{"id":"https://openalex.org/W7138287342","doi":"https://doi.org/10.1609/aaai.v40i10.37778","title":"Leveraging Textual Compositional Reasoning for Robust Change Captioning","display_name":"Leveraging Textual Compositional Reasoning for Robust Change Captioning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138287342","doi":"https://doi.org/10.1609/aaai.v40i10.37778"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i10.37778","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37778","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37778/41740","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://ojs.aaai.org/index.php/AAAI/article/download/37778/41740","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090285682","display_name":"Kyu Ri Park","orcid":"https://orcid.org/0000-0001-9531-1677"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyu Ri Park","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129664452","display_name":"Jiyoung Park","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiyoung Park","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713034","display_name":"Seong Tae Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong Tae Kim","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657202","display_name":"Hong Joo Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hong Joo Lee","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036936141","display_name":"Jung Uk Kim","orcid":"https://orcid.org/0000-0003-4533-4875"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Uk Kim","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"10","first_page":"8296","last_page":"8304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9193999767303467,"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":0.9193999767303467,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.006599999964237213,"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/closed-captioning","display_name":"Closed captioning","score":0.8500999808311462},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5565999746322632},{"id":"https://openalex.org/keywords/visual-cortex","display_name":"Visual cortex","score":0.43540000915527344},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38690000772476196},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.36090001463890076},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3596999943256378},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35910001397132874},{"id":"https://openalex.org/keywords/temporal-cortex","display_name":"Temporal cortex","score":0.3476000130176544},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8500999808311462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523000240325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580999851226807},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C2779345533","wikidata":"https://www.wikidata.org/wiki/Q75785","display_name":"Visual cortex","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C2993858690","wikidata":"https://www.wikidata.org/wiki/Q744385","display_name":"Temporal cortex","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i10.37778","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37778","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37778/41740","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37778","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37778","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37778/41740","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":0.5216980576515198,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138287342.pdf","grobid_xml":"https://content.openalex.org/works/W7138287342.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Change":[0,105],"captioning":[1],"aims":[2],"to":[3,22,33,62,68,85,125,155],"describe":[4],"changes":[5,27,164],"between":[6,112],"a":[7,54,116],"pair":[8],"of":[9,98],"images.":[10],"However,":[11],"existing":[12],"works":[13],"rely":[14],"on":[15],"visual":[16,110,132,144,158,170],"features":[17,147,161,171],"alone,":[18],"which":[19],"often":[20],"fail":[21],"capture":[23,163],"subtle":[24],"but":[25],"meaningful":[26],"because":[28],"they":[29],"lack":[30],"the":[31],"ability":[32],"represent":[34],"explicitly":[35],"structured":[36],"information":[37],"such":[38],"as":[39],"object":[40],"relationships":[41],"and":[42,134,145,159,162],"compositional":[43,94,127],"semantics.":[44],"To":[45],"alleviate":[46],"this,":[47],"we":[48],"present":[49],"CORTEX":[50,74,96,154],"(COmpositional":[51],"Reasoning-aware":[52,117],"TEXt-guided),":[53],"novel":[55],"framework":[56],"that":[57,91,107,122,142,165],"integrates":[58],"complementary":[59],"textual":[60,77,146,160],"cues":[61,70],"enhance":[63],"change":[64],"understanding.":[65],"In":[66],"addition":[67],"capturing":[69],"from":[71],"pixel-level":[72],"differences,":[73],"utilizes":[75],"scene-level":[76],"knowledge":[78],"provided":[79],"by":[80],"Vision":[81],"Language":[82],"Models":[83],"(VLMs)":[84],"extract":[86],"richer":[87],"image":[88],"text":[89],"signals":[90],"reveal":[92],"underlying":[93],"reasoning.":[95,151],"consists":[97],"three":[99],"key":[100],"modules:":[101],"(i)":[102],"an":[103,136],"Image-level":[104],"Detector":[106],"identifies":[108],"low-level":[109],"differences":[111],"paired":[113],"images,":[114],"(ii)":[115],"Text":[118],"Extraction":[119],"(RTE)":[120],"module":[121,141],"use":[123],"VLMs":[124],"generate":[126],"reasoning":[128],"descriptions":[129],"implicit":[130],"in":[131,169],"features,":[133],"(iii)":[135],"Image-Text":[137],"Dual":[138],"Alignment":[139],"(ITDA)":[140],"aligns":[143],"for":[148],"fine-grained":[149],"relational":[150],"This":[152],"enables":[153],"reason":[156],"over":[157],"are":[166],"otherwise":[167],"ambiguous":[168],"alone.":[172]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}