{"id":"https://openalex.org/W4415536721","doi":"https://doi.org/10.1145/3746027.3755055","title":"Balancing Cross-Modal Attention for Generalized Zero-Shot Learning","display_name":"Balancing Cross-Modal Attention for Generalized Zero-Shot Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536721","doi":"https://doi.org/10.1145/3746027.3755055"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755055","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/10.1145/3746027.3755055","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101545905","display_name":"Zhijie Rao","orcid":"https://orcid.org/0009-0003-9580-1133"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhijie Rao","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038505509","display_name":"Jingcai Guo","orcid":"https://orcid.org/0000-0002-0449-4525"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingcai Guo","raw_affiliation_strings":["Department of Computing & LSGI, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing & LSGI, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101545905"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17040689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3360","last_page":"3369"},"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":0.9990000128746033,"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":0.9990000128746033,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9330000281333923,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5841000080108643},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5525000095367432},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5063999891281128},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.43779999017715454},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.42640000581741333},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.3846000134944916},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3750999867916107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5967000126838684},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5796999931335449},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5525000095367432},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755055","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":{"id":"doi:10.1145/3746027.3755055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755055","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":27,"referenced_works":["https://openalex.org/W2070148066","https://openalex.org/W2108598243","https://openalex.org/W2118978333","https://openalex.org/W2141350700","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2440599146","https://openalex.org/W2552383788","https://openalex.org/W2596142952","https://openalex.org/W2963351448","https://openalex.org/W2963545832","https://openalex.org/W2963691377","https://openalex.org/W2963960318","https://openalex.org/W2982407353","https://openalex.org/W3035655772","https://openalex.org/W3096831136","https://openalex.org/W3143107425","https://openalex.org/W3203055845","https://openalex.org/W4200633401","https://openalex.org/W4304084141","https://openalex.org/W4312762894","https://openalex.org/W4312791158","https://openalex.org/W4312901050","https://openalex.org/W4382466082","https://openalex.org/W4384819681","https://openalex.org/W4386076660","https://openalex.org/W4402702970"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,88,169],"Generalized":[3],"Zero-Shot":[4],"Learning":[5],"have":[6],"demonstrated":[7],"promising":[8],"results":[9],"by":[10],"leveraging":[11],"cross-modal":[12],"attention":[13,36,48,55,79,116,150,161,178,189],"mechanisms":[14],"to":[15,34,59,66,82,120,147,163,184],"model":[16],"the":[17,83,92,122,187,199,202],"nuanced":[18],"relationships":[19],"between":[20],"semantic":[21],"attributes":[22,40,87,119],"and":[23,50,91,138,155],"visual":[24],"regions.":[25],"However,":[26],"we":[27,101],"find":[28],"that":[29],"inherent":[30],"attribute":[31],"imbalance":[32],"leads":[33,58],"significant":[35],"disparities,":[37],"i.e.,":[38],"those":[39],"with":[41,175],"less":[42],"sample":[43],"weights":[44],"often":[45],"exhibit":[46],"lower":[47],"confidence":[49],"poorer":[51],"localization":[52],"accuracy.":[53],"This":[54],"illusion":[56],"obviously":[57],"potential":[60],"degraded":[61],"or":[62,74],"even":[63],"counterproductive":[64],"contributions":[65],"category":[67],"determination.":[68],"Conventional":[69],"rebalancing":[70],"approaches":[71],"like":[72],"resampling":[73],"reweighting":[75],"are":[76],"ineffective":[77],"for":[78,152,165],"calibration":[80],"due":[81],"complex":[84],"interdependencies":[85],"among":[86],"one":[89],"object":[90],"absence":[93],"of":[94,125,190,201],"region-level":[95],"annotation":[96],"guidance.":[97],"In":[98],"this":[99],"paper,":[100],"propose":[102],"a":[103],"novel":[104],"coarse-to-fine":[105],"framework":[106],"termed":[107],"Hierarchical":[108],"Progressive":[109],"Attention":[110,136,141],"Network":[111],"(HPAN),":[112],"which":[113],"leverages":[114],"latent":[115],"consistency":[117],"across":[118],"rectify":[121],"focus":[123],"deviation":[124],"minor":[126,156],"attributes.":[127],"HPAN":[128],"comprises":[129],"two":[130],"synergistic":[131],"components,":[132],"Super-Attribute":[133],"Guided":[134],"Generable":[135],"(SGGA)":[137],"Rebalanced":[139],"Attribute":[140],"Calibration":[142],"(RAAC).":[143],"SGGA":[144],"employs":[145],"super-attributes":[146],"establish":[148],"unified":[149],"regions":[151],"both":[153],"major":[154],"attributes,":[157],"subsequently":[158],"propagating":[159],"these":[160],"masks":[162,179],"RAAC":[164,167],"calibration.":[166],"specializes":[168],"capturing":[170],"fine-grained":[171],"attribute-region":[172],"interaction":[173],"relations,":[174],"its":[176],"output":[177],"serving":[180],"as":[181],"supervisory":[182],"signals":[183],"iteratively":[185],"optimize":[186],"coarse":[188],"SGGA.":[191],"Extensive":[192],"experiments":[193],"on":[194],"three":[195],"benchmark":[196],"datasets":[197],"verify":[198],"effectiveness":[200],"proposed":[203],"method.":[204],"Code":[205],"is":[206],"available":[207],"at":[208],"github.com/zjrao/HPAN.":[209]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}