{"id":"https://openalex.org/W4415536913","doi":"https://doi.org/10.1145/3746027.3755077","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","display_name":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536913","doi":"https://doi.org/10.1145/3746027.3755077"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755077","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":"article","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/A5107079459","display_name":"Ling You","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ling You","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118983870","display_name":"Wenxuan Huang","orcid":"https://orcid.org/0009-0001-9656-813X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Huang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinni Xie","orcid":"https://orcid.org/0009-0007-5815-1062"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinni Xie","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangyi Wei","orcid":"https://orcid.org/0009-0006-7630-5558"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyi Wei","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049078901","display_name":"Bangyan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bangyan Li","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043643513","display_name":"Shaohui Lin","orcid":"https://orcid.org/0000-0003-0284-9940"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Lin","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709798","display_name":"Yang Li","orcid":"https://orcid.org/0000-0001-9427-7665"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063110936","display_name":"Changbo Wang","orcid":"https://orcid.org/0000-0001-8940-6418"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbo Wang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5107079459"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15991088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3418","last_page":"3427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9954000115394592,"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":0.736299991607666},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6061000227928162},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.5825999975204468},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41760000586509705},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.41200000047683716},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.39980000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202000260353088},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.736299991607666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5760999917984009},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755077","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":[{"id":"https://openalex.org/G4818587641","display_name":null,"funder_award_id":"62472178, 62376244","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2797664359","https://openalex.org/W2963916161","https://openalex.org/W3186413649","https://openalex.org/W4321193776","https://openalex.org/W4385800687","https://openalex.org/W4389519587","https://openalex.org/W4390873312","https://openalex.org/W4400490710","https://openalex.org/W4402241126","https://openalex.org/W4402702917","https://openalex.org/W4402754220"],"related_works":[],"abstract_inverted_index":{"Soccer":[0],"is":[1],"a":[2,80,126,147,159],"globally":[3],"popular":[4],"sporting":[5],"event,":[6],"typically":[7],"characterized":[8],"by":[9],"long":[10,138,174],"matches":[11],"and":[12,30,42,122,162,202],"distinctive":[13],"highlight":[14],"moments.":[15],"Recent":[16],"advances":[17],"in":[18,27,69,114,125,191],"Multimodal":[19],"Large":[20],"Language":[21],"Models":[22],"(MLLMs)":[23],"show":[24],"promising":[25],"capabilities":[26],"temporal":[28,40,55,175,200],"grounding":[29],"video":[31,68,139],"understanding.":[32],"However,":[33],"generating":[34,195],"soccer":[35,50,106,116,142],"commentary":[36,197],"requires":[37],"both":[38],"precise":[39],"localization":[41],"semantically":[43],"rich":[44],"descriptions":[45],"over":[46],"long-form":[47],"videos.":[48,117],"Existing":[49],"MLLMs":[51],"often":[52],"rely":[53],"on":[54,75,187],"priors":[56],"for":[57,108],"caption":[58],"generation,":[59],"which":[60],"limits":[61],"their":[62],"ability":[63,171],"to":[64,86,92,167,172],"process":[65],"the":[66,76,88,97,103,169,188],"entire":[67],"an":[70,192],"end-to-end":[71,105,193],"manner.":[72],"Traditional":[73],"approaches,":[74],"other":[77],"hand,":[78],"follow":[79],"complex":[81],"two-step":[82],"paradigm":[83],"that":[84,153,180],"fails":[85],"capture":[87],"global":[89,130],"context,":[90],"leading":[91],"suboptimal":[93],"performance.":[94],"To":[95,136],"solve":[96],"above":[98],"issues,":[99],"we":[100,144],"present":[101],"TimeSoccer,":[102],"first":[104],"MLLM":[107],"Single-anchor":[109],"Dense":[110],"Video":[111],"Captioning":[112],"(SDVC)":[113],"full-match":[115],"TimeSoccer":[118,182],"jointly":[119],"predicts":[120],"timestamps":[121],"generates":[123],"captions":[124],"single":[127],"pass,":[128],"enabling":[129],"context":[131],"modeling":[132],"across":[133],"45-minute":[134],"matches.":[135],"support":[137],"understanding":[140],"of":[141],"matches,":[143],"introduce":[145],"MoFA-Select,":[146],"training-free,":[148],"motion-aware":[149],"frame":[150],"compression":[151],"module":[152],"adaptively":[154],"selects":[155],"representative":[156],"frames":[157],"via":[158],"coarse-to-fine":[160],"strategy,":[161],"incorporates":[163],"complementary":[164],"training":[165],"paradigms":[166],"strengthen":[168],"model's":[170],"handle":[173],"sequences.":[176],"Extensive":[177],"experiments":[178],"demonstrate":[179],"our":[181],"achieves":[183],"State-of-The-Art":[184],"(SoTA)":[185],"performance":[186],"SDVC":[189],"task":[190],"form,":[194],"high-quality":[196],"with":[198],"accurate":[199],"alignment":[201],"strong":[203],"semantic":[204],"relevance.":[205],"For":[206],"more":[207],"information,":[208],"please":[209],"visit:":[210],"https://vpx-ecnu.github.io/TimeSoccer-Website/.":[211]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}