{"id":"https://openalex.org/W3200604919","doi":"https://doi.org/10.1145/3474085.3479218","title":"Multi-modal Representation Learning for Video Advertisement Content Structuring","display_name":"Multi-modal Representation Learning for Video Advertisement Content Structuring","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3200604919","doi":"https://doi.org/10.1145/3474085.3479218","mag":"3200604919"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3479218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479218","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.06637","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Daya Guo","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":true,"raw_author_name":"Daya Guo","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhaoyang Zeng","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":"Zhaoyang Zeng","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.1938,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49657989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4770","last_page":"4774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.8222000002861023},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6025000214576721},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.602400004863739},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5569999814033508},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.8222000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212000131607056},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5569999814033508},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.27459999918937683},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3479218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479218","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":"pmh:oai:arXiv.org:2109.06637","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.06637","pdf_url":"https://arxiv.org/pdf/2109.06637","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.06637","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.06637","pdf_url":"https://arxiv.org/pdf/2109.06637","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2097117768","https://openalex.org/W2336403884","https://openalex.org/W2526050071","https://openalex.org/W2883429621","https://openalex.org/W2962677524","https://openalex.org/W2968928822","https://openalex.org/W2983918066","https://openalex.org/W2984008963","https://openalex.org/W2997706915"],"related_works":[],"abstract_inverted_index":{"Video":[0,153],"advertisement":[1,10],"content":[2,36,168],"structuring":[3,50],"aims":[4],"to":[5,60,82,112],"segment":[6,14],"a":[7,57],"given":[8],"video":[9,29,44,65,128,174],"and":[11,23,33,39,46,71,99,122,144,171],"label":[12],"each":[13,120],"on":[15,74,147],"various":[16],"dimensions,":[17],"such":[18],"as":[19],"presentation":[20],"form,":[21],"scene,":[22],"style.":[24],"Different":[25],"from":[26,64],"real-life":[27],"videos,":[28],"advertisements":[30,66,175],"contain":[31],"sufficient":[32],"useful":[34],"multi-modal":[35,58,62,75,110,167],"like":[37,169],"caption":[38,170],"speech,":[40],"which":[41],"provides":[42],"crucial":[43],"semantics":[45],"would":[47],"enhance":[48],"the":[49,88,108,126,148,178],"process.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,77,92,102],"propose":[56],"encoder":[59,111],"learn":[61],"representation":[63],"by":[67,96],"interacting":[68],"between":[69,116],"video-audio":[70],"text.":[72],"Based":[73],"representation,":[76],"then":[78],"apply":[79],"Boundary-Matching":[80],"Network":[81],"generate":[83],"temporal":[84,114],"proposals.":[85],"To":[86],"make":[87],"proposals":[89,95],"more":[90],"accurate,":[91],"refine":[93],"generated":[94],"scene-guided":[97],"alignment":[98],"re-ranking.":[100],"Finally,":[101],"incorporate":[103],"proposal":[104,121],"located":[105],"embeddings":[106],"into":[107],"introduced":[109],"capture":[113],"relationships":[115],"local":[117],"features":[118,124],"of":[119,125,150],"global":[123],"whole":[127],"for":[129],"classification.":[130],"Experimental":[131],"results":[132],"show":[133],"that":[134,165],"our":[135],"method":[136],"achieves":[137],"significantly":[138,176],"improvement":[139],"compared":[140],"with":[141],"several":[142],"baselines":[143],"Rank":[145],"1":[146],"task":[149],"Multi-modal":[151],"Ads":[152],"Understanding":[154],"in":[155,173],"ACM":[156],"Multimedia":[157],"2021":[158],"Grand":[159],"Challenge.":[160],"Ablation":[161],"study":[162],"further":[163],"shows":[164],"leveraging":[166],"speech":[172],"improve":[177],"performance.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-09-27T00:00:00"}