{"id":"https://openalex.org/W4403791648","doi":"https://doi.org/10.1145/3664647.3680829","title":"Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning","display_name":"Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791648","doi":"https://doi.org/10.1145/3664647.3680829"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680829","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680829","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680829","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069741268","display_name":"Xiangyan Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyan Qu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3658-8099","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672021","display_name":"Jing Yu","orcid":"https://orcid.org/0000-0002-3966-511X"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3966-511X","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066465215","display_name":"Keke Gai","orcid":"https://orcid.org/0000-0001-6784-0221"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Gai","raw_affiliation_strings":["School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6784-0221","affiliations":[{"raw_affiliation_string":"School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275773","display_name":"Jiamin Zhuang","orcid":"https://orcid.org/0000-0002-1598-0764"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Zhuang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1598-0764","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037051033","display_name":"Yuanmin Tang","orcid":"https://orcid.org/0000-0003-2849-1852"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanmin Tang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2849-1852","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115601598","display_name":"Gang Xiong","orcid":"https://orcid.org/0000-0002-3190-6521"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Xiong","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3190-6521","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052269317","display_name":"Gaopeng Gou","orcid":"https://orcid.org/0000-0002-3533-4874"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaopeng Gou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3533-4874","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Australia Institute of Machine Learning, University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"Australia Institute of Machine Learning, University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.778,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87615364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4581","last_page":"4590"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9668999910354614,"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/computer-science","display_name":"Computer science","score":0.718663215637207},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6578183770179749},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6043099761009216},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5413903594017029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5298157930374146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4608156085014343},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3647037744522095},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3268775939941406},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08876043558120728},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07033854722976685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718663215637207},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6578183770179749},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6043099761009216},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5413903594017029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298157930374146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4608156085014343},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3647037744522095},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3268775939941406},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08876043558120728},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07033854722976685},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680829","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680829","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680829","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680829","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1978394996","https://openalex.org/W2044913453","https://openalex.org/W2108598243","https://openalex.org/W2128532956","https://openalex.org/W2171061940","https://openalex.org/W2400717490","https://openalex.org/W2532958541","https://openalex.org/W2533598788","https://openalex.org/W2607642691","https://openalex.org/W2747329762","https://openalex.org/W2799215068","https://openalex.org/W2886710928","https://openalex.org/W2924476266","https://openalex.org/W2930957955","https://openalex.org/W2963486920","https://openalex.org/W2963499153","https://openalex.org/W2963545832","https://openalex.org/W2998708909","https://openalex.org/W3105935311","https://openalex.org/W3143107425","https://openalex.org/W3169480011","https://openalex.org/W3177525997","https://openalex.org/W4247950230","https://openalex.org/W4304084141","https://openalex.org/W4312283137","https://openalex.org/W4387968003","https://openalex.org/W4387968028","https://openalex.org/W4387968122"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Recent":[0],"work":[1],"shows":[2],"that":[3,33,168],"documents":[4,60],"from":[5,59,83],"encyclopedias":[6],"serve":[7],"as":[8],"helpful":[9],"auxiliary":[10],"information":[11,35,100],"for":[12,92,161],"zero-shot":[13,163],"learning.":[14,164],"Existing":[15],"methods":[16,152],"align":[17,64,132],"the":[18,65,89,97,106,142,172],"entire":[19,69],"semantics":[20],"of":[21,99],"a":[22,43,51,74],"document":[23,155],"with":[24],"corresponding":[25],"images":[26,62],"to":[27,54,78,110,120,130,137],"transfer":[28],"knowledge.":[29],"However,":[30],"they":[31],"disregard":[32],"semantic":[34,57,75,81,117,139],"is":[36,177],"not":[37],"equivalent":[38],"between":[39],"them,":[40],"resulting":[41],"in":[42,157],"suboptimal":[44],"alignment.":[45,94],"In":[46],"this":[47],"work,":[48],"we":[49,72,104,148,166],"propose":[50,73,105],"novel":[52],"network":[53],"extract":[55],"multi-view":[56,80],"concepts":[58,91],"and":[61,63,85,115,144],"matching":[66],"rather":[67],"than":[68],"concepts.":[70],"Specifically,":[71],"decomposition":[76],"module":[77],"generate":[79],"embeddings":[82],"visual":[84],"textual":[86],"sides,":[87],"providing":[88],"basic":[90],"partial":[93,174],"To":[95],"alleviate":[96],"issue":[98],"redundancy":[101],"among":[102,123],"embeddings,":[103],"local-to-semantic":[107],"variance":[108],"loss":[109,119],"capture":[111],"distinct":[112],"local":[113],"details":[114],"multiple":[116],"diversity":[118],"enforce":[121],"orthogonality":[122],"embeddings.":[124],"Subsequently,":[125],"two":[126,154],"losses":[127],"are":[128],"introduced":[129],"partially":[131],"visual-semantic":[133],"embedding":[134],"pairs":[135],"according":[136],"their":[138],"relevance":[140],"at":[141,179],"view":[143],"word-to-patch":[145],"levels.":[146],"Consequently,":[147],"consistently":[149],"outperform":[150],"state-of-the-art":[151],"under":[153],"sources":[156],"three":[158],"standard":[159],"benchmarks":[160],"document-based":[162],"Qualitatively,":[165],"show":[167],"our":[169],"model":[170],"learns":[171],"interpretable":[173],"association.":[175],"Code":[176],"available":[178],"https://github.com/MorningStarOvO/EmDepart.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
