{"id":"https://openalex.org/W4414359691","doi":"https://doi.org/10.24963/ijcai.2025/906","title":"Can Retelling Have Adequate Information for Reasoning? An Enhancement Method for Imperfect Video Understanding with Large Language Model","display_name":"Can Retelling Have Adequate Information for Reasoning? An Enhancement Method for Imperfect Video Understanding with Large Language Model","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359691","doi":"https://doi.org/10.24963/ijcai.2025/906"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/906","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/906","pdf_url":"https://www.ijcai.org/proceedings/2025/0906.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0906.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100674542","display_name":"Mingxin Li","orcid":"https://orcid.org/0000-0002-7595-3717"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxin Li","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390316","display_name":"Wenhao Wang","orcid":"https://orcid.org/0000-0002-7015-9047"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112986079","display_name":"Hongru Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongru Ji","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680344","display_name":"Xianghua Li","orcid":"https://orcid.org/0000-0003-0253-3882"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghua Li","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083269284","display_name":"Chao Gao","orcid":"https://orcid.org/0000-0002-5205-0670"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Gao","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26356877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8150","last_page":"8158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.982200026512146,"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":0.982200026512146,"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":0.9729999899864197,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9702000021934509,"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/imperfect","display_name":"Imperfect","score":0.7005000114440918},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5748000144958496},{"id":"https://openalex.org/keywords/online-video","display_name":"Online video","score":0.4050000011920929},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37860000133514404},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.36899998784065247},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.33009999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331000208854675},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823000073432922},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4268999993801117},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/906","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/906","pdf_url":"https://www.ijcai.org/proceedings/2025/0906.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/906","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/906","pdf_url":"https://www.ijcai.org/proceedings/2025/0906.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2392277617","display_name":null,"funder_award_id":"U22A 2098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2703680814","display_name":null,"funder_award_id":"62261136549","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3007078423","display_name":null,"funder_award_id":"62471403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5195067714","display_name":null,"funder_award_id":"G2024WD0151","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5518866307","display_name":null,"funder_award_id":"62271411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G922937089","display_name":null,"funder_award_id":"D5000240309","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359691.pdf","grobid_xml":"https://content.openalex.org/works/W4414359691.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0,26],"Language":[1,27],"Models":[2,28],"(LLMs)":[3],"demonstrate":[4],"strong":[5,71],"capabilities":[6,44,73],"in":[7,17],"video":[8,18,53,91,114,161],"understanding.":[9,92],"However,":[10],"it":[11],"exhibits":[12],"hallucinations":[13],"and":[14,37,60,83,96,124,144],"factual":[15],"errors":[16],"description.":[19],"On":[20],"the":[21,47,50,61,66,70,107,135,147,153],"one":[22],"hand,":[23],"existing":[24],"Multimodal":[25],"(MLLMs)":[29],"are":[30,140],"primarily":[31],"trained":[32],"by":[33,117],"combining":[34],"language":[35],"models":[36],"vision":[38],"models,":[39],"with":[40,164],"their":[41],"visual":[42],"understanding":[43,162],"depending":[45],"on":[46,106,159],"performance":[48],"of":[49,63,69,74,168],"backbone.":[51],"Moreover,":[52],"descriptions":[54],"often":[55],"suffer":[56],"from":[57],"incomplete":[58],"content":[59],"possibility":[62],"errors.":[64],"Given":[65],"proven":[67],"assessment":[68],"reasoning":[72,126,132],"LLMs,":[75],"this":[76],"paper":[77],"proposes":[78],"ERSR,":[79],"a":[80,121],"novel":[81],"Entity":[82],"Relationship":[84],"based":[85,105],"Self-Enhanced":[86],"Reasoning":[87],"method":[88,155],"for":[89],"imperfect":[90],"Specifically,":[93],"an":[94,165],"entities":[95],"relationships":[97],"strategy":[98,127],"is":[99,128],"designed":[100],"to":[101,130],"perform":[102],"scene":[103],"graphs":[104],"limited":[108],"observed":[109],"entity":[110],"relationships,":[111],"thereby":[112],"enhancing":[113],"descriptions.":[115],"Furthermore,":[116],"providing":[118],"question":[119,137],"feedbacks,":[120],"self-enhanced":[122],"forward":[123],"feedback":[125],"provided":[129],"enhance":[131],"logic.":[133],"Finally,":[134],"prediction":[136],"answering":[138],"results":[139,158],"re-validated":[141],"through":[142],"rethinking":[143],"verifying":[145],"using":[146],"LLMs.":[148],"Extensive":[149],"experiments":[150],"show":[151],"that":[152],"proposed":[154],"achieves":[156],"competitive":[157],"real-world":[160],"datasets,":[163],"overall":[166],"improvement":[167],"no":[169],"less":[170],"than":[171],"1.4%.":[172]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}