{"id":"https://openalex.org/W6945532302","doi":"https://doi.org/10.2312/pg.20221238","title":"Multi-instance Referring Image Segmentation of Scene Sketches based on Global Reference Mechanism","display_name":"Multi-instance Referring Image Segmentation of Scene Sketches based on Global Reference Mechanism","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W6945532302","doi":"https://doi.org/10.2312/pg.20221238"},"language":"en","primary_location":{"id":"doi:10.2312/pg.20221238","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20221238","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2312/pg.20221238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ling, Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ling, Peng","raw_affiliation_strings":["Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mo, Haoran","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mo, Haoran","raw_affiliation_strings":["Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gao, Chengying","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Chengying","raw_affiliation_strings":["Sun Yat-sen university, china"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen university, china","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25252055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38339999318122864,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38339999318122864,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.33480000495910645,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.02979999966919422,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7534999847412109},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6578999757766724},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5853999853134155},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5419999957084656},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5084999799728394},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.49160000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851999998092651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7750999927520752},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6578999757766724},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5419999957084656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.49160000681877136},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.46230000257492065},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2312/pg.20221238","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20221238","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.2312/pg.20221238","is_oa":true,"landing_page_url":"https://doi.org/10.2312/pg.20221238","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scene":[0],"sketch":[1,12],"segmentation":[2,22,34,72,91,153],"based":[3],"on":[4],"referring":[5,20,70,151,163],"expression":[6,83],"plays":[7],"an":[8],"important":[9],"role":[10],"in":[11,99],"editing":[13],"of":[14,30,42,55,73,113,154,162,174],"anime":[15],"industry.":[16],"While":[17],"most":[18],"existing":[19,146],"image":[21,71,152,164],"approaches":[23],"are":[24],"designed":[25,148],"for":[26,36,68,93,149,158],"the":[27,53,78,82,96,105,110,114,117,159,167,170],"standard":[28,160],"task":[29,161],"generating":[31],"a":[32,37,40,64,88,100,122,127],"binary":[33],"mask":[35],"single":[38],"or":[39],"group":[41],"target(s),":[43],"we":[44,61,125],"think":[45],"it":[46,86],"necessary":[47],"to":[48,132,135,139],"equip":[49],"these":[50],"models":[51],"with":[52,145],"ability":[54],"multi-instance":[56,69,150],"segmentation.":[57],"To":[58,108],"this":[59],"end,":[60],"propose":[62,126],"GRM-Net,":[63],"one-stage":[65],"framework":[66],"tailored":[67],"scene":[74,155],"sketches.":[75],"We":[76,143],"extract":[77],"language":[79],"features":[80],"from":[81,121],"and":[84,103,116,157,166,172],"fuse":[85],"into":[87],"conventional":[89],"instance":[90],"pipeline":[92],"filtering":[94],"out":[95],"undesired":[97],"instances":[98],"coarse-to-fine":[101],"manner":[102],"keeping":[104],"matched":[106],"ones.":[107],"model":[109],"relative":[111],"arrangement":[112],"objects":[115],"relationship":[118],"among":[119],"them":[120],"global":[123,128],"view,":[124],"reference":[129],"mechanism":[130],"(GRM)":[131],"assign":[133],"references":[134],"each":[136],"detected":[137],"candidate":[138],"identify":[140],"its":[141],"position.":[142],"compare":[144],"methods":[147],"sketches":[156],"segmentation,":[165],"results":[168],"demonstrate":[169],"effectiveness":[171],"superiority":[173],"our":[175],"approach.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}