{"id":"https://openalex.org/W4414856492","doi":"https://doi.org/10.1109/tmm.2025.3618542","title":"Unleashing the Potential of Hierarchical Region Clues for Open-Vocabulary Multi-Label Classification","display_name":"Unleashing the Potential of Hierarchical Region Clues for Open-Vocabulary Multi-Label Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414856492","doi":"https://doi.org/10.1109/tmm.2025.3618542"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3618542","doi":"https://doi.org/10.1109/tmm.2025.3618542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618542","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,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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"},"volume":null,"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/A5072105606","display_name":"Peirong Ma","orcid":"https://orcid.org/0000-0001-6391-7527","observed_orcids":["https://orcid.org/0000-0001-6391-7527"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peirong Ma","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6391-7527","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031121165","display_name":"Wu Ran","orcid":"https://orcid.org/0000-0001-8478-0750","observed_orcids":["https://orcid.org/0000-0001-8478-0750"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Ran","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8478-0750","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960599","display_name":"Zhiquan He","orcid":"https://orcid.org/0000-0002-6674-6003","observed_orcids":["https://orcid.org/0000-0002-6674-6003"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiquan He","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6674-6003","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Pu","orcid":"https://orcid.org/0000-0002-0892-1213","observed_orcids":["https://orcid.org/0000-0002-0892-1213"]},"institutions":[{"id":"https://openalex.org/I133868755","display_name":"Shanghai Medical College of Fudan University","ror":"https://ror.org/01zntxs11","country_code":"CN","type":"education","lineage":["https://openalex.org/I133868755","https://openalex.org/I24943067"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Pu","raw_affiliation_strings":["Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0892-1213","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I133868755","https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070355771","display_name":"Hong Lu","orcid":"https://orcid.org/0000-0002-4572-2854","observed_orcids":["https://orcid.org/0000-0002-4572-2854"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Lu","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4572-2854","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19733225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"9832","last_page":"9846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8481000065803528,"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":0.8481000065803528,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.10379999876022339,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03150000050663948,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-pre-training","display_name":"vision-language pre-training","score":0.7639999985694885},{"id":"https://openalex.org/keywords/region-selection","display_name":"region selection","score":0.7450000047683716},{"id":"https://openalex.org/keywords/unseen-class-generalization","display_name":"unseen class generalization","score":0.7269999980926514},{"id":"https://openalex.org/keywords/multi-label-image-recognition","display_name":"multi-label image recognition","score":0.5680000185966492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112000226974487},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7415000200271606},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.633899986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6308000087738037},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5228999853134155},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.483599990606308},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C2780217385","wikidata":"https://www.wikidata.org/wiki/Q2389284","display_name":"Hierarchical organization","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3618542","doi":"https://doi.org/10.1109/tmm.2025.3618542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618542","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,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7143284523","display_name":"\u52a8\u6001\u573a\u666f\u4e2d\u673a\u5668\u4eba\u663e\u8457\u6027\u76ee\u6807\u8bc6\u522b\u4e0e\u8868\u8fbe\u6280\u672f\u7814\u7a76","funder_award_id":"62072112","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2250539671","https://openalex.org/W2413850928","https://openalex.org/W2577784528","https://openalex.org/W2770962865","https://openalex.org/W2912423076","https://openalex.org/W2997136715","https://openalex.org/W3034978279","https://openalex.org/W3035524453","https://openalex.org/W3035665101","https://openalex.org/W3114005958","https://openalex.org/W3124902415","https://openalex.org/W3163811911","https://openalex.org/W3167456680","https://openalex.org/W3169149706","https://openalex.org/W3173859428","https://openalex.org/W3176136157","https://openalex.org/W3194842893","https://openalex.org/W3198377975","https://openalex.org/W3210123923","https://openalex.org/W3212203927","https://openalex.org/W4200374933","https://openalex.org/W4210314542","https://openalex.org/W4214673031","https://openalex.org/W4288083516","https://openalex.org/W4293202648","https://openalex.org/W4312310776","https://openalex.org/W4312458986","https://openalex.org/W4312629998","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4321021726","https://openalex.org/W4377000427","https://openalex.org/W4382450414","https://openalex.org/W4386066010","https://openalex.org/W4386075561","https://openalex.org/W4386076029","https://openalex.org/W4386076046","https://openalex.org/W4386076156","https://openalex.org/W4386159669","https://openalex.org/W4390872587","https://openalex.org/W4390874207"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"multi-label":[1,31,66,133,138,195],"classification":[2,139,142,196],"(OV-MLC)":[3],"aims":[4],"to":[5,16,56,95,115,179,191,208],"leverage":[6],"the":[7,19,27,45,58,73,80,98,147,161,214,235],"rich":[8,61],"multi-modal":[9],"knowledge":[10],"from":[11,76],"Vision-language":[12],"pre-training":[13],"(VLP)":[14],"models":[15],"further":[17],"improve":[18],"recognition":[20,123],"ability":[21],"for":[22,167,220],"unseen":[23,221],"(novel)":[24],"classes":[25],"beyond":[26],"training":[28],"set":[29],"in":[30,65,79,83,131,185],"scenarios.":[32],"Existing":[33],"OV-MLC":[34,93],"methods":[35],"only":[36],"perform":[37],"predictions":[38,162],"on":[39,225],"single":[40],"hierarchical":[41,62,102,110,118,153],"regions,":[42],"and":[43,68],"aggregate":[44],"prediction":[46],"scores":[47],"of":[48,60,100,124,143,163,217],"these":[49],"regions":[50,78,184],"through":[51],"simpletop-kmean":[52],"pooling.":[53],"This":[54],"fails":[55],"unleash":[57],"potential":[59],"region":[63,103,145,166,175],"clues":[64],"images":[67],"does":[69],"not":[70],"fully":[71,96],"exploit":[72],"discriminative":[74],"information":[75],"all":[77],"image,":[81,148],"resulting":[82],"sub-optimal":[84],"performance.":[85],"In":[86,198],"this":[87],"work,":[88],"we":[89,106,149,200],"propose":[90,201],"a":[91,109,132,151,173,202],"novel":[92,152],"framework":[94],"harness":[97],"power":[99],"multiple":[101,125],"clues.":[104],"Specifically,":[105],"first":[107],"design":[108],"clue":[111],"gathering":[112],"(HCG)":[113],"module":[114],"gather":[116],"different":[117,129],"clues,":[119],"enabling":[120],"more":[121],"precise":[122],"object":[126],"categories":[127],"with":[128],"sizes":[130],"image.":[134],"Then,":[135],"by":[136],"viewing":[137],"as":[140],"single-label":[141],"each":[144,164,168],"within":[146],"present":[150],"score":[154],"aggregation":[155],"(HSA)":[156],"approach,":[157],"thereby":[158],"better":[159],"utilizing":[160],"image":[165,187],"class.":[169],"We":[170],"also":[171],"utilize":[172],"well-designed":[174],"selection":[176],"strategy":[177,207],"(RSS)":[178],"eliminate":[180],"noise":[181],"or":[182],"background":[183],"an":[186],"that":[188,230],"are":[189],"irrelevant":[190],"classification,":[192],"achieving":[193],"higher":[194],"accuracy.":[197],"addition,":[199],"hybrid":[203],"prompt":[204],"learning":[205],"(HPL)":[206],"enhance":[209],"visual-semantic":[210],"consistency":[211],"while":[212],"preserving":[213],"generalization":[215],"capability":[216],"label":[218],"embeddings":[219],"classes.":[222],"Extensive":[223],"experiments":[224],"public":[226],"benchmark":[227],"datasets":[228],"demonstrate":[229],"our":[231],"method":[232],"significantly":[233],"outperforms":[234],"current":[236],"state-of-the-art.":[237]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}