{"id":"https://openalex.org/W4415537826","doi":"https://doi.org/10.1145/3746027.3755727","title":"Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions","display_name":"Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537826","doi":"https://doi.org/10.1145/3746027.3755727"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755727","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755727","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755727","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100769097","display_name":"Jingdong Zhang","orcid":"https://orcid.org/0009-0008-6668-1140"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingdong Zhang","raw_affiliation_strings":["Texas A&M University, College Station, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, Texas, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058387246","display_name":"Hanrong Ye","orcid":"https://orcid.org/0000-0002-7986-6143"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hanrong Ye","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353783","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0144-9489"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Texas A&M University, College Station, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, Texas, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668416","display_name":"Wenping Wang","orcid":"https://orcid.org/0000-0002-2284-3952"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenping Wang","raw_affiliation_strings":["Texas A&M University, College Station, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, Texas, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341938","display_name":"Dan Xu","orcid":"https://orcid.org/0000-0003-0136-9603"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dan Xu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100769097"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17055846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/task","display_name":"Task (project management)","score":0.6348999738693237},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5651000142097473},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5159000158309937},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4903999865055084},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42669999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145999908447266},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6348999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5651000142097473},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755727","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755727","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-149706","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-149706","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755727","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755727","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2031489346","https://openalex.org/W2340897893","https://openalex.org/W2962864421","https://openalex.org/W2964193874","https://openalex.org/W3035160371","https://openalex.org/W3083779147","https://openalex.org/W4386075981","https://openalex.org/W4397026326"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"simultaneous":[3],"learning":[4,174],"of":[5,48,55,73,115,163,175],"multiple":[6],"dense":[7,136,158,178,203],"prediction":[8,94,179],"tasks":[9],"with":[10,138],"partially":[11,200],"annotated":[12,201],"label":[13],"data":[14],"has":[15],"emerged":[16],"as":[17],"an":[18],"important":[19],"research":[20],"area.":[21],"Previous":[22],"works":[23],"primarily":[24],"focus":[25],"on":[26,184],"leveraging":[27],"cross-task":[28,105],"relations":[29],"or":[30],"conducting":[31],"adversarial":[32],"training":[33,54],"for":[34,103,120,199],"extra":[35,53],"regularization,":[36],"which":[37],"achieve":[38],"promising":[39],"performance":[40],"improvements,":[41],"while":[42],"still":[43],"suffering":[44],"from":[45,125],"the":[46,97,126,173,176],"lack":[47],"direct":[49],"pixel-wise":[50,87],"supervision":[51,88],"and":[52,81,93,146,165,188],"heavy":[56],"mapping":[57],"networks.":[58],"To":[59],"effectively":[60],"tackle":[61],"this":[62],"challenge,":[63],"we":[64],"propose":[65],"a":[66,71,109,113],"novel":[67],"approach":[68],"to":[69,84,134,154,170],"optimize":[70],"set":[72],"compact":[74],"learnable":[75],"hierarchical":[76],"task":[77,99,122,129,149],"tokens,":[78],"including":[79],"global":[80,98,110,128,145],"fine-grained":[82,116,148],"ones,":[83],"discover":[85,155],"consistent":[86],"signals":[89],"in":[90,108],"both":[91],"feature":[92,106,141],"levels.":[95],"Specifically,":[96],"tokens":[100,119,150],"are":[101,151],"designed":[102],"effective":[104],"interactions":[107,137],"context.":[111],"Then,":[112],"group":[114],"task-specific":[117,140,157],"spatial":[118],"each":[121,139],"is":[123,132],"learned":[124,144],"corresponding":[127],"tokens.":[130],"It":[131],"embedded":[133],"have":[135],"map.":[142],"The":[143],"local":[147],"further":[152],"used":[153],"pseudo":[156],"labels":[159],"at":[160],"different":[161],"levels":[162],"granularity,":[164],"they":[166],"can":[167],"be":[168],"utilized":[169],"directly":[171],"supervise":[172],"multi-task":[177,202],"framework.":[180],"Extensive":[181],"experimental":[182],"results":[183],"challenging":[185],"NYUD-v2,":[186],"Cityscapes,":[187],"PASCAL":[189],"Context":[190],"datasets":[191],"demonstrate":[192],"significant":[193],"improvements":[194],"over":[195],"existing":[196],"state-of-the-art":[197],"methods":[198],"prediction.":[204]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}