{"id":"https://openalex.org/W7137950795","doi":"https://doi.org/10.1609/aaai.v40i9.37704","title":"R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios","display_name":"R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137950795","doi":"https://doi.org/10.1609/aaai.v40i9.37704"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37704","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37704","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37704","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129667045","display_name":"Zhu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Lu","raw_affiliation_strings":["Southern University of Science and Technology\nSpatialtemporal AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology\nSpatialtemporal AI","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668160","display_name":"Tiantian Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Geng","raw_affiliation_strings":["Southern University of Science and Technology\nUniversity of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology\nUniversity of Birmingham","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067518059","display_name":"Yangye Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangye Chen","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129670990","display_name":"Teng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Teng Wang","raw_affiliation_strings":["Southern University of Science and Technology\nThe University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology\nThe University of Hong Kong","institution_ids":["https://openalex.org/I3045169105","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704169","display_name":"Ping Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I75746372","display_name":"ZTE (United States)","ror":"https://ror.org/0518yg160","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098582","https://openalex.org/I75746372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Lu","raw_affiliation_strings":["ZTE Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZTE Corporation","institution_ids":["https://openalex.org/I75746372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129732890","display_name":"Feng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Southern University of Science and Technology\nSpatialtemporal AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology\nSpatialtemporal AI","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23321514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7627","last_page":"7635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9839000105857849,"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":0.9839000105857849,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0026000000070780516,"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/T10860","display_name":"Speech and Audio Processing","score":0.001500000013038516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6111000180244446},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.579200029373169},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5637000203132629},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5278000235557556},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.44040000438690186},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42250001430511475},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4074999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133999705314636},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364999771118164},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37704","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37704","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37704","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37704","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37704/41666","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37704","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37704","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2236135741","display_name":null,"funder_award_id":"2024YFE0203100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"rapid":[1],"advancements":[2],"have":[3],"been":[4],"made":[5],"in":[6,13,37,77,103,152,194],"multimodal":[7],"large":[8],"language":[9],"models":[10],"(MLLMs),":[11],"especially":[12],"video":[14,23],"understanding":[15],"tasks.":[16],"However,":[17],"current":[18],"research":[19],"focuses":[20],"on":[21,92],"simple":[22],"scenarios,":[24],"failing":[25],"to":[26,116,164],"reflect":[27],"the":[28,147,168,175],"complex":[29],"and":[30,72,106,184],"diverse":[31],"nature":[32],"of":[33,64,88,149,170],"real-world":[34,180],"audio-visual":[35,50,89,104,154,181],"events":[36],"videos.":[38],"To":[39,121,167],"bridge":[40],"this":[41,93,195],"gap,":[42],"we":[43,59,95,125],"firstly":[44],"introduce":[45],"R-AVST,":[46],"a":[47,61,128,187],"dataset":[48,177],"for":[49,100,179,190],"reasoning":[51,102],"featuring":[52],"fine-grained":[53],"spatio-temporal":[54,101,155,182],"annotations.":[55],"In":[56],"constructing":[57],"this,":[58],"design":[60],"pipeline":[62],"consisting":[63],"LLM-based":[65],"key":[66],"object":[67],"extraction,":[68],"automatic":[69],"spatial":[70],"annotation":[71],"manual":[73],"quality":[74],"inspection,":[75],"resulting":[76],"over":[78],"5K":[79],"untrimmed":[80],"videos":[81],"with":[82],"27K":[83],"objects":[84],"across":[85],"100":[86],"types":[87],"events.":[90],"Building":[91],"dataset,":[94],"define":[96],"three":[97],"core":[98],"tasks":[99],"scenes":[105],"generate":[107],"more":[108],"than":[109],"8K":[110],"high-quality,":[111],"evenly":[112],"distributed":[113],"question-answer":[114],"pairs":[115],"effectively":[117],"benchmark":[118],"model":[119,131],"performance.":[120],"further":[122],"enhance":[123],"reasoning,":[124,156,183],"propose":[126],"AVST-Zero,":[127],"reinforcement":[129],"learning-based":[130],"that":[132],"avoids":[133],"intermediate":[134],"supervision,":[135],"directly":[136],"optimizing":[137],"behavior":[138],"via":[139],"carefully":[140],"designed":[141,178],"multi-dimensional":[142],"rewards.":[143],"Extensive":[144],"experiments":[145],"validate":[146],"effectiveness":[148],"our":[150,171],"R-AVST":[151,173],"advancing":[153],"upon":[157],"which":[158],"AVST-Zero":[159,185],"demonstrates":[160],"competitive":[161],"performance":[162],"compared":[163],"existing":[165],"models.":[166],"best":[169],"knowledge,":[172],"is":[174],"first":[176],"offers":[186],"novel":[188],"perspective":[189],"tackling":[191],"future":[192],"challenges":[193],"domain.":[196]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-03-18T00:00:00"}