{"id":"https://openalex.org/W4415428267","doi":"https://doi.org/10.3233/faia251078","title":"STaR: Multi-Granular Spatio-Temporal Reasoning for Long-Form Dense Video Captioning","display_name":"STaR: Multi-Granular Spatio-Temporal Reasoning for Long-Form Dense Video Captioning","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428267","doi":"https://doi.org/10.3233/faia251078"},"language":null,"primary_location":{"id":"doi:10.3233/faia251078","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251078","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251078","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101788337","display_name":"Yihao Wu","orcid":"https://orcid.org/0009-0007-4051-8639"},"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":"Yihao Wu","raw_affiliation_strings":["Hangzhou Dianzi University"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019671611","display_name":"Chaocan Cai","orcid":"https://orcid.org/0000-0002-0463-4428"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Chenhuan Cai","raw_affiliation_strings":["University of Zurich"],"affiliations":[{"raw_affiliation_string":"University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051997091","display_name":"Liqi Yan","orcid":"https://orcid.org/0000-0002-7077-4947"},"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":"Liqi Yan","raw_affiliation_strings":["Hangzhou Dianzi University"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101517889","display_name":"Huapeng Li","orcid":"https://orcid.org/0000-0002-4394-2220"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Huapeng Li","raw_affiliation_strings":["University of Zurich"],"affiliations":[{"raw_affiliation_string":"University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024460899","display_name":"Jianhui Zhang","orcid":"https://orcid.org/0000-0001-6680-0949"},"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":["Hangzhou Dianzi University"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107913559","display_name":"J. B. Liu","orcid":"https://orcid.org/0009-0003-8197-0083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Liu","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055007304","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-5304-7975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012288206","display_name":"Fangli Guan","orcid":"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":["Hangzhou Dianzi University"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620221","display_name":"Pan Li","orcid":"https://orcid.org/0000-0002-9289-4712"},"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":["Hangzhou Dianzi University"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101788337"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6808104,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9918000102043152,"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":0.875},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7226999998092651},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5343000292778015},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.3959999978542328},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37059998512268066},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.361299991607666},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.35440000891685486}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126000165939331},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7226999998092651},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.600600004196167},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3959999978542328},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251078","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251078","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251078","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251078","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"video":[1,7],"captioning":[2],"is":[3,154],"crucial":[4],"for":[5],"enhancing":[6],"understanding":[8],"in":[9,17,30],"daily":[10],"applications":[11],"and":[12,35,81,88,92,110,142,148],"presents":[13],"a":[14,51,101],"significant":[15],"challenge":[16],"multimodal":[18],"analysis.":[19],"Existing":[20],"methods":[21],"often":[22],"overlook":[23],"video-to-dynamic-space":[24],"mapping":[25],"at":[26,156],"varying":[27],"scales,":[28],"resulting":[29],"captions":[31,144],"that":[32,135],"lack":[33],"specificity":[34],"remain":[36],"overly":[37],"general,":[38],"failing":[39],"to":[40,64,76,86,106,121],"capture":[41,77],"real-world":[42],"physical":[43],"detail.":[44],"To":[45],"address":[46],"this":[47],"limitation,":[48],"we":[49,96],"propose":[50],"multi-granularity":[52],"Spatio-Temporal":[53],"Reasoning":[54],"(STaR)":[55],"approach,":[56],"which":[57],"integrates:":[58],"(i)":[59],"efficient":[60],"global":[61],"feature":[62,84],"integration":[63],"model":[65,137],"long-term":[66],"temporal":[67,147],"dependencies,":[68],"(ii)":[69],"spatial":[70,79,93,149],"attention":[71],"mechanisms":[72],"with":[73,145],"position":[74],"encoding":[75],"absolute":[78],"information,":[80],"(iii)":[82],"cross-modal":[83],"fusion":[85],"align":[87],"unify":[89],"global,":[90],"local,":[91],"representations.":[94],"Moreover,":[95],"enhance":[97],"the":[98,108,113,123,126],"framework":[99],"using":[100],"Large":[102],"Language":[103],"Model":[104],"(LLM)":[105],"improve":[107],"richness":[109],"naturalness":[111],"of":[112,125],"generated":[114],"descriptions.":[115],"Comparative":[116],"experiments":[117],"have":[118],"been":[119],"conducted":[120],"evaluate":[122],"effectiveness":[124],"proposed":[127],"method":[128],"on":[129],"SoccerNet":[130],"dataset.":[131],"Experimental":[132],"results":[133],"demonstrate":[134],"our":[136],"effectively":[138],"enhances":[139],"localization":[140],"accuracy":[141],"generates":[143],"superior":[146],"detail":[150],"fidelity.":[151],"The":[152],"code":[153],"available":[155],"https://github.com/bread-555/STaR.":[157]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}