{"id":"https://openalex.org/W4387968591","doi":"https://doi.org/10.1145/3581783.3612159","title":"HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification","display_name":"HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968591","doi":"https://doi.org/10.1145/3581783.3612159"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.16244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045662308","display_name":"Shuyi Ouyang","orcid":"https://orcid.org/0000-0003-4507-4153"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuyi Ouyang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4507-4153","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078676052","display_name":"Hongyi Wang","orcid":"https://orcid.org/0000-0002-2336-1496"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2336-1496","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034985742","display_name":"Ziwei Niu","orcid":"https://orcid.org/0000-0003-0171-5158"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Niu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0171-5158","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042681907","display_name":"Zhenjia Bai","orcid":"https://orcid.org/0009-0008-3969-3007"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjia Bai","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-3969-3007","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066963650","display_name":"Shiao Xie","orcid":"https://orcid.org/0000-0002-5106-5512"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiao Xie","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5106-5512","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102747236","display_name":"Yingying Xu","orcid":"https://orcid.org/0000-0003-1217-0448"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Xu","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1217-0448","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057181928","display_name":"Ruofeng Tong","orcid":"https://orcid.org/0000-0002-8167-5354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruofeng Tong","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8167-5354","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044216245","display_name":"Yen\u2010Wei Chen","orcid":"https://orcid.org/0000-0002-5952-0188"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yen-Wei Chen","raw_affiliation_strings":["Ritsumeikan University, Kusatsu, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5952-0188","affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Kusatsu, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090814258","display_name":"Lanfen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanfen Lin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4098-588X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5045662308"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.2355,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53288873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4768","last_page":"4777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.7884828448295593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6616511344909668},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5256563425064087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5105739831924438},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49530115723609924},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4929633140563965},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48693525791168213},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47488492727279663},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4220591187477112},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4161180555820465},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36798396706581116},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34656137228012085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884828448295593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6616511344909668},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5256563425064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5105739831924438},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49530115723609924},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4929633140563965},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48693525791168213},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47488492727279663},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4220591187477112},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4161180555820465},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36798396706581116},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34656137228012085},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.16244","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16244","pdf_url":"https://arxiv.org/pdf/2407.16244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.16244","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16244","pdf_url":"https://arxiv.org/pdf/2407.16244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5268433318","display_name":null,"funder_award_id":"2020ND8AD01","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5417803145","display_name":null,"funder_award_id":"LZ22F020012","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968591.pdf","grobid_xml":"https://content.openalex.org/works/W4387968591.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W1962468782","https://openalex.org/W2007972815","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2410641892","https://openalex.org/W2412782625","https://openalex.org/W2521365688","https://openalex.org/W2560023338","https://openalex.org/W2560096627","https://openalex.org/W2788361849","https://openalex.org/W2890153145","https://openalex.org/W2932399282","https://openalex.org/W2943563866","https://openalex.org/W2963300078","https://openalex.org/W2963676620","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2979826702","https://openalex.org/W2982112268","https://openalex.org/W2997136715","https://openalex.org/W3035665101","https://openalex.org/W3035682985","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3102424508","https://openalex.org/W3138516171","https://openalex.org/W3167456680","https://openalex.org/W3170544306","https://openalex.org/W3170841864","https://openalex.org/W3171625335","https://openalex.org/W3192931333","https://openalex.org/W3205618423","https://openalex.org/W3211490618","https://openalex.org/W4214673031","https://openalex.org/W4214893857","https://openalex.org/W4304080876","https://openalex.org/W4312443924","https://openalex.org/W4312726009"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2565656575","https://openalex.org/W4200301313"],"abstract_inverted_index":{"The":[0,214],"task":[1],"of":[2,59,86,175,199],"multi-label":[3,79],"image":[4,80],"classification":[5,40,81],"involves":[6,158],"recognizing":[7],"multiple":[8,170],"objects":[9,67,133,174],"within":[10,52],"a":[11,35,53,129,143,159,185],"single":[12,54,130],"image.":[13,70],"Considering":[14],"both":[15],"valuable":[16],"semantic":[17,116],"information":[18],"contained":[19],"in":[20,28,38,47,68,78,109,113,180],"the":[21,29,44,69,84,114,196],"labels":[22],"and":[23,50,102,124,178,202],"essential":[24],"visual":[25,99,122],"features":[26,58,123,167],"presented":[27],"image,":[30,55],"tight":[31],"visual-linguistic":[32,111],"interactions":[33],"play":[34],"vital":[36],"role":[37],"improving":[39],"performance.":[41],"Moreover,":[42],"given":[43],"potential":[45],"variance":[46],"object":[48],"size":[49],"appearance":[51],"attention":[56,187],"to":[57,64,172],"different":[60,135],"scales":[61,171],"can":[62],"help":[63],"discover":[65],"possible":[66],"Recently,":[71],"Transformer-based":[72],"methods":[73,97,222],"have":[74,92,206],"achieved":[75],"great":[76],"success":[77],"by":[82],"leveraging":[83],"advantage":[85],"modeling":[87],"long-range":[88],"dependencies,":[89],"but":[90],"they":[91,119],"several":[93],"limitations.":[94],"Firstly,":[95],"existing":[96],"treat":[98],"feature":[100],"extraction":[101],"cross-modal":[103,126,193],"fusion":[104,127],"as":[105],"separate":[106],"steps,":[107],"resulting":[108],"insufficient":[110],"alignment":[112],"joint":[115,165,197],"space.":[117],"Additionally,":[118],"only":[120],"extract":[121],"perform":[125],"at":[128],"scale,":[131],"neglecting":[132],"with":[134,149,223],"characteristics.":[136],"To":[137],"address":[138],"these":[139],"issues,":[140],"we":[141],"propose":[142],"Hierarchical":[144],"Scale-Aware":[145],"Vision-Language":[146],"Transformer":[147],"(HSVLT)":[148],"two":[150],"appealing":[151],"designs:":[152],"(1)A":[153],"hierarchical":[154],"multi-scale":[155],"architecture":[156],"that":[157,190,218],"Cross-Scale":[160],"Aggregation":[161],"module,":[162],"which":[163],"leverages":[164],"multi-modal":[166,203],"extracted":[168],"from":[169],"recognize":[173],"varying":[176],"sizes":[177],"appearances":[179],"images.":[181],"(2)Interactive":[182],"Visual-Linguistic":[183],"Attention,":[184],"novel":[186],"mechanism":[188],"module":[189],"tightly":[191],"integrates":[192],"interaction,":[194],"enabling":[195],"updating":[198],"visual,":[200],"linguistic":[201],"features.":[204],"We":[205],"evaluated":[207],"our":[208],"method":[209],"on":[210],"three":[211],"benchmark":[212],"datasets.":[213],"experimental":[215],"results":[216],"demonstrate":[217],"HSVLT":[219],"surpasses":[220],"state-of-the-art":[221],"lower":[224],"computational":[225],"cost.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}