{"id":"https://openalex.org/W7204715181","doi":"https://doi.org/10.1038/s41598-026-68807-w","title":"Dense soccer video captioning with global context and player position awareness","display_name":"Dense soccer video captioning with global context and player position awareness","publication_year":2026,"publication_date":"2026-08-30","ids":{"openalex":"https://openalex.org/W7204715181","doi":"https://doi.org/10.1038/s41598-026-68807-w"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-68807-w","doi":"https://doi.org/10.1038/s41598-026-68807-w","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-68807-w","pdf_url":"https://www.nature.com/articles/s41598-026-68807-w_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-68807-w_reference.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129690050","display_name":"Chenyi Xu","orcid":"https://orcid.org/0009-0008-7915-9079","observed_orcids":["https://orcid.org/0009-0008-7915-9079"]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyi Xu","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148729325","display_name":"Yihao Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Wu","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133806150","display_name":"Liqi Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liqi Yan","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148756745","display_name":"Zhiyuan Bai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Bai","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148725779","display_name":"Qifan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI, Menlo Park, CA, 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, Menlo Park, CA, 94025, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012288206","display_name":"Fangli Guan","orcid":"https://orcid.org/0000-0001-7409-2129","observed_orcids":["https://orcid.org/0000-0001-7409-2129"]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangli Guan","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681112","display_name":"Jianhui Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Zhang","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148690949","display_name":"Pan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Li","raw_affiliation_strings":["College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5133806150"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9258000254631042,"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":0.9258000254631042,"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":0.06859999895095825,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0019000000320374966,"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/dense-captioning","display_name":"dense captioning","score":0.9390000104904175},{"id":"https://openalex.org/keywords/cross-modal-feature-fusion","display_name":"cross-modal feature fusion","score":0.9760000109672546}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9708999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406000137329102},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7731999754905701},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7265999913215637},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6736999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5273000001907349},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C2781368080","wikidata":"https://www.wikidata.org/wiki/Q501688","display_name":"Context awareness","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s41598-026-68807-w","doi":"https://doi.org/10.1038/s41598-026-68807-w","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-68807-w","pdf_url":"https://www.nature.com/articles/s41598-026-68807-w_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-68807-w","doi":"https://doi.org/10.1038/s41598-026-68807-w","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-68807-w","pdf_url":"https://www.nature.com/articles/s41598-026-68807-w_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6993468942","display_name":"\u9762\u5411\u81ea\u4e3b\u52a8\u6001\u4e09\u7ef4\u91cd\u5efa\u7684\u5177\u8eab\u667a\u80fd\u89c6\u89c9\u8bed\u8a00\u5bfc\u822a\u6280\u672f\u7814\u7a76","funder_award_id":"LQN25F020019","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321933","display_name":"Hainan Normal University","ror":"https://ror.org/031dhcv14"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204715181.pdf","grobid_xml":"https://content.openalex.org/works/W7204715181.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2519328139","https://openalex.org/W2619947201","https://openalex.org/W2729046720","https://openalex.org/W2969844053","https://openalex.org/W3022778813","https://openalex.org/W3175189620","https://openalex.org/W4221151978","https://openalex.org/W4285118488","https://openalex.org/W4308756504","https://openalex.org/W4400647706","https://openalex.org/W4402716120","https://openalex.org/W4413145855"],"related_works":["https://openalex.org/W4415536913","https://openalex.org/W4404350804","https://openalex.org/W4309880838","https://openalex.org/W4385800687","https://openalex.org/W2369254460","https://openalex.org/W4415428267","https://openalex.org/W7162368605","https://openalex.org/W4281484618","https://openalex.org/W4387846231","https://openalex.org/W7222832364"],"abstract_inverted_index":{"Abstract":[0],"Sports":[1],"video":[2,69,82],"captioning":[3,26,125],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,134,174],"understanding":[9],"and":[10,15,33,50,100,109,129,132,142,157],"describing":[11],"dynamic":[12],"visual":[13],"content,":[14],"it":[16],"is":[17],"particularly":[18],"challenging":[19],"for":[20,65,79,147,163],"long":[21],"soccer":[22,68,167],"broadcasts.":[23],"Existing":[24],"dense":[25,67],"methods":[27],"often":[28],"rely":[29],"on":[30,93],"local":[31],"clips":[32],"may":[34],"miss":[35],"match-level":[36],"temporal":[37,155],"context":[38,83,156],"or":[39],"player-position":[40,159],"cues,":[41],"which":[42],"can":[43],"lead":[44],"to":[45],"captions":[46],"with":[47,112],"insufficient":[48],"spatial":[49,89,110],"event-sequence":[51],"detail.":[52],"To":[53],"address":[54],"these":[55],"challenges,":[56],"we":[57],"propose":[58],"Spatio-Contextual":[59],"Perceiver":[60],"Resampler":[61],"(SCPR),":[62],"a":[63,113],"framework":[64],"single-anchored":[66],"captioning.":[70],"SCPR":[71,122],"combines":[72],"three":[73],"components:":[74],"(1)":[75],"global-local":[76],"feature":[77,103],"integration":[78],"incorporating":[80],"long-range":[81],"around":[84],"each":[85],"caption":[86],"anchor;":[87],"(2)":[88],"position":[90],"encoding":[91],"based":[92],"the":[94,119,135],"absolute":[95],"2D":[96],"locations":[97],"of":[98],"players;":[99],"(3)":[101],"cross-modal":[102],"fusion":[104],"that":[105,153],"aligns":[106],"global,":[107],"local,":[108],"features":[111],"trainable":[114],"language":[115],"decoder.":[116],"Evaluated":[117],"under":[118],"SoccerNet-Caption":[120],"protocol,":[121],"improves":[123],"several":[124],"metrics,":[126],"especially":[127],"CIDEr,":[128],"increases":[130],"recall":[131],"F1":[133],"spotting":[136],"stage,":[137],"while":[138,169],"some":[139],"strict":[140],"localization":[141],"ROUGE-style":[143],"metrics":[144],"remain":[145],"stronger":[146],"competing":[148],"baselines.":[149],"These":[150],"results":[151],"suggest":[152],"global":[154],"explicit":[158],"cues":[160],"are":[161],"useful":[162],"generating":[164],"more":[165],"detailed":[166],"commentaries,":[168],"also":[170],"revealing":[171],"remaining":[172],"trade-offs":[173],"precise":[175],"timestamp":[176],"localization.":[177]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-31T00:00:00"}
