{"id":"https://openalex.org/W4406890750","doi":"https://doi.org/10.1109/tmm.2025.3535404","title":"GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models","display_name":"GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406890750","doi":"https://doi.org/10.1109/tmm.2025.3535404"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535404","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hub.hku.hk/handle/10722/357469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101751546","display_name":"Jing Hao","orcid":"https://orcid.org/0000-0002-2305-1201"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Hao","raw_affiliation_strings":["University of Hong Kong, Hong Kong, SAR, China","University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2305-1201","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016553220","display_name":"Moyun Liu","orcid":"https://orcid.org/0000-0002-4530-2606"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Moyun Liu","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4530-2606","affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930120","display_name":"Jinrong Yang","orcid":"https://orcid.org/0000-0002-7678-0360"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinrong Yang","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070510981","display_name":"Kuo Feng Hung","orcid":"https://orcid.org/0000-0002-3971-3484"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kuo Feng Hung","raw_affiliation_strings":["University of Hong Kong, Hong Kong, SAR, China","University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3971-3484","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.809,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83750224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"3501","last_page":"3512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13049","display_name":"Surface Roughness and Optical Measurements","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699660062789917},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6343997716903687},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6050068736076355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5596362352371216},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5095810890197754},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5059570670127869},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4079975485801697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699660062789917},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6343997716903687},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6050068736076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5596362352371216},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5095810890197754},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5059570670127869},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4079975485801697},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3535404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535404","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/357469","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/357469","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:hub.hku.hk:10722/357469","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/357469","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1969624871","https://openalex.org/W2175023734","https://openalex.org/W2962766617","https://openalex.org/W3034233533","https://openalex.org/W3035618398","https://openalex.org/W3047377799","https://openalex.org/W3097762837","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3153051248","https://openalex.org/W3170841864","https://openalex.org/W3174982506","https://openalex.org/W3179324864","https://openalex.org/W3207804100","https://openalex.org/W4214703515","https://openalex.org/W4214893857","https://openalex.org/W4226267082","https://openalex.org/W4285256277","https://openalex.org/W4312364648","https://openalex.org/W4312446817","https://openalex.org/W4312531268","https://openalex.org/W4312815172","https://openalex.org/W4312866343","https://openalex.org/W4312933868","https://openalex.org/W4327807853","https://openalex.org/W4362641980","https://openalex.org/W4375802461","https://openalex.org/W4385767327","https://openalex.org/W4385804789","https://openalex.org/W4386066126","https://openalex.org/W4386066444","https://openalex.org/W4386071535","https://openalex.org/W4386071792","https://openalex.org/W4386075553","https://openalex.org/W4386076084","https://openalex.org/W4386076522","https://openalex.org/W4387517523","https://openalex.org/W4388129777","https://openalex.org/W4390873054","https://openalex.org/W4390873795","https://openalex.org/W4390874575","https://openalex.org/W4400316340","https://openalex.org/W4402727359","https://openalex.org/W4407637743","https://openalex.org/W4411012701","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6794345597","https://openalex.org/W6797399245","https://openalex.org/W6798837711","https://openalex.org/W6809665764","https://openalex.org/W6809885388","https://openalex.org/W6845839425","https://openalex.org/W6851607685","https://openalex.org/W6851950068","https://openalex.org/W6852206773","https://openalex.org/W6854034129","https://openalex.org/W6854362512","https://openalex.org/W6857614378","https://openalex.org/W6865348343"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Detecting":[0],"glass":[1,170],"regions":[2],"is":[3],"a":[4,98,143,177],"challenging":[5],"task":[6],"due":[7],"to":[8,72],"the":[9,31,37,43,52,61,79,135,158,168,182,189],"inherent":[10],"ambiguity":[11],"in":[12,20,25,51,211],"their":[13],"transparency":[14],"and":[15,36,54,90,213],"reflective":[16],"characteristics.":[17],"Current":[18],"solutions":[19,49],"this":[21,68],"field":[22],"remain":[23],"rooted":[24],"conventional":[26],"deep":[27],"learning":[28,215],"paradigms,":[29],"requiring":[30],"construction":[32],"of":[33,39,57,64,81,119,124,139,184,197],"annotated":[34],"datasets":[35],"design":[38],"network":[40],"architectures.":[41],"However,":[42],"evident":[44],"drawback":[45],"with":[46,129,181,193],"these":[47,74,185],"mainstream":[48],"lies":[50],"time-consuming":[53],"labor-intensive":[55],"process":[56],"curating":[58],"datasets,":[59],"alongside":[60],"increasing":[62],"complexity":[63],"model":[65],"structures.":[66],"In":[67],"paper,":[69],"we":[70,96,141],"propose":[71],"address":[73],"issues":[75],"by":[76],"fully":[77],"harnessing":[78],"capabilities":[80],"two":[82,186],"existing":[83],"vision":[84],"foundation":[85],"models":[86],"(VFMs):":[87],"Stable":[88,114],"Diffusion":[89],"Segment":[91],"Anything":[92],"Model":[93],"(SAM).":[94],"Firstly,":[95],"construct":[97],"Synthetic":[99],"but":[100],"photorealistic":[101],"large-scale":[102,169],"Glass":[103],"Surface":[104],"Detection":[105],"dataset,":[106],"dubbed":[107],"S-GSD,":[108],"without":[109],"any":[110],"labour":[111],"cost":[112],"via":[113],"Diffusion.":[115],"This":[116],"dataset":[117,172,206],"consists":[118],"four":[120],"different":[121],"scales,":[122],"consisting":[123],"168":[125],"k":[126],"images":[127],"totally":[128],"precise":[130],"masks.":[131],"Besides,":[132],"based":[133],"on":[134,167],"powerful":[136],"segmentation":[137,171],"ability":[138],"SAM,":[140],"devise":[142],"simple":[144,159],"<bold":[145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[146,150,152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</b>lass":[147],"surface":[148],"s<bold":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E</b>g<bold":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</b>entor":[153],"named":[154],"GEM,":[155],"which":[156],"follows":[157],"query-based":[160],"encoder-decoder":[161],"architecture.":[162],"Comprehensive":[163],"experiments":[164,201],"are":[165],"conducted":[166],"GSD-S.":[173],"Our":[174],"GEM":[175],"establishes":[176],"new":[178],"state-of-the-art":[179],"performance":[180,210],"help":[183],"VFMs,":[187],"surpassing":[188],"best-reported":[190],"method":[191],"GlassSemNet":[192],"an":[194],"IoU":[195],"improvement":[196],"2.1%.":[198],"Additionally,":[199],"extensive":[200],"demonstrate":[202],"that":[203],"our":[204],"synthetic":[205],"S-GSD":[207],"exhibits":[208],"remarkable":[209],"zero-shot":[212],"transfer":[214],"settings.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}