{"id":"https://openalex.org/W4387969264","doi":"https://doi.org/10.1145/3581783.3612371","title":"MM-AU:Towards Multimodal Understanding of Advertisement Videos","display_name":"MM-AU:Towards Multimodal Understanding of Advertisement Videos","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969264","doi":"https://doi.org/10.1145/3581783.3612371"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612371","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612371","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612371","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059652479","display_name":"Digbalay Bose","orcid":"https://orcid.org/0000-0002-5281-1695"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Digbalay Bose","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085315115","display_name":"Rajat Hebbar","orcid":"https://orcid.org/0000-0002-0904-0573"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajat Hebbar","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059679122","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047152376","display_name":"Anfeng Xu","orcid":"https://orcid.org/0009-0001-5780-9797"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anfeng Xu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059652479"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.4232,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82950491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9968000054359436,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9950000047683716,"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":0.7600586414337158},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6210611462593079},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5690160393714905},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5043388605117798},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4800899624824524},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.4591512084007263},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4325343072414398},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41342025995254517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35146820545196533},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3260366916656494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.303777813911438},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09872156381607056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600586414337158},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6210611462593079},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5690160393714905},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5043388605117798},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4800899624824524},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.4591512084007263},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4325343072414398},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41342025995254517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35146820545196533},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3260366916656494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.303777813911438},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09872156381607056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612371","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612371","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":{"id":"doi:10.1145/3581783.3612371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612371","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612371","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308774","display_name":"John Simon Guggenheim Memorial Foundation","ror":"https://ror.org/0407tnq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969264.pdf","grobid_xml":"https://content.openalex.org/works/W4387969264.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W276347511","https://openalex.org/W570162864","https://openalex.org/W1596987789","https://openalex.org/W1927052826","https://openalex.org/W2002055708","https://openalex.org/W2003249666","https://openalex.org/W2005249702","https://openalex.org/W2044807399","https://openalex.org/W2064675550","https://openalex.org/W2097397553","https://openalex.org/W2129186114","https://openalex.org/W2252037843","https://openalex.org/W2476601196","https://openalex.org/W2579448560","https://openalex.org/W2593116425","https://openalex.org/W2742409927","https://openalex.org/W2751861701","https://openalex.org/W2753927079","https://openalex.org/W2895249420","https://openalex.org/W2962711930","https://openalex.org/W2963524571","https://openalex.org/W2974119277","https://openalex.org/W2981058299","https://openalex.org/W2990881710","https://openalex.org/W2999863388","https://openalex.org/W3093066905","https://openalex.org/W3094717204","https://openalex.org/W3099528782","https://openalex.org/W3104132365","https://openalex.org/W3104455028","https://openalex.org/W3119957342","https://openalex.org/W3174906557","https://openalex.org/W3196974791","https://openalex.org/W3207721319","https://openalex.org/W3216765867","https://openalex.org/W4243033101","https://openalex.org/W4312676283","https://openalex.org/W4313020336","https://openalex.org/W4319300292","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W1971486620"],"abstract_inverted_index":{"Advertisement":[0],"videos":[1,115],"(ads)":[2],"play":[3],"an":[4],"integral":[5],"part":[6],"in":[7,153],"the":[8,16,52,57,65,72,85,90,129,136],"domain":[9],"of":[10,18,44,67,74,87,93,112,131],"Internet":[11],"e-commerce,":[12],"as":[13,28],"they":[14],"amplify":[15],"reach":[17],"particular":[19],"products":[20],"to":[21,31,71,83,159,163],"a":[22,29,105],"broad":[23,53],"audience":[24],"or":[25],"can":[26],"serve":[27],"medium":[30],"raise":[32],"awareness":[33],"about":[34,51],"specific":[35],"issues":[36],"through":[37,128],"concise":[38],"narrative":[39,42],"structures.":[40],"The":[41],"structures":[43],"advertisements":[45,88],"involve":[46],"several":[47],"elements":[48],"like":[49],"reasoning":[50,126],"content":[54],"(topic":[55],"and":[56,60,76,99,151],"underlying":[58],"message)":[59],"examining":[61],"fine-grained":[62],"details":[63],"involving":[64],"transition":[66],"perceived":[68,96],"tone":[69,97],"due":[70],"sequence":[73],"events":[75],"interaction":[77],"among":[78],"characters.":[79],"In":[80],"this":[81],"work,":[82],"facilitate":[84],"understanding":[86],"along":[89],"three":[91],"dimensions":[92],"topic":[94],"categorization,":[95],"transition,":[98],"social":[100],"message":[101],"detection,":[102],"we":[103,140],"introduce":[104],"multimodal":[106,154],"multilingual":[107],"benchmark":[108],"called":[109],"MM-AU":[110],"comprised":[111],"8.4":[113],"K":[114],"(147hrs)":[116],"curated":[117],"from":[118,145],"multiple":[119,124,146],"web-based":[120],"sources.":[121],"We":[122],"explore":[123],"zero-shot":[125],"baselines":[127],"application":[130],"large":[132],"language":[133],"models":[134,157],"on":[135],"ads":[137],"transcripts.":[138],"Further,":[139],"demonstrate":[141],"that":[142],"leveraging":[143],"signals":[144],"modalities,":[147],"including":[148],"audio,":[149],"video,":[150],"text,":[152],"transformer-based":[155],"supervised":[156],"leads":[158],"improved":[160],"performance":[161],"compared":[162],"unimodal":[164],"approaches.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
