{"id":"https://openalex.org/W7138122487","doi":"https://doi.org/10.1609/aaai.v40i13.38031","title":"Seeing Is Believing: Grounding Long-Video Understanding in Spatio-Temporal Visual Evidence","display_name":"Seeing Is Believing: Grounding Long-Video Understanding in Spatio-Temporal Visual Evidence","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138122487","doi":"https://doi.org/10.1609/aaai.v40i13.38031"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38031","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38031","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38031","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129697904","display_name":"Zhaoyang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoyang Wei","raw_affiliation_strings":["University of the Chinese Academy of Sciences\nTencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences\nTencent","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064039971","display_name":"Guoliang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guoliang Wang","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122986169","display_name":"Guohua Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohua Gao","raw_affiliation_strings":["University of the Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031281125","display_name":"Yanchao Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanchao Hao","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698611","display_name":"Mingda Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingda Li","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102769588","display_name":"Wenchao Ding","orcid":"https://orcid.org/0000-0003-4249-526X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Ding","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129687665","display_name":"Xi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708326","display_name":"Shizhu He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhu He","raw_affiliation_strings":["University of the Chinese Academy of Sciences\nInstitute of automation, Chinese academy of science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences\nInstitute of automation, Chinese academy of science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129711588","display_name":"Xuehui Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehui Yu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5129697904"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39198856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10584","last_page":"10592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9916999936103821,"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":0.9916999936103821,"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":0.001500000013038516,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6449000239372253},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5145000219345093},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.41830000281333923},{"id":"https://openalex.org/keywords/fragility","display_name":"Fragility","score":0.4156999886035919},{"id":"https://openalex.org/keywords/speculation","display_name":"Speculation","score":0.3862999975681305},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3643999993801117},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3619999885559082},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.36079999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891999840736389},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C80191262","wikidata":"https://www.wikidata.org/wiki/Q5477668","display_name":"Fragility","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C47941915","wikidata":"https://www.wikidata.org/wiki/Q107885","display_name":"Speculation","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C104319648","wikidata":"https://www.wikidata.org/wiki/Q1412040","display_name":"Figure\u2013ground","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38031","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38031","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38031","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38031","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"Vision":[1],"Language":[2],"Models":[3],"(VLMs)":[4],"have":[5],"excelled":[6],"at":[7],"image":[8],"and":[9,27,53,92,107,163],"video":[10],"understanding,":[11],"applying":[12],"them":[13],"to":[14,38,73,87,137,194],"hour-long":[15],"videos":[16],"is":[17,58,77],"held":[18],"back":[19],"by":[20,60,64,79,126,158],"two":[21],"interrelated":[22,102],"challenges:":[23],"exorbitant":[24],"computational":[25],"expense":[26],"a":[28,112,119,159,164,190,199],"qualitative":[29],"breakdown":[30],"in":[31],"long-term":[32],"temporal":[33],"reasoning.":[34],"Thus,":[35],"models":[36,136],"tend":[37],"generate":[39],"answers":[40,139],"based":[41],"on":[42,177],"speculation":[43],"instead":[44],"of":[45,104],"solid":[46],"visual":[47,81,133],"facts,":[48],"causing":[49],"both":[50],"factually":[51],"incorrect":[52],"plausible":[54],"hallucinations.":[55],"This":[56,83],"problem":[57],"compounded":[59],"current":[61],"benchmarks":[62],"that,":[63],"only":[65,189],"emphasizing":[66],"final":[67],"answers,":[68],"lack":[69],"an":[70,127,148],"effective":[71,192],"mechanism":[72],"check":[74],"whether":[75],"reasoning":[76],"substantiated":[78],"specific":[80],"evidence.":[82],"makes":[84],"it":[85],"hard":[86],"differentiate":[88],"between":[89],"true":[90],"understanding":[91,196],"pretend":[93],"comprehension,":[94],"inhibiting":[95],"targeted":[96],"model":[97,105],"refinement.":[98],"To":[99],"address":[100],"these":[101],"challenges":[103],"fragility":[106],"evaluation":[108,128,202],"weakness,":[109],"we":[110,116,144],"adopt":[111],"twofold":[113],"strategy.":[114,167],"First,":[115],"present":[117],"EV\u00b2-Bench,":[118],"large-scale":[120],"benchmark":[121],"that":[122,153,171],"breaks":[123],"new":[124],"ground":[125],"paradigm":[129],"built":[130],"upon":[131],"spatio-temporal":[132],"evidence,":[134],"forcing":[135],"justify":[138],"with":[140],"checkable":[141],"hints.":[142],"Second,":[143],"put":[145],"forward":[146],"DynamicSelect,":[147],"adaptive":[149],"token":[150],"compression":[151,166],"system":[152],"efficiently":[154],"condenses":[155],"salient":[156],"information":[157],"dynamic":[160],"semantic":[161],"selector":[162],"hierarchical":[165],"Comprehensive":[168],"experiments":[169],"demonstrate":[170],"DynamicSelect":[172],"significantly":[173],"outperforms":[174],"the":[175,205],"baselines":[176],"EV\u00b2-Bench":[178],"as":[179,181],"well":[180],"other":[182],"public":[183],"benchmarks.":[184],"Our":[185],"study":[186],"offers":[187],"not":[188],"more":[191,200,208],"approach":[193],"long-video":[195],"but":[197],"also":[198],"stringent":[201],"paradigm,":[203],"indicating":[204],"way":[206],"toward":[207],"robust":[209],"models.":[210]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}