the object of interest. We demonstrate the efficacy of the proposed model on the new dataset.","abstract_has_math":false,"creators":["Hui, Kexin"],"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":2019,"date_issued":"2019-02-08T18:44:47Z","date_published":"2019-02-08T18:44:47Z","updated_at":"2026-07-22T22:24:42Z","subjects":["ANNOTATION","VIDEO SEGMENTATION"],"languages":["en"],"rights":["Copyright 2018 Kexin Hui"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/102966","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":["Hui, Kexin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-02-08T18:44:47Z","2021-02-09T10:15:26Z","2018-12-14","2018-12"]},{"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":["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":["ANNOTATION","VIDEO SEGMENTATION"]}]},{"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 Kexin Hui"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/102966"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In this work, we provide tools for annotating both object category and shot transitions for a new semantic modal instance-level object segmentation dataset. This new dataset provides ample opportunities to train models for instance-level segmentation, both modal and amodal. Moreover, in this work, we also present results for instance-level segmentation using ResNet-based DeepLab, a state-of-the-art semantic image segmentation model. We also develop a new semantic amodal instance-level video segmentation model based on DeepLab for the aforementioned dataset. Our model for amodal segmentation operates on a per-frame basis, and the model is guided by the modal mask estimated from the current frame and from previous frames delineating the object of interest. We demonstrate the efficacy of the proposed model on the new dataset.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2020-12-01","The student, Kexin Hui, accepted the attached license on 2018-12-14 at 02:22.","The student, Kexin Hui, submitted this Thesis for approval on 2018-12-14 at 02:32.","This Thesis was approved for publication on 2018-12-14 at 08:08.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13327 on 2019-02-08 at 11:42:24","Made available in DSpace on 2019-02-08T18:44:47Z (GMT). No. of bitstreams: 2 HUI-THESIS-2018.pdf: 17911472 bytes, checksum: 8d45d654c678be7971327bc00a647a08 (MD5) LICENSE.txt: 4206 bytes, checksum: 4b3f1b2275cf8b55d8222ef8dc5c779c (MD5) Previous issue date: 2018-12-14","Embargo set by: Seth Robbins for item 109994 Lift date: 2021-02-08T18:44:50Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 109994 on 2021-02-09T10:15:26Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Semantic amodal video segmentation using a synthetic dataset"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander"],"dc:creator":["Hui, Kexin"],"dc:date":["2019-02-08T18:44:47Z","2021-02-09T10:15:26Z","2018-12-14","2018-12"],"dc:description":["In this work, we provide tools for annotating both object category and shot transitions for a new semantic modal instance-level object segmentation dataset. This new dataset provides ample opportunities to train models for instance-level segmentation, both modal and amodal. Moreover, in this work, we also present results for instance-level segmentation using ResNet-based DeepLab, a state-of-the-art semantic image segmentation model. We also develop a new semantic amodal instance-level video segmentation model based on DeepLab for the aforementioned dataset. Our model for amodal segmentation operates on a per-frame basis, and the model is guided by the modal mask estimated from the current frame and from previous frames delineating the object of interest. We demonstrate the efficacy of the proposed model on the new dataset.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2020-12-01","The student, Kexin Hui, accepted the attached license on 2018-12-14 at 02:22.","The student, Kexin Hui, submitted this Thesis for approval on 2018-12-14 at 02:32.","This Thesis was approved for publication on 2018-12-14 at 08:08.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13327 on 2019-02-08 at 11:42:24","Made available in DSpace on 2019-02-08T18:44:47Z (GMT). No. of bitstreams: 2 HUI-THESIS-2018.pdf: 17911472 bytes, checksum: 8d45d654c678be7971327bc00a647a08 (MD5) LICENSE.txt: 4206 bytes, checksum: 4b3f1b2275cf8b55d8222ef8dc5c779c (MD5) Previous issue date: 2018-12-14","Embargo set by: Seth Robbins for item 109994 Lift date: 2021-02-08T18:44:50Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 109994 on 2021-02-09T10:15:26Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/102966"],"dc:language":["en"],"dc:rights":["Copyright 2018 Kexin Hui"],"dc:subject":["ANNOTATION","VIDEO SEGMENTATION"],"dc:title":["Semantic amodal video segmentation using a synthetic dataset"],"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":"2026-07-22T22:24:42Z"}