{"id":"https://openalex.org/W4412394948","doi":"https://doi.org/10.1145/3726302.3731957","title":"Retrieval-Augmented Image Captioning and Generation with Entity Concepts Enhancement for Baidu Multimodal Advertising","display_name":"Retrieval-Augmented Image Captioning and Generation with Entity Concepts Enhancement for Baidu Multimodal Advertising","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412394948","doi":"https://doi.org/10.1145/3726302.3731957"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3731957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3731957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731957","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th 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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731957","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lei Shen","orcid":"https://orcid.org/0009-0005-8510-7572"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Shen","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0005-8510-7572","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","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/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/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/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/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":"middle","author":{"id":"https://openalex.org/A5082529620","display_name":"Zhongmin Cai","orcid":"https://orcid.org/0000-0002-4903-3992"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongmin Cai","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-4903-3992","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4324","last_page":"4328"},"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":0.9986000061035156,"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":0.9977999925613403,"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":0.9625764489173889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973471879959106},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5231608152389526},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4667993187904358},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4505501389503479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3909912109375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3693086504936218},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33908113837242126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32379424571990967}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9625764489173889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973471879959106},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5231608152389526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4667993187904358},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4505501389503479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3909912109375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693086504936218},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33908113837242126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32379424571990967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3731957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3731957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731957","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3731957","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3731957","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3731957","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412394948.pdf","grobid_xml":"https://content.openalex.org/works/W4412394948.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2963966654","https://openalex.org/W2998702515","https://openalex.org/W3080510735","https://openalex.org/W3211032667","https://openalex.org/W4251167157","https://openalex.org/W4308623137","https://openalex.org/W4312933868","https://openalex.org/W4366123788","https://openalex.org/W4386065803","https://openalex.org/W4386076004","https://openalex.org/W4398160873","https://openalex.org/W4400529471","https://openalex.org/W4402703029","https://openalex.org/W4402753874","https://openalex.org/W4402754015","https://openalex.org/W4403582537","https://openalex.org/W6600007113"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,11,30,38,73,110,173,185,193,202],"generative":[3],"artificial":[4],"intelligence":[5],"are":[6],"driving":[7],"a":[8,92,145],"significant":[9,213],"transformation":[10],"information":[12],"retrieval":[13],"and":[14,43,62,78,177,221],"content":[15,32,95],"generation,":[16],"creating":[17],"substantial":[18],"opportunities":[19],"for":[20,100,218],"online":[21,101],"advertising.":[22],"Text-to-image":[23],"generation":[24,96,179],"technology":[25],"has":[26,211],"become":[27],"increasingly":[28],"prevalent":[29],"advertising":[31,84,102,194],"production,":[33],"demonstrating":[34,170],"promising":[35],"performance":[36,172],"improvements":[37],"terms":[39],"of":[40,54,81,117,167,188,190,199,207],"semantic":[41],"relevance":[42],"visual":[44],"appeal.":[45],"However,":[46],"existing":[47,182],"models":[48],"often":[49],"suffer":[50],"from":[51],"inadequate":[52],"representation":[53],"entity":[55,111,139,155],"concepts,":[56],"such":[57],"as":[58],"prominent":[59],"product":[60],"brands":[61],"recognizable":[63],"landmarks.":[64],"This":[65],"inherent":[66],"limitation":[67],"subsequently":[68],"leads":[69],"to":[70,137,157,181,215],"notable":[71],"deficiencies":[72],"brand":[74],"tonality,":[75],"industry-specific":[76],"relevance,":[77],"market":[79],"adaptability":[80],"the":[82,108,165,186,197,200,203,222],"generated":[83],"content.":[85],"To":[86],"address":[87],"this":[88],"challenge,":[89],"we":[90],"propose":[91],"multimodal":[93,130],"ad":[94],"framework":[97,114,201],"specifically":[98],"engineered":[99],"system,":[103],"particularly":[104,184],"focused":[105],"on":[106,129,150],"resolving":[107],"deficiency":[109],"concepts.":[112],"Our":[113],"is":[115],"comprised":[116],"two":[118],"phases:":[119],"first,":[120],"an":[121],"image":[122,142,160,175,178],"captioning":[123,176],"module":[124],"with":[125,154],"entity-aware":[126],"learning":[127],"based":[128],"large":[131],"language":[132],"model,":[133],"leveraging":[134],"retrieval-augmented":[135],"techniques":[136],"incorporate":[138],"concepts":[140,156],"into":[141],"descriptions;":[143],"second,":[144],"text-to-image":[146],"diffusion":[147],"model":[148],"refined":[149],"image-text":[151],"pairs":[152],"enriched":[153],"facilitate":[158],"entity-grounded":[159],"generation.":[161],"Extensive":[162],"experiments":[163],"validate":[164],"effectiveness":[166],"our":[168],"framework,":[169],"superior":[171],"both":[174,219],"compared":[180],"methods,":[183],"accuracy":[187],"depiction":[189],"relevant":[191],"entities":[192],"images.":[195],"Moreover,":[196],"deployment":[198],"system":[204],"primary":[205],"traffic":[206],"Baidu":[208],"Search":[209],"Ads,":[210],"brought":[212],"enhancements":[214],"advertisement":[216],"revenue":[217],"advertisers":[220],"platform.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}