{"id":"https://openalex.org/W4387968685","doi":"https://doi.org/10.1145/3581783.3612263","title":"Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences","display_name":"Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968685","doi":"https://doi.org/10.1145/3581783.3612263"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612263","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":["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/A5045597655","display_name":"Dingyi Yang","orcid":"https://orcid.org/0009-0006-8924-5259"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dingyi Yang","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061707215","display_name":"Hongyu Chen","orcid":"https://orcid.org/0009-0001-7682-1775"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Chen","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090399594","display_name":"X. Hou","orcid":"https://orcid.org/0000-0002-5116-3454"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglin Hou","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027308029","display_name":"Tiezheng Ge","orcid":"https://orcid.org/0000-0003-1381-2692"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Ge","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883869","display_name":"Yuning Jiang","orcid":"https://orcid.org/0000-0003-1665-3025"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuning Jiang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045597655"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.597,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69777093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5705","last_page":"5715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9966999888420105,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9779000282287598,"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/closed-captioning","display_name":"Closed captioning","score":0.9176394939422607},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.8536142706871033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8074231147766113},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6799335479736328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.633354902267456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5757697224617004},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5432899594306946},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49555838108062744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4635564386844635},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4520568251609802},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4456619620323181},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44290027022361755},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.41997456550598145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3480374813079834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3210276961326599},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2666066884994507}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9176394939422607},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.8536142706871033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074231147766113},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6799335479736328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633354902267456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5757697224617004},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5432899594306946},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49555838108062744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4635564386844635},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4520568251609802},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4456619620323181},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44290027022361755},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.41997456550598145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3480374813079834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3210276961326599},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2666066884994507},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612263","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4668466387","display_name":null,"funder_award_id":"6207246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8390650537","display_name":null,"funder_award_id":"62072462","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1631260214","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2138621090","https://openalex.org/W2187089797","https://openalex.org/W2425121537","https://openalex.org/W2600463316","https://openalex.org/W2625940279","https://openalex.org/W2822349497","https://openalex.org/W2890231609","https://openalex.org/W2955956881","https://openalex.org/W2963062932","https://openalex.org/W2963267809","https://openalex.org/W2982260276","https://openalex.org/W2997248215","https://openalex.org/W3205021045","https://openalex.org/W3206055785","https://openalex.org/W3206723373","https://openalex.org/W4283274728","https://openalex.org/W4285606530","https://openalex.org/W4304080462","https://openalex.org/W4319317262","https://openalex.org/W6600433979"],"related_works":["https://openalex.org/W2529311304","https://openalex.org/W4248275646","https://openalex.org/W4210416330","https://openalex.org/W2992609826","https://openalex.org/W3124809058","https://openalex.org/W2552900035","https://openalex.org/W2162875951","https://openalex.org/W2062875858","https://openalex.org/W4380047323","https://openalex.org/W2138330538"],"abstract_inverted_index":{"Stylized":[0,83],"visual":[1,34,126,172,199],"captioning":[2,200],"aims":[3,87],"to":[4,70,88,142,160,207,224],"generate":[5,89,143,161,180],"image":[6],"or":[7],"video":[8],"descriptions":[9,163],"with":[10,23,57],"specific":[11],"styles,":[12],"making":[13],"them":[14],"more":[15],"attractive":[16],"and":[17,64,124,156,170,204],"emotionally":[18],"appropriate.":[19],"One":[20],"major":[21],"challenge":[22],"this":[24,115],"task":[25],"is":[26],"the":[27,65,79,154,166,186],"lack":[28],"of":[29,81],"paired":[30],"stylized":[31,162,182],"captions":[32,67,90,183],"for":[33,114,196],"content,":[35],"so":[36],"most":[37],"existing":[38],"works":[39],"focus":[40],"on":[41,48,146,165,213],"unsupervised":[42],"methods":[43],"that":[44,60,209],"do":[45],"not":[46],"rely":[47],"parallel":[49],"datasets.":[50],"However,":[51],"these":[52,75],"approaches":[53,203],"still":[54],"require":[55],"training":[56,131],"sufficient":[58],"examples":[59,99],"have":[61],"style":[62,140,144,168,187,215],"labels,":[63],"generated":[66],"are":[68,205,210],"limited":[69],"predefined":[71],"styles.":[72,227],"To":[73],"address":[74],"limitations,":[76],"we":[77,137,152],"explore":[78],"problem":[80],"Few-Shot":[82],"Visual":[84],"Captioning,":[85],"which":[86,117],"in":[91],"any":[92],"desired":[93,181],"style,":[94],"using":[95],"only":[96],"a":[97,110,119,125,139],"few":[98],"as":[100,134],"guidance":[101],"during":[102],"inference,":[103,176],"without":[104],"requiring":[105],"further":[106,219],"training.":[107],"We":[108],"propose":[109],"framework":[111],"called":[112],"FS-StyleCap":[113],"task,":[116],"utilizes":[118],"conditional":[120],"encoder-decoder":[121],"language":[122],"model":[123,178],"projection":[127],"module.":[128],"Our":[129,192],"two-step":[130],"scheme":[132],"proceeds":[133],"follows:":[135],"first,":[136],"train":[138],"extractor":[141,155],"representations":[145],"an":[147],"unlabeled":[148],"text-only":[149],"corpus.":[150],"Then,":[151],"freeze":[153],"enable":[157],"our":[158,177,221],"decoder":[159],"based":[164],"extracted":[167],"vector":[169],"projected":[171],"content":[173],"vectors.":[174],"During":[175],"can":[179],"by":[184],"deriving":[185],"representation":[188],"from":[189],"user-supplied":[190],"examples.":[191],"automatic":[193],"evaluation":[194],"results":[195],"few-shot":[197],"sentimental":[198],"outperform":[201],"state-of-the-art":[202],"comparable":[206],"models":[208],"fully":[211],"trained":[212],"labeled":[214],"corpora.":[216],"Human":[217],"evaluations":[218],"confirm":[220],"model's":[222],"ability":[223],"handle":[225],"multiple":[226]},"counts_by_year":[{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}