{"id":"https://openalex.org/W7138280709","doi":"https://doi.org/10.1609/aaai.v40i5.37390","title":"Rethinking Video-Language Model from the Language Input Perspective","display_name":"Rethinking Video-Language Model from the Language Input Perspective","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138280709","doi":"https://doi.org/10.1609/aaai.v40i5.37390"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37390","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37390","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i5.37390","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129649664","display_name":"Xiang Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113067511","display_name":"Wanlong Fang","orcid":"https://orcid.org/0000-0003-4480-3107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanlong Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129748655","display_name":"Changshuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changshuo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129304350","display_name":"Xiaoye Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoye Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129643535","display_name":"Daizong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3885","last_page":"3893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9648000001907349,"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":0.9648000001907349,"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":0.0071000000461936,"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":0.006200000178068876,"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/bridging","display_name":"Bridging (networking)","score":0.7400000095367432},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6672000288963318},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6459000110626221},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6412000060081482},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6261000037193298},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2971999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425000071525574},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7400000095367432},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6672000288963318},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6459000110626221},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4171999990940094},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.26759999990463257},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37390","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37390","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"},{"id":"pmh:oai:ojs.aaai.org:article/37390","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37390","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37390","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":[{"score":0.5914585590362549,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Driven":[0],"by":[1,46,169],"the":[2,20,42,47,65,135,178,184,190],"wave":[3],"of":[4,36,156,192],"large":[5],"language":[6],"models,":[7],"Video-Language":[8],"Models":[9],"(VLMs)":[10],"have":[11,30],"become":[12],"a":[13,54,90,112,171],"significant":[14,32],"yet":[15],"challenging":[16],"technology":[17],"to":[18,59,101,120,138,151,165,187],"bridge":[19,122],"gap":[21],"between":[22],"videos":[23,123,162],"and":[24,70,80,124,131],"texts.":[25,125,158],"Although":[26],"previous":[27],"VLM":[28],"works":[29],"made":[31],"progress,":[33],"almost":[34],"all":[35,41,64],"them":[37],"implicitly":[38],"assume":[39],"that":[40,88,177],"texts":[43,66,93,133],"are":[44,77],"predefined":[45,74],"specific":[48,140],"template.":[49],"In":[50],"real-world":[51],"applications,":[52],"such":[53],"strict":[55],"assumption":[56],"is":[57,67,86],"impossible":[58],"satisfy":[60],"since":[61],"1)":[62],"predefining":[63],"extremely":[68],"time-consuming":[69],"labor-intensive.":[71],"2)":[72],"these":[73],"text":[75,141,148],"inputs":[76],"too":[78],"restrictive":[79],"user-unfriendly,":[81],"limiting":[82],"their":[83],"applications.":[84],"It":[85],"observed":[87],"given":[89],"video":[91],"input,":[92],"with":[94],"similar":[95],"semantics":[96,155],"but":[97],"different":[98],"templates":[99],"lead":[100],"various":[102,117],"performances.":[103],"To":[104],"this":[105,108],"end,":[106],"in":[107],"paper,":[109],"we":[110,127,144,160],"propose":[111,145],"novel":[113],"plug-and-play":[114,185],"framework":[115],"for":[116],"VLM-based":[118],"methods":[119],"fully":[121],"Specifically,":[126],"first":[128],"generate":[129],"positive":[130],"negative":[132],"from":[134],"original":[136],"ones":[137],"target":[139],"components.":[142],"Then,":[143],"an":[146],"attribute-based":[147],"reasoning":[149],"strategy":[150],"mine":[152],"fine-grained":[153],"textual":[154],"generated":[157],"Finally,":[159],"utilize":[161],"as":[163,183],"guidance":[164],"conduct":[166],"cross-modal":[167],"bridging":[168],"designing":[170],"self-weighted":[172],"loss.":[173],"Extensive":[174],"experiments":[175],"show":[176],"proposed":[179],"method":[180],"can":[181],"serve":[182],"module":[186],"effectively":[188],"improve":[189],"performance":[191],"state-of-the-art":[193],"VLMs.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}