{"id":"https://openalex.org/W4415536589","doi":"https://doi.org/10.1145/3746027.3755539","title":"CLIP-MT: Multi-Modal Knowledge-Driven Adaptive Scale Feature Allocation for Multi-Task Dense Prediction","display_name":"CLIP-MT: Multi-Modal Knowledge-Driven Adaptive Scale Feature Allocation for Multi-Task Dense Prediction","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536589","doi":"https://doi.org/10.1145/3746027.3755539"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755539","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092574641","display_name":"Shalayiding Sirejiding","orcid":"https://orcid.org/0000-0003-1255-4994"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shalayiding Sirejiding","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1255-4994","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688231","display_name":"Yue Ding","orcid":"https://orcid.org/0000-0002-2911-1244"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Ding","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2911-1244","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016420216","display_name":"Yuxiang Lu","orcid":"https://orcid.org/0009-0002-6344-3880"},"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":"Yuxiang Lu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0002-6344-3880","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104314486","display_name":"Xinyi Hou","orcid":"https://orcid.org/0009-0001-9649-621X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Hou","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-9649-621X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103060401","display_name":"Shaokai Wu","orcid":"https://orcid.org/0009-0004-0531-1120"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaokai Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-0531-1120","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113150835","display_name":"Qichen He","orcid":"https://orcid.org/0000-0003-1973-9529"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichen He","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1973-9529","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102908344","display_name":"Chunlin Wang","orcid":"https://orcid.org/0000-0001-5561-2053"},"institutions":[{"id":"https://openalex.org/I4210143356","display_name":"Chuxiong Normal University","ror":"https://ror.org/04c14yn55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210143356"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Wang","raw_affiliation_strings":["Chuxiong Normal University, Chuxiong, China"],"raw_orcid":"https://orcid.org/0000-0001-5561-2053","affiliations":[{"raw_affiliation_string":"Chuxiong Normal University, Chuxiong, China","institution_ids":["https://openalex.org/I4210143356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085858293","display_name":"Wenqiang Guo","orcid":"https://orcid.org/0000-0003-2300-6627"},"institutions":[{"id":"https://openalex.org/I94047373","display_name":"Xinjiang University of Finance and Economics","ror":"https://ror.org/00fk31757","country_code":"CN","type":"education","lineage":["https://openalex.org/I94047373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Guo","raw_affiliation_strings":["Xinjiang University of Finance and Economics, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-2300-6627","affiliations":[{"raw_affiliation_string":"Xinjiang University of Finance and Economics, Urumqi, China","institution_ids":["https://openalex.org/I94047373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102899381","display_name":"Hongtao Lu","orcid":"https://orcid.org/0000-0003-2300-3039"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2300-3039","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15379928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6986","last_page":"6995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/feature","display_name":"Feature (linguistics)","score":0.7074999809265137},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5444999933242798},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5436000227928162},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.47380000352859497},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44429999589920044},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627999782562256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7074999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6155999898910522},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6686351019","display_name":null,"funder_award_id":"YG2024ZD06","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2104408738","https://openalex.org/W2959581809","https://openalex.org/W2963877604","https://openalex.org/W2964247799","https://openalex.org/W2966182616","https://openalex.org/W3035276179","https://openalex.org/W3138516171","https://openalex.org/W3141797743","https://openalex.org/W4312443924","https://openalex.org/W4312550876","https://openalex.org/W4313156423","https://openalex.org/W4382240003","https://openalex.org/W4392172801","https://openalex.org/W4395481595","https://openalex.org/W4396680455","https://openalex.org/W4402753899"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,50],"visual":[3],"multi-task":[4],"learning":[5],"(MTL)":[6],"have":[7],"sparked":[8],"significant":[9],"interest.":[10],"However,":[11],"existing":[12,167],"dense":[13,38,171],"prediction":[14,172],"MTL":[15],"methods":[16,168],"predominantly":[17],"rely":[18],"on":[19,135,154],"single-modality":[20],"image":[21,78],"data,":[22],"limiting":[23],"their":[24],"performance":[25],"due":[26],"to":[27,75,97,108],"the":[28,110,155],"absence":[29],"of":[30],"complementary":[31],"knowledge":[32],"from":[33],"other":[34],"modalities.":[35],"Additionally,":[36],"different":[37],"tasks":[39],"exhibit":[40],"heterogeneous":[41],"preferences":[42],"during":[43],"information":[44,96,144],"decoding,":[45],"posing":[46],"a":[47,63,85,102,123,146],"critical":[48],"challenge":[49],"effectively":[51],"allocating":[52],"multi-scale":[53,143],"encoded":[54],"features.":[55],"To":[56],"address":[57],"these":[58],"limitations,":[59],"we":[60,83,115,139],"propose":[61],"CLIP-MT,":[62],"Multi-Modal":[64],"Knowledge-Driven":[65],"Adaptive":[66,118],"Scale":[67,119],"Feature":[68,89,148],"Allocation":[69],"for":[70],"Multi-Task":[71],"Dense":[72],"Prediction.":[73],"Specifically,":[74],"enrich":[76],"task-shared":[77],"features":[79,133],"with":[80],"multi-modal":[81,141],"knowledge,":[82],"introduce":[84],"novel":[86],"CLIP-Guided":[87],"Global":[88],"Enhancer":[90],"(CGGF),":[91],"which":[92],"leverages":[93],"aligned":[94],"text-image":[95],"augment":[98],"object-level":[99],"representations":[100],"through":[101,145],"dual-path":[103],"feature":[104],"fusion":[105],"architecture.":[106],"Furthermore,":[107],"tackle":[109],"task-specific":[111,136],"scale":[112],"preference":[113],"problem,":[114],"design":[116],"an":[117],"Selection":[120],"Gate":[121],"(ASSG),":[122],"learnable":[124],"gating":[125],"mechanism":[126],"that":[127,161],"dynamically":[128],"selects":[129],"high-":[130],"or":[131],"low-scale":[132],"based":[134],"demands.":[137],"Finally,":[138],"integrate":[140],"and":[142,157],"Task-Aware":[147],"Fusion":[149],"Module":[150],"(TAFF).":[151],"Extensive":[152],"experiments":[153],"NYUDv2":[156],"PASCAL-Context":[158],"datasets":[159],"demonstrate":[160],"CLIP-MT":[162],"achieves":[163],"state-of-the-art":[164],"performance,":[165],"outperforming":[166],"across":[169],"multiple":[170],"tasks.":[173]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}