{"id":"https://openalex.org/W3206408630","doi":"https://doi.org/10.1145/3474085.3478561","title":"A Picture is Worth a Thousand Words","display_name":"A Picture is Worth a Thousand Words","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206408630","doi":"https://doi.org/10.1145/3474085.3478561","mag":"3206408630"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3478561","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/abs/2110.09756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067298679","display_name":"Yupan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupan Huang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China","Sun-Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun-Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378248","display_name":"Bei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Bei Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China","Sun-Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun-Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2792","last_page":"2794"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.991100013256073,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9866999983787537,"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":0.7798716425895691},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6435589790344238},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5491379499435425},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5235069394111633},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5090636610984802},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49604520201683044},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.455860435962677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4448765814304352},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.416059672832489},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3514491021633148},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24093744158744812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798716425895691},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6435589790344238},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5491379499435425},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5235069394111633},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5090636610984802},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49604520201683044},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.455860435962677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4448765814304352},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.416059672832489},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3514491021633148},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24093744158744812},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3478561","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"mag:3206408630","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09756","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3206408630","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09756","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2277195237","https://openalex.org/W2549599535","https://openalex.org/W2604178507","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2953106684","https://openalex.org/W2954841306","https://openalex.org/W2963981733","https://openalex.org/W2966792645","https://openalex.org/W2988975212","https://openalex.org/W2995404354","https://openalex.org/W3091588028","https://openalex.org/W3104152799","https://openalex.org/W3109579959","https://openalex.org/W4213019668"],"related_works":["https://openalex.org/W1241505","https://openalex.org/W6451020","https://openalex.org/W2530218","https://openalex.org/W6676372","https://openalex.org/W3906825","https://openalex.org/W3253406","https://openalex.org/W11288440","https://openalex.org/W14417179","https://openalex.org/W3729861","https://openalex.org/W8763"],"abstract_inverted_index":{"A":[0],"creative":[1],"image-and-text":[2,94],"generative":[3],"AI":[4,32],"system":[5,34,55,72,137],"mimics":[6],"humans'":[7],"extraordinary":[8],"abilities":[9],"to":[10,35,60,85,118,129],"provide":[11],"users":[12,44,67],"with":[13,51,75,96],"diverse":[14,38,77,140],"and":[15,40,48,123,142],"comprehensive":[16],"caption":[17],"suggestions,":[18],"as":[19,21,109],"well":[20],"rich":[22,41,58,102,143],"image":[23,47,59,103],"creations.":[24],"In":[25],"this":[26,87],"work,":[27],"we":[28],"demonstrate":[29],"such":[30],"an":[31,46,69],"creation":[33,104],"produce":[36],"both":[37,139],"captions":[39,63,108,117,141],"images.":[42],"When":[43],"imagine":[45],"associate":[49],"it":[50,74],"multiple":[52,76,107],"captions,":[53],"our":[54,71,90,136],"paints":[56],"a":[57,81,97,125],"reflect":[61],"all":[62],"faithfully.":[64],"Likewise,":[65],"when":[66],"upload":[68],"image,":[70],"depicts":[73],"captions.":[78],"We":[79,111],"propose":[80],"unified":[82],"multi-modal":[83],"framework":[84,91],"achieve":[86],"goal.":[88],"Specifically,":[89],"jointly":[92],"models":[93],"representations":[95],"Transformer":[98],"network,":[99],"which":[100],"supports":[101,138],"by":[105],"accepting":[106],"input.":[110],"consider":[112],"the":[113],"relations":[114],"among":[115],"input":[116],"encourage":[119],"diversity":[120],"in":[121],"training":[122],"adopt":[124],"non-autoregressive":[126],"decoding":[127],"strategy":[128],"enable":[130],"real-time":[131],"inference.":[132],"Based":[133],"on":[134],"these,":[135],"images":[144],"generations.":[145],"Our":[146],"code":[147],"is":[148],"available":[149],"online.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}