{"id":"https://openalex.org/W4400529471","doi":"https://doi.org/10.1145/3626772.3661350","title":"Enhancing Baidu Multimodal Advertisement with Chinese Text-to-Image Generation via Bilingual Alignment and Caption Synthesis","display_name":"Enhancing Baidu Multimodal Advertisement with Chinese Text-to-Image Generation via Bilingual Alignment and Caption Synthesis","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400529471","doi":"https://doi.org/10.1145/3626772.3661350"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3661350","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3661350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103326213","display_name":"Kang Zhao","orcid":"https://orcid.org/0009-0000-3053-3965"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Zhao","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3053-3965","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102734030","display_name":"Xinyu Zhao","orcid":"https://orcid.org/0009-0000-0253-5488"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhao","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0253-5488","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725735","display_name":"Zhipeng Jin","orcid":"https://orcid.org/0009-0003-0863-2539"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Jin","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0863-2539","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747784","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0001-5077-4782"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5077-4782","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325818","display_name":"Wen Tao","orcid":"https://orcid.org/0009-0002-5481-4512"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Tao","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5481-4512","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011745550","display_name":"Cong Han","orcid":"https://orcid.org/0009-0003-6516-1139"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6516-1139","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086810479","display_name":"Shuanglong Li","orcid":"https://orcid.org/0009-0002-7346-5258"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuanglong Li","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7346-5258","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034880019","display_name":"Lin Liu","orcid":"https://orcid.org/0009-0003-7305-8940"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7305-8940","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2855","last_page":"2859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9929999709129333,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9878000020980835,"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":0.7338413000106812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5247645378112793},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4520558714866638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4316824674606323},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4217183291912079},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.338601291179657},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07151120901107788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7338413000106812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5247645378112793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4520558714866638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4316824674606323},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4217183291912079},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.338601291179657},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07151120901107788}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3661350","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3661350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2117340018","https://openalex.org/W2512971201","https://openalex.org/W3154430790","https://openalex.org/W4206238894","https://openalex.org/W4291125268","https://openalex.org/W4301045096","https://openalex.org/W4306316995","https://openalex.org/W4318147416","https://openalex.org/W4366344047","https://openalex.org/W4384652685","https://openalex.org/W4386059972","https://openalex.org/W4390873054"],"related_works":["https://openalex.org/W2908364646","https://openalex.org/W2275271759","https://openalex.org/W2014532210","https://openalex.org/W1992760298","https://openalex.org/W2767629806","https://openalex.org/W2319899002","https://openalex.org/W2953463546","https://openalex.org/W2187359640","https://openalex.org/W2354585676","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,173],"generative":[3],"artificial":[4],"intelligence":[5],"have":[6],"revolutionized":[7],"information":[8],"retrieval":[9],"and":[10,64,69,108,126,165],"content":[11,70],"generation,":[12],"opening":[13],"up":[14],"new":[15],"opportunities":[16],"for":[17,43,82],"the":[18,32,120,145,149,155],"e-commerce":[19],"industry.":[20],"In":[21],"particular,":[22],"text-to-image":[23,117],"generation":[24,34,80,118,150],"models":[25],"offer":[26],"a":[27,78,90,115,127,135,191],"novel":[28],"approach":[29],"to":[30,53,99,122,142],"guiding":[31],"image":[33,67,85,92,163,166,188],"process":[35,141],"using":[36,124],"natural":[37],"language":[38],"input,":[39],"which":[40,61],"is":[41,62],"inspiring":[42],"multimodal":[44,48,129,138],"search":[45,49,83],"advertising.":[46],"Traditional":[47],"ads":[50,185],"require":[51],"advertisers":[52],"prepare":[54,89],"ad":[55,59,84],"creatives,":[56],"such":[57],"as":[58],"images,":[60],"time-consuming":[63],"requires":[65],"uniform":[66],"specifications":[68],"quality":[71],"inspection.":[72],"To":[73],"this":[74],"end,":[75],"we":[76,88,112,133],"propose":[77],"streamlined":[79],"framework":[81,172],"creatives.":[86],"First,":[87],"Chinese":[91,116],"caption":[93],"model":[94],"with":[95,148,186],"high-quality":[96,106],"image-caption":[97],"pairs":[98],"bootstrap":[100],"training":[101],"data":[102],"refinement.":[103],"With":[104],"curated":[105],"images":[107],"synthesized":[109],"descriptive":[110],"captions,":[111],"then":[113],"train":[114],"model,":[119],"largest":[121],"date,":[123],"SDXL":[125],"10-billion":[128],"text":[130,146],"encoder.":[131],"Specifically,":[132],"introduce":[134],"two-stage":[136],"bilingual":[137],"representation":[139],"alignment":[140],"seamlessly":[143],"integrate":[144],"encoder":[147],"model.":[151],"Extensive":[152],"experiments":[153],"validate":[154],"effectiveness":[156],"of":[157,162,170],"our":[158,171],"framework,":[159],"including":[160],"assessments":[161],"captioning":[164],"generation.":[167],"The":[168],"implementation":[169],"Baidu":[174],"Search":[175],"Ads":[176],"shows":[177],"significant":[178],"revenue":[179],"increase,":[180],"For":[181],"example,":[182],"beauty":[183],"industry":[184],"generated":[187],"creatives":[189],"achieve":[190],"29%":[192],"higher":[193],"click-through":[194],"rate":[195],"(CTR).":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}