{"id":"https://openalex.org/W4415536729","doi":"https://doi.org/10.1145/3746027.3754573","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","display_name":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536729","doi":"https://doi.org/10.1145/3746027.3754573"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754573","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754573","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.03039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104024632","display_name":"Yiran Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Meng","raw_affiliation_strings":["Artificial Intelligence Academy, Sun Yat-Sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0001-5856-2490","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Academy, Sun Yat-Sen University, Zhuhai, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019083425","display_name":"Jiangang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Ye","raw_affiliation_strings":["Sun Yat-Sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0005-4188-2155","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077250575","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0003-3641-1429"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Cardiff University, Cardiff, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3641-1429","affiliations":[{"raw_affiliation_string":"Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030883042","display_name":"Guanghui Yue","orcid":"https://orcid.org/0000-0002-6761-8767"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Yue","raw_affiliation_strings":["School of Biomedical Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6761-8767","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006837984","display_name":"Xudong Mao","orcid":"https://orcid.org/0000-0002-1952-4176"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Mao","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0002-1952-4176","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000079751","display_name":"Ruomei Wang","orcid":"https://orcid.org/0000-0002-2712-4412"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruomei Wang","raw_affiliation_strings":["School of Software Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2712-4412","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102379113","display_name":"Baoquan Zhao","orcid":"https://orcid.org/0000-0002-0574-1663"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoquan Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0002-0574-1663","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"836","last_page":"845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9894000291824341,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8144000172615051},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7829999923706055},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5751000046730042},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5703999996185303},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.42660000920295715},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8144000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105999827384949},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7829999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.42660000920295715},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3754573","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754573","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"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:182479","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/view/cardiffauthors/A2824239D.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:arXiv.org:2508.03039","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03039","pdf_url":"https://arxiv.org/pdf/2508.03039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.03039","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03039","pdf_url":"https://arxiv.org/pdf/2508.03039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2333086965","display_name":null,"funder_award_id":"62302535, 62176223, 62371305","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2337252826","https://openalex.org/W4200631219","https://openalex.org/W4221166276","https://openalex.org/W4307838488","https://openalex.org/W4388188440","https://openalex.org/W4395470960","https://openalex.org/W4402727142","https://openalex.org/W4402727272","https://openalex.org/W4402961691","https://openalex.org/W4403878506","https://openalex.org/W4404782776"],"related_works":[],"abstract_inverted_index":{"Cross-video":[0],"question":[1],"answering":[2],"presents":[3],"significant":[4],"challenges":[5,35],"beyond":[6],"traditional":[7],"single-video":[8],"understanding,":[9],"particularly":[10],"in":[11,126,133,137,142],"establishing":[12],"meaningful":[13],"connections":[14],"across":[15,70],"video":[16,72],"streams":[17],"and":[18,62,88,140,144],"managing":[19],"the":[20],"complexity":[21],"of":[22],"multi-source":[23],"information":[24],"retrieval.":[25],"We":[26],"introduce":[27],"VideoForest,":[28],"a":[29,54,75,90,111],"novel":[30],"framework":[31,93],"that":[32,59,80,94],"addresses":[33],"these":[34],"through":[36],"person-anchored":[37],"hierarchical":[38,98],"reasoning,":[39],"enabling":[40],"effective":[41],"cross-video":[42,118,127],"understanding":[43],"without":[44],"requiring":[45],"end-to-end":[46],"training.":[47],"VideoForest":[48],"integrates":[49],"three":[50],"key":[51],"innovations:":[52],"1)":[53],"human-anchored":[55],"feature":[56],"extraction":[57],"mechanism":[58],"employs":[60],"ReID":[61],"tracking":[63],"algorithms":[64],"to":[65,100],"establish":[66],"robust":[67],"spatiotemporal":[68],"relationships":[69],"multiple":[71],"sources;":[73],"2)":[74],"multi-granularity":[76],"spanning":[77],"tree":[78],"structure":[79,99],"hierarchically":[81],"organizes":[82],"visual":[83],"content":[84],"around":[85],"person-level":[86],"trajectories;":[87],"3)":[89],"multi-agent":[91],"reasoning":[92,128],"efficiently":[95],"traverses":[96],"this":[97],"answer":[101],"complex":[102],"queries.":[103],"To":[104],"evaluate":[105],"our":[106],"method,":[107],"we":[108],"develop":[109],"CrossVideoQA,":[110],"comprehensive":[112],"benchmark":[113],"specifically":[114],"designed":[115],"for":[116],"person-centric":[117],"analysis.":[119],"Experimental":[120],"results":[121],"demonstrate":[122],"VideoForest's":[123],"superior":[124],"performance":[125],"tasks,":[129],"achieving":[130],"71.93%":[131],"accuracy":[132],"person":[134],"recognition,":[135],"83.75%":[136],"behavior":[138],"analysis,":[139],"51.67%":[141],"summarization":[143],"reasoning.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}