{"id":"https://openalex.org/W4415541274","doi":"https://doi.org/10.1145/3746027.3763762","title":"Higher-Order Vision-Language Fusion for Video Popularity Prediction","display_name":"Higher-Order Vision-Language Fusion for Video Popularity Prediction","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541274","doi":"https://doi.org/10.1145/3746027.3763762"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3763762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3763762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047948744","display_name":"Qisheng Xu","orcid":"https://orcid.org/0000-0003-4141-5950"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qisheng Xu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-4141-5950","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262862","display_name":"Binli Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binli Luo","raw_affiliation_strings":["Central South University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0002-9590-344X","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Zhou","orcid":"https://orcid.org/0009-0002-5808-5695"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhou","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0002-5808-5695","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zengming Lin","orcid":"https://orcid.org/0009-0008-9509-0235"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengming Lin","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0008-9509-0235","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hui Geng","orcid":"https://orcid.org/0009-0003-7046-2235"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Geng","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0003-7046-2235","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112917050","display_name":"Xianhan Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhan Tan","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-1719-5248","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33255101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14086","last_page":"14093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9958999752998352,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9958999752998352,"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":0.9955999851226807,"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":0.9876999855041504,"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/popularity","display_name":"Popularity","score":0.6019999980926514},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5928000211715698},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5769000053405762},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5507000088691711},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.40799999237060547},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3962000012397766},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349999785423279},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5200999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4011000096797943},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35199999809265137},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2984870255","wikidata":"https://www.wikidata.org/wiki/Q5196451","display_name":"User engagement","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C3020234875","wikidata":"https://www.wikidata.org/wiki/Q1260632","display_name":"Media content","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3763762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3763762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":19,"referenced_works":["https://openalex.org/W2619383789","https://openalex.org/W2899477876","https://openalex.org/W2911672342","https://openalex.org/W2963590343","https://openalex.org/W2970602317","https://openalex.org/W3007113923","https://openalex.org/W3017267450","https://openalex.org/W3042805811","https://openalex.org/W3099645789","https://openalex.org/W3120991986","https://openalex.org/W4308112567","https://openalex.org/W4383187404","https://openalex.org/W4387708435","https://openalex.org/W4387968554","https://openalex.org/W4388192780","https://openalex.org/W4402912714","https://openalex.org/W4403195287","https://openalex.org/W4403780546","https://openalex.org/W4403780710"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"the":[1,18,66,136,152,158,166],"popularity":[2],"of":[3,168],"social":[4,181],"media":[5,182],"videos":[6,23],"involves":[7],"estimating":[8],"user":[9,39,176],"engagement":[10],"based":[11],"on":[12],"rich":[13],"multimodal":[14],"information":[15],"embedded":[16],"within":[17],"posts.":[19],"Unlike":[20],"static":[21],"images,":[22],"incorporate":[24,127],"temporally":[25,102],"evolving":[26],"visual":[27,104],"signals":[28,140],"that,":[29],"alongside":[30],"associated":[31,91],"metadata":[32],"such":[33],"as":[34],"descriptions,":[35],"hashtags,":[36],"timestamps,":[37],"and":[38,58,69,86,90,131,175],"attributes,":[40],"offer":[41],"valuable":[42],"insights":[43],"into":[44,94],"their":[45],"potential":[46],"audience":[47],"reach.":[48],"Prior":[49],"approaches":[50],"typically":[51],"extract":[52],"features":[53,105],"from":[54],"different":[55],"modalities":[56],"independently":[57],"merge":[59],"them":[60],"via":[61],"na\u00efve":[62],"concatenation,":[63],"which":[64],"overlooks":[65],"semantic":[67,97,170],"discrepancy":[68],"interaction":[70],"dynamics":[71],"across":[72,172],"modalities.":[73],"To":[74],"address":[75],"these":[76],"limitations,":[77],"we":[78,126],"propose":[79],"a":[80,95],"feature":[81],"fusion":[82],"framework":[83],"that":[84,116,141],"encodes":[85],"aligns":[87],"video":[88,183],"content":[89,121,132],"textual":[92,108],"cues":[93],"shared":[96],"space.":[98],"By":[99],"jointly":[100],"modeling":[101],"structured":[103],"with":[106,138],"context-aware":[107],"embeddings,":[109],"our":[110,146],"method":[111,147],"effectively":[112],"captures":[113],"cross-modal":[114],"correlations":[115],"are":[117],"crucial":[118],"for":[119],"discerning":[120],"virality":[122],"patterns.":[123],"In":[124],"addition,":[125],"user-centric":[128],"behavioral":[129],"profiles":[130],"creation":[133],"dynamics,":[134],"enriching":[135],"representation":[137],"personalized":[139],"reflect":[142],"audience-specific":[143],"preferences.":[144],"Notably,":[145],"achieves":[148],"top-tier":[149],"performance":[150],"in":[151,178],"2025":[153],"SMP":[154],"challenge,":[155],"ranking":[156],"among":[157],"highest-performing":[159],"entries.":[160],"This":[161],"strong":[162],"empirical":[163],"result":[164],"underscores":[165],"value":[167],"deep":[169],"alignment":[171],"video,":[173],"text,":[174],"domains":[177],"accurately":[179],"forecasting":[180],"popularity.":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}