{"id":"https://openalex.org/W2808614953","doi":"https://doi.org/10.1145/3206025.3210498","title":"Multimedia Content Understanding by Learning from Very Few Examples","display_name":"Multimedia Content Understanding by Learning from Very Few Examples","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2808614953","doi":"https://doi.org/10.1145/3206025.3210498","mag":"2808614953"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3210498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3206025.3210498","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3210498","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3210498","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guo-Jun Qi","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100766907"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05898455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9395999908447266,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9276000261306763,"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":0.8437268137931824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6457682847976685},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6163474321365356},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5368649959564209},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5325837135314941},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5105370283126831},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5016069412231445},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47487872838974},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4656651020050049},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4602109491825104},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45753955841064453},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.434553861618042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8437268137931824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6457682847976685},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6163474321365356},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5368649959564209},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5325837135314941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5105370283126831},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5016069412231445},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47487872838974},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4656651020050049},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4602109491825104},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45753955841064453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.434553861618042},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3206025.3210498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3206025.3210498","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3210498","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3206025.3210498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3206025.3210498","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3206025.3210498","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G1793915314","display_name":"RI: Medium: Collaborative Research: Understanding and Editing Visual Sentiment","funder_award_id":"1704309","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808614953.pdf","grobid_xml":"https://content.openalex.org/works/W2808614953.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1971174658","https://openalex.org/W2099195351","https://openalex.org/W2385859805","https://openalex.org/W4256429076","https://openalex.org/W4295520087","https://openalex.org/W2726367589","https://openalex.org/W4311117049","https://openalex.org/W4223452531","https://openalex.org/W2770818364","https://openalex.org/W4308235896"],"abstract_inverted_index":{"In":[0,26,103],"this":[1],"tutorial,":[2],"the":[3,61,69,89,146],"speaker":[4],"will":[5,29,59,87,106,115,142],"present":[6],"serval":[7],"parallel":[8],"efforts":[9],"on":[10,81],"building":[11],"deep":[12],"learning":[13,46],"models":[14,80,96,121],"with":[15,20,47,99,138],"very":[16,100],"few":[17,48,101,139],"supervision":[18],"information,":[19],"or":[21],"without":[22],"unsupervised":[23,42],"data":[24],"available.":[25],"particular,":[27,104],"we":[28,105],"discuss":[30,60,88,107,117,143],"in":[31,144],"details.":[32],"(1)":[33],"Generative":[34],"Adverbial":[35],"Nets":[36],"(GANs)":[37],"and":[38,51,78],"their":[39],"applications":[40],"to":[41,76,93,97,119,131],"feature":[43],"extractions,":[44],"semi-supervised":[45,70],"labeled":[49],"examples":[50],"a":[52,133],"large":[53],"amount":[54],"of":[55,84,91,110],"unlabeled":[56],"data.":[57],"We":[58,86,114,141],"state-of-the-art":[62],"results":[63],"that":[64],"have":[65],"been":[66],"achieved":[67],"by":[68,124],"GANs.":[71],"(2)":[72],"Low-Shot":[73],"Learning":[74],"algorithms":[75],"train":[77,132],"test":[79],"disjoint":[82],"sets":[83],"tasks.":[85],"ideas":[90],"how":[92,118],"efficiently":[94],"adapt":[95],"tasks":[98],"examples.":[102],"several":[108],"paradigms":[109],"learning-to-learn":[111],"approaches.":[112],"(3)":[113],"also":[116],"transfer":[120,149],"across":[122],"modalities":[123,137],"leveraging":[125],"abundant":[126],"labels":[127],"from":[128],"one":[129],"modality":[130],"model":[134],"for":[135],"other":[136],"labels.":[140],"details":[145],"cross-modal":[147],"label":[148],"approach.":[150]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}