{"id":"https://openalex.org/W4401634027","doi":"https://doi.org/10.1109/tcsvt.2024.3444895","title":"Object-Centric Cross-Modal Knowledge Reasoning for Future Event Prediction in Videos","display_name":"Object-Centric Cross-Modal Knowledge Reasoning for Future Event Prediction in Videos","publication_year":2024,"publication_date":"2024-08-16","ids":{"openalex":"https://openalex.org/W4401634027","doi":"https://doi.org/10.1109/tcsvt.2024.3444895"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3444895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3444895","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013311511","display_name":"Chenghang Lai","orcid":"https://orcid.org/0000-0001-9181-9334"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenghang Lai","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102353589","display_name":"Haibo Wang","orcid":"https://orcid.org/0009-0008-4690-3375"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Wang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647216","display_name":"Weifeng Ge","orcid":"https://orcid.org/0009-0000-6627-5101"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Ge","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing and the School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013311511"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.735,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71334741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"34","issue":"12","first_page":"13324","last_page":"13337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9926000237464905,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9832000136375427,"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/computer-science","display_name":"Computer science","score":0.7504204511642456},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6356843709945679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5576422810554504},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.48469188809394836},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4405933618545532},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.403107613325119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504204511642456},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6356843709945679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5576422810554504},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.48469188809394836},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4405933618545532},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.403107613325119},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3444895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3444895","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4690267869","display_name":null,"funder_award_id":"62176061","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":55,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2133459682","https://openalex.org/W2214124602","https://openalex.org/W2277195237","https://openalex.org/W2886641317","https://openalex.org/W2896659472","https://openalex.org/W2952132648","https://openalex.org/W3021065276","https://openalex.org/W3096383329","https://openalex.org/W3097683561","https://openalex.org/W3106534186","https://openalex.org/W3106884574","https://openalex.org/W3119777426","https://openalex.org/W3126721948","https://openalex.org/W3163971663","https://openalex.org/W3176641147","https://openalex.org/W3181951703","https://openalex.org/W3204588463","https://openalex.org/W4205157616","https://openalex.org/W4205510032","https://openalex.org/W4285125423","https://openalex.org/W4292263758","https://openalex.org/W4312560592","https://openalex.org/W4322576752","https://openalex.org/W4379984087","https://openalex.org/W4385801664","https://openalex.org/W4386071707","https://openalex.org/W4386076522","https://openalex.org/W4389519587","https://openalex.org/W4392309090","https://openalex.org/W4394862623","https://openalex.org/W6745537798","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6778883912","https://openalex.org/W6802987763","https://openalex.org/W6810334672","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6851762504","https://openalex.org/W6851948999","https://openalex.org/W6851950068","https://openalex.org/W6852776751","https://openalex.org/W6852952677","https://openalex.org/W6853013044","https://openalex.org/W6853094705","https://openalex.org/W6853116092","https://openalex.org/W6853465110","https://openalex.org/W6853515732","https://openalex.org/W6854917811","https://openalex.org/W6855810401","https://openalex.org/W6856926427"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Although":[0],"multi-modal":[1],"large":[2,94],"language":[3,95],"models":[4],"possess":[5],"impressive":[6],"cross-modal":[7,33,69],"reasoning":[8,71,170],"and":[9,16,91,122,126,143,151,167],"prediction":[10,28,35],"capabilities,":[11],"they":[12],"lack":[13],"a":[14,25,75,83,87,92,159],"unified":[15],"rigorous":[17],"evaluation":[18],"standard.":[19],"In":[20],"this":[21,62],"paper,":[22],"we":[23,65,157],"introduce":[24],"future":[26,55,165,184],"event":[27,169,185],"task":[29,41],"to":[30,45],"assess":[31],"the":[32,43,54,111,124,130,133,138,176,191,194],"temporal":[34],"capabilities":[36],"of":[37,48,164,193],"these":[38],"models.":[39],"This":[40],"requires":[42],"model":[44,96],"generate":[46],"descriptions":[47],"events":[49],"that":[50,175],"may":[51],"occur":[52],"in":[53,108,129],"based":[56],"on":[57,114],"input":[58],"video.":[59,131],"To":[60,153],"tackle":[61],"new":[63],"task,":[64],"propose":[66],"an":[67,79],"object-centric":[68,168],"knowledge":[70],"framework,":[72,156],"which":[73],"combines":[74],"basic":[76],"information":[77,107,128],"encoder,":[78,86],"adaptive":[80,99],"multi-segment":[81,100],"filter,":[82],"spatial-temporal":[84,118],"relation":[85,119],"vision-text":[88,134],"interaction":[89,135],"module,":[90],"pre-trained":[93],"decoder.":[97],"The":[98,117],"filter":[101],"captures":[102],"selectively":[103],"capture":[104],"critical":[105],"visual":[106,141],"videos,":[109],"enhancing":[110],"model\u2019s":[112],"focus":[113],"relevant":[115],"features.":[116],"encoder":[120],"decomposes":[121],"associates":[123],"objects":[125],"scene":[127],"Additionally,":[132],"module":[136],"enhances":[137],"connection":[139],"between":[140],"sequences":[142],"their":[144],"corresponding":[145],"textual":[146],"narratives,":[147],"ensuring":[148],"semantic":[149],"coherence":[150],"consistency.":[152],"evaluate":[154],"our":[155],"constructed":[158],"dataset":[160],"containing":[161],"descriptions,":[162],"dialogues":[163],"events,":[166],"chains.":[171],"Experimental":[172],"results":[173],"indicate":[174],"proposed":[177],"framework":[178],"outperforms":[179],"all":[180],"previous":[181],"methods":[182],"for":[183],"prediction.":[186],"Ablation":[187],"studies":[188],"further":[189],"demonstrate":[190],"effectiveness":[192],"designed":[195],"modules.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}