{"id":"https://openalex.org/W4416323874","doi":"https://doi.org/10.26599/cvm.2025.9450415","title":"Multi-Task Gradual Inference with a Single Encoder\u2013Decoder Network for Automatic Portrait Matting","display_name":"Multi-Task Gradual Inference with a Single Encoder\u2013Decoder Network for Automatic Portrait Matting","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4416323874","doi":"https://doi.org/10.26599/cvm.2025.9450415"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450415","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450415","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108738401","display_name":"Wenbing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenbing Yang","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009533191","display_name":"Wei Ma","orcid":"https://orcid.org/0000-0001-9652-4260"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ma","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010586673","display_name":"Qing Mi","orcid":"https://orcid.org/0000-0001-5063-3189"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Mi","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110213667","display_name":"Hongbin Zha","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Zha","raw_affiliation_strings":["School of Electronics Engineering and Computer Science, Peking University,Key Laboratory of Machine Perception (MOE),Beijing,China,100871","Key Laboratory of Machine Perception (MOE), School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering and Computer Science, Peking University,Key Laboratory of Machine Perception (MOE),Beijing,China,100871","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception (MOE), School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108738401"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33015387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"6","first_page":"1385","last_page":"1398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9686999917030334,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9686999917030334,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.005499999970197678,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.004699999932199717,"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/inference","display_name":"Inference","score":0.7067000269889832},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6775000095367432},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6419000029563904},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6258000135421753},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5627999901771545},{"id":"https://openalex.org/keywords/portrait","display_name":"Portrait","score":0.4422000050544739},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.4235000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7103000283241272},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7067000269889832},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6419000029563904},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C2779662243","wikidata":"https://www.wikidata.org/wiki/Q970395","display_name":"Shape context","level":3,"score":0.37700000405311584},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/cvm.2025.9450415","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450415","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b84ed5711b6c4cf1b65082cbed75c0d7","is_oa":true,"landing_page_url":"https://doaj.org/article/b84ed5711b6c4cf1b65082cbed75c0d7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 11, Iss 6, Pp 1385-1398 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450415","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450415","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8008040666","display_name":null,"funder_award_id":"62176010,61771026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2035773017","https://openalex.org/W2194775991","https://openalex.org/W2295475768","https://openalex.org/W2518810941","https://openalex.org/W2604469346","https://openalex.org/W2891201469","https://openalex.org/W2955340181","https://openalex.org/W2963587345","https://openalex.org/W2985469567","https://openalex.org/W2997597456","https://openalex.org/W3016693803","https://openalex.org/W3034368090","https://openalex.org/W3035010169","https://openalex.org/W3166852674","https://openalex.org/W3207351435","https://openalex.org/W4205174848","https://openalex.org/W4281478479","https://openalex.org/W4283804702","https://openalex.org/W4312429965","https://openalex.org/W4312524025","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,30,50,124,137],"multi-task":[4],"gradual":[5,76],"inference":[6,77],"model,":[7,133],"MTGINet,":[8],"for":[9,56,71,142],"automatic":[10,18],"portrait":[11,19,46,144],"matting.":[12,74,145],"It":[13,146],"handles":[14],"the":[15,37,43,62,69,84,106,115,118,131,161,171],"subtasks":[16,85],"of":[17,40,148],"matting,":[20,28],"namely":[21],"portrait-transition-background":[22],"trimap":[23,57],"segmentation":[24],"and":[25,89,94,165],"transition":[26],"region":[27],"with":[29,45,65,151,156],"single":[31],"encoder-decoder":[32],"structure.":[33],"First,":[34],"we":[35,60,113,134],"enrich":[36],"highest":[38],"stage":[39],"features":[41,64,116],"from":[42,68,117],"encoder":[44,70],"shape":[47,51],"context":[48,52],"via":[49,86,123],"aggregation":[53],"(SCA)":[54],"module":[55],"segmentation.":[58],"Then,":[59],"fuse":[61],"SCA-enhanced":[63],"detailed":[66],"clues":[67],"transition-region-aware":[72],"alpha":[73],"The":[75],"model":[78,173],"naturally":[79],"allows":[80],"sufficient":[81],"interaction":[82],"between":[83],"forward":[87],"computation":[88],"backwards":[90],"propagation":[91],"during":[92],"training,":[93],"therefore":[95],"achieves":[96],"high":[97],"accuracy":[98],"while":[99],"maintaining":[100],"low":[101],"complexity.":[102],"In":[103,128],"addition,":[104],"considering":[105],"discrepancies":[107],"in":[108],"feature":[109,125],"requirements":[110],"across":[111],"subtasks,":[112],"adapt":[114],"encoders":[119],"before":[120],"reusing":[121],"them":[122],"rectification":[126],"module.":[127],"addition":[129],"to":[130],"MTGINet":[132],"have":[135],"constructed":[136],"new":[138],"large-scale":[139],"dataset,":[140],"HPM-17K,":[141],"half-body":[143],"consists":[147],"16,967":[149],"images":[150],"diverse":[152],"backgrounds.":[153],"Comparative":[154],"experiments":[155],"existing":[157],"deep":[158],"models":[159],"on":[160],"public":[162],"P3M-10K":[163],"dataset":[164,168],"our":[166],"HPM-17K":[167],"demonstrate":[169],"that":[170],"proposed":[172],"exhibits":[174],"state-of-the-art":[175],"performance.":[176]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-11-18T00:00:00"}