{"id":"https://openalex.org/W7167944662","doi":"https://doi.org/10.1145/3805712.3808387","title":"ATVG: Agentic System for Factually Grounded Travel Advertisement Video Generation","display_name":"ATVG: Agentic System for Factually Grounded Travel Advertisement Video Generation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167944662","doi":"https://doi.org/10.1145/3805712.3808387"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808387","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th 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://doi.org/10.1145/3805712.3808387","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106008668","display_name":"Byung Eun Jeon","orcid":"https://orcid.org/0009-0002-4151-8896"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byung Eun Jeon","raw_affiliation_strings":["Snap Inc., Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0002-4151-8896","affiliations":[{"raw_affiliation_string":"Snap Inc., Seattle, USA","institution_ids":["https://openalex.org/I4210142583","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581308","display_name":"Xiao Bai","orcid":"https://orcid.org/0000-0002-7491-2454"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Bai","raw_affiliation_strings":["Snap Inc., Palo Alto, USA"],"raw_orcid":"https://orcid.org/0000-0002-7491-2454","affiliations":[{"raw_affiliation_string":"Snap Inc., Palo Alto, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444409","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0002-8934-3346"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]},{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["Snap Inc., Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0002-8934-3346","affiliations":[{"raw_affiliation_string":"Snap Inc., Bellevue, USA","institution_ids":["https://openalex.org/I4210108985","https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101494431","display_name":"Jinchao Li","orcid":"https://orcid.org/0000-0003-1378-2788"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]},{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinchao Li","raw_affiliation_strings":["Snap Inc., Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0002-1116-9923","affiliations":[{"raw_affiliation_string":"Snap Inc., Bellevue, USA","institution_ids":["https://openalex.org/I4210108985","https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":1,"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":"5166","last_page":"5170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5917999744415283,"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":0.5917999744415283,"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":0.1607999950647354,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06019999831914902,"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/clips","display_name":"CLIPS","score":0.6976000070571899},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5719000101089478},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.35499998927116394},{"id":"https://openalex.org/keywords/contextual-advertising","display_name":"Contextual advertising","score":0.3163999915122986},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.3109000027179718},{"id":"https://openalex.org/keywords/online-video","display_name":"Online video","score":0.29760000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156999707221985},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.6976000070571899},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5196999907493591},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.35499998927116394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C70133500","wikidata":"https://www.wikidata.org/wiki/Q1815904","display_name":"Contextual advertising","level":4,"score":0.3163999915122986},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808387","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808387","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.49730661511421204,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4409361136","https://openalex.org/W7160089983"],"related_works":[],"abstract_inverted_index":{"Consumer":[0],"content":[1],"platforms":[2],"and":[3,89,113,127,136],"advertisers":[4],"stand":[5],"to":[6,93,103],"benefit":[7],"from":[8,54],"generating":[9],"high-quality":[10],"video":[11,17,52,85,143],"ads":[12,53],"at":[13],"scale,":[14],"but":[15],"current":[16],"generation":[18,91],"systems":[19],"often":[20],"produce":[21],"structurally":[22],"unreliable":[23],"or":[24],"factually":[25,40],"incorrect":[26],"outputs":[27,92],"that":[28,49,75,123],"can":[29,148],"degrade":[30],"the":[31,99,117,140,145],"viewer":[32],"experience.":[33],"We":[34,115],"propose":[35],"ATVG":[36],"(Agentic":[37],"system":[38,48,60,118],"for":[39,131],"grounded":[41],"Travel":[42],"advertisement":[43],"Video":[44],"Generation),":[45],"an":[46,69,77],"agentic":[47,108],"generates":[50],"travel":[51],"only":[55],"a":[56,104,120],"city":[57],"name.":[58],"The":[59,142],"plans":[61],"clips":[62,67],"across":[63],"multiple":[64],"themes;":[65],"grounds":[66],"via":[68,87],"LLM-guided":[70],"iterative":[71],"image":[72],"retrieval":[73],"process":[74],"selects":[76],"anchor":[78],"image;":[79],"expands":[80],"lightweight":[81],"concepts":[82],"into":[83],"detailed":[84],"prompts":[86],"meta-prompts;":[88],"verifies":[90],"detect":[94],"visual":[95],"artifacts":[96,126],"before":[97],"assembling":[98],"final":[100],"video.":[101],"Compared":[102],"single-prompt":[105],"baseline,":[106],"our":[107],"approach":[109],"improves":[110],"multi-scene":[111],"composition":[112],"factuality.":[114],"demonstrate":[116],"through":[119],"web":[121,146],"app":[122,147],"exposes":[124],"intermediate":[125],"full":[128],"agent":[129],"logs":[130],"20":[132],"cities,":[133],"covering":[134],"popular":[135],"long-tail":[137],"cities":[138],"around":[139],"world.":[141],"demonstrating":[144],"be":[149],"found":[150],"at:":[151],"https://www.youtube.com/watch?v=-yh_jBDmhGo.":[152]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-07-11T00:00:00"}