{"id":"https://openalex.org/W4415536635","doi":"https://doi.org/10.1145/3746027.3755556","title":"EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction","display_name":"EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536635","doi":"https://doi.org/10.1145/3746027.3755556"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755556","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/2510.21786","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101481753","display_name":"Q. Su","orcid":"https://orcid.org/0000-0002-7761-3636"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qile Su","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7761-3636","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shoutai Zhu","orcid":"https://orcid.org/0009-0009-6800-0908"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoutai Zhu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6800-0908","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Zhang","orcid":"https://orcid.org/0009-0001-8549-3179"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8549-3179","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082007071","display_name":"Baoyu Liang","orcid":"https://orcid.org/0000-0002-2365-589X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyu Liang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2365-589X","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038117386","display_name":"Chao Tong","orcid":"https://orcid.org/0000-0003-4414-4965"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Tong","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China and State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4414-4965","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China and State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4698","last_page":"4707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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":0.9968000054359436,"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/event","display_name":"Event (particle physics)","score":0.6430000066757202},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5259000062942505},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.3905999958515167},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3626999855041504},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.35569998621940613},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3522000014781952},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3384000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187000155448914},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5809999704360962},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.427700012922287},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3626999855041504},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755556","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755556","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:arXiv.org:2510.21786","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21786","pdf_url":"https://arxiv.org/pdf/2510.21786","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:2510.21786","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21786","pdf_url":"https://arxiv.org/pdf/2510.21786","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/G2282956519","display_name":null,"funder_award_id":"62176016,72274127","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2158794898","https://openalex.org/W2194775991","https://openalex.org/W2810685774","https://openalex.org/W2895833243","https://openalex.org/W2962935746","https://openalex.org/W3021013305","https://openalex.org/W3034679267","https://openalex.org/W3153389197","https://openalex.org/W3181951703","https://openalex.org/W3205786327","https://openalex.org/W3213949621","https://openalex.org/W4214555767","https://openalex.org/W4293547730","https://openalex.org/W4307925598","https://openalex.org/W4388979610"],"related_works":[],"abstract_inverted_index":{"Script":[0],"event":[1,9,112,133,148,174],"induction,":[2],"which":[3,93,177],"aims":[4],"to":[5,114,144],"predict":[6],"the":[7,12,35,51,125,145,181,189,211,214,217,220,233,239],"subsequent":[8],"based":[10,172],"on":[11,207],"context,":[13],"is":[14,44,128],"a":[15,45,66,89,131,168],"challenging":[16],"task":[17,67,215],"in":[18,23,34,50],"NLP,":[19],"achieving":[20],"remarkable":[21],"success":[22],"practical":[24],"applications.":[25],"However,":[26],"human":[27],"events":[28,184],"are":[29,160],"mostly":[30],"recorded":[31],"and":[32,83,100,185,188,216,235,241],"presented":[33],"form":[36],"of":[37,47,53,79,95,106,140,147,213,219],"videos":[38,99],"rather":[39],"than":[40,102],"scripts,":[41],"yet":[42],"there":[43],"lack":[46],"related":[48],"research":[49],"realm":[52],"vision.":[54],"To":[55],"address":[56],"this":[57,116],"problem,":[58],"we":[59],"introduce":[60],"AVEP":[61],"(Action-centric":[62],"Video":[63],"Event":[64],"Prediction),":[65],"that":[68,153],"distinguishes":[69],"itself":[70],"from":[71],"existing":[72,110],"video":[73,104,111,141,173,200,227],"prediction":[74,175,201,228],"tasks":[75],"through":[76],"its":[77],"incorporation":[78],"more":[80,101,121],"complex":[81],"logic":[82],"richer":[84],"semantic":[85],"information.":[86],"We":[87,165,194,230],"present":[88],"large":[90],"structured":[91,138],"dataset,":[92],"consists":[94],"about":[96],"35K":[97],"annotated":[98],"178K":[103],"clips":[105],"event,":[107],"built":[108],"upon":[109],"datasets":[113],"support":[115],"task.":[117],"The":[118],"dataset":[119,234],"offers":[120],"fine-grained":[122],"annotations,":[123],"where":[124],"atomic":[126],"unit":[127],"represented":[129],"as":[130,158,203,205],"multimodal":[132],"argument":[134],"node,":[135],"providing":[136],"better":[137],"representations":[139],"events.":[142],"Due":[143],"complexity":[146,212],"structures,":[149],"traditional":[150],"visual":[151],"models":[152,202],"take":[154],"patches":[155],"or":[156],"frames":[157],"input":[159],"not":[161],"well-suited":[162],"for":[163,237],"AVEP.":[164],"propose":[166],"EventFormer,":[167],"node-graph":[169],"hierarchical":[170],"attention":[171],"model,":[176],"can":[178],"capture":[179],"both":[180,210],"relationships":[182,191],"between":[183,192],"their":[186],"arguments":[187],"coreferencial":[190],"arguments.":[193],"conducted":[195],"experiments":[196,240],"using":[197],"several":[198],"SOTA":[199],"well":[204],"LVLMs":[206],"AVEP,":[208],"demonstrating":[209],"value":[218],"dataset.":[221],"Our":[222],"approach":[223],"outperforms":[224],"all":[225],"these":[226],"models.":[229],"will":[231],"release":[232],"code":[236],"replicating":[238],"annotations.":[242]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}