{"id":"https://openalex.org/W3205131834","doi":"https://doi.org/10.1145/3462244.3479965","title":"Semi-supervised Visual Feature Integration for Language Models through Sentence Visualization","display_name":"Semi-supervised Visual Feature Integration for Language Models through Sentence Visualization","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3205131834","doi":"https://doi.org/10.1145/3462244.3479965","mag":"3205131834"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3479965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"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/A5070202314","display_name":"Lisai Zhang","orcid":"https://orcid.org/0000-0002-2902-9515"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lisai Zhang","raw_affiliation_strings":["Intelligent Computing Research Center, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Computing Research Center, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895423","display_name":"Qingcai Chen","orcid":"https://orcid.org/0000-0001-8473-7293"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":["Intelligenet Computing Research Center, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligenet Computing Research Center, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060382408","display_name":"Joanna Siebert","orcid":"https://orcid.org/0000-0001-6276-3642"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joanna Siebert","raw_affiliation_strings":["Intelligenet Computing Research Center, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligenet Computing Research Center, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014238603","display_name":"Buzhou Tang","orcid":"https://orcid.org/0000-0003-0271-8246"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Buzhou Tang","raw_affiliation_strings":["Intelligenet Computing Research Center, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligenet Computing Research Center, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070202314"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210144487"],"apc_list":null,"apc_paid":null,"fwci":0.4803,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65364379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"682","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9962999820709229,"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/T10028","display_name":"Topic Modeling","score":0.9905999898910522,"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":0.8675283193588257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6686930656433105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6510986089706421},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5861552953720093},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5365080833435059},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48470401763916016},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4659263789653778},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44781494140625},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.41709965467453003},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07133403420448303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675283193588257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6686930656433105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6510986089706421},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5861552953720093},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5365080833435059},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48470401763916016},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4659263789653778},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44781494140625},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.41709965467453003},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07133403420448303},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3462244.3479965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1840435438","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2020755048","https://openalex.org/W2112184938","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2143623448","https://openalex.org/W2145056192","https://openalex.org/W2149056056","https://openalex.org/W2149557440","https://openalex.org/W2194775991","https://openalex.org/W2250742840","https://openalex.org/W2250770256","https://openalex.org/W2568389463","https://openalex.org/W2739181657","https://openalex.org/W2745461083","https://openalex.org/W2778940641","https://openalex.org/W2782345990","https://openalex.org/W2798881773","https://openalex.org/W2806055002","https://openalex.org/W2950178297","https://openalex.org/W2953106684","https://openalex.org/W2953276893","https://openalex.org/W2963264012","https://openalex.org/W2963371565","https://openalex.org/W2963991017","https://openalex.org/W2964126458","https://openalex.org/W2969876226","https://openalex.org/W2998356391","https://openalex.org/W3090449556"],"related_works":["https://openalex.org/W1872130062","https://openalex.org/W2293457016","https://openalex.org/W2977842567","https://openalex.org/W2567044968","https://openalex.org/W159132833","https://openalex.org/W2808571346","https://openalex.org/W2033261979","https://openalex.org/W87581401","https://openalex.org/W2411652523","https://openalex.org/W2950819771"],"abstract_inverted_index":{"Integrating":[0],"visual":[1,36,47],"features":[2,48],"has":[3],"been":[4],"proved":[5],"useful":[6],"for":[7,39,77,138,147],"natural":[8,106],"language":[9,16,41,94,100,107,121,149],"understanding":[10],"tasks.":[11],"Nevertheless,":[12],"most":[13],"existing":[14],"multimodal":[15,148],"models":[17],"highly":[18],"rely":[19],"on":[20,22,104],"training":[21],"aligned":[23,75,136],"image":[24,130],"and":[25,55,71,89,109,132],"text":[26],"data.":[27],"In":[28,43],"this":[29],"paper,":[30],"we":[31],"propose":[32],"a":[33,52,68,144],"novel":[34],"semi-supervised":[35,69],"integration":[37,64],"framework":[38,70,83,116,126],"pre-trained":[40],"models.":[42,122],"the":[44,46,63,78,82,93,98,118,139],"framework,":[45],"are":[49],"obtained":[50],"through":[51],"sentence":[53],"visualization":[54],"vision-language":[56],"fusion":[57],"mechanism.":[58],"The":[59],"uniqueness":[60],"includes:":[61],"1)":[62],"is":[65],"conducted":[66],"via":[67],"does":[72,133],"not":[73,91,134],"require":[74,135],"images":[76,137],"processed":[79,140],"sentences.":[80],"2)":[81],"works":[84],"as":[85],"an":[86,129],"auxiliary":[87],"component,":[88],"will":[90],"affect":[92],"processing":[95],"ability":[96],"of":[97],"integrated":[99],"model.":[101],"Experimental":[102],"results":[103],"both":[105],"inference":[108],"reading":[110],"comprehension":[111],"tasks":[112],"demonstrate":[113],"that":[114,124],"our":[115,125],"improves":[117],"strong":[119],"baseline":[120],"Considering":[123],"only":[127],"requires":[128],"database,":[131],"texts,":[141],"it":[142],"provides":[143],"feasible":[145],"way":[146],"learning.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}