{"id":"https://openalex.org/W7160307548","doi":"https://doi.org/10.1109/wacv61042.2026.00738","title":"ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering","display_name":"ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160307548","doi":"https://doi.org/10.1109/wacv61042.2026.00738"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5135285247","display_name":"Jeongwan Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongwan Shin","raw_affiliation_strings":["DGIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DGIST","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045230148","display_name":"Chan Hur","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan Hur","raw_affiliation_strings":["Kyungpook National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135331399","display_name":"Seongmin Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Seongmin Cho","raw_affiliation_strings":["4Genon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"4Genon","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135412606","display_name":"Jaeho Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeho Choi","raw_affiliation_strings":["DGIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DGIST","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010610758","display_name":"Hyeyoung Park","orcid":"https://orcid.org/0000-0003-0716-4385"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeyoung Park","raw_affiliation_strings":["Kyungpook National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52146986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7647","last_page":"7657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9882000088691711,"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":0.9882000088691711,"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":0.0026000000070780516,"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":0.0015999999595806003,"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/question-answering","display_name":"Question answering","score":0.4375999867916107},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.30250000953674316},{"id":"https://openalex.org/keywords/interactive-video","display_name":"Interactive video","score":0.28529998660087585},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.27900001406669617},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2745000123977661},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.26660001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720300018787384},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2765716052","https://openalex.org/W2799176631","https://openalex.org/W2963541336","https://openalex.org/W2964220823","https://openalex.org/W2990152177","https://openalex.org/W3126721948","https://openalex.org/W3175961224","https://openalex.org/W3197457832","https://openalex.org/W4385801730","https://openalex.org/W4386075754","https://openalex.org/W4389519587","https://openalex.org/W4389524050","https://openalex.org/W4390871765","https://openalex.org/W4401042244","https://openalex.org/W4401979966","https://openalex.org/W4402671548","https://openalex.org/W4402727520","https://openalex.org/W4402727764","https://openalex.org/W4402753952","https://openalex.org/W4404781468","https://openalex.org/W4404781975","https://openalex.org/W4411119276","https://openalex.org/W4413145669","https://openalex.org/W4413146669","https://openalex.org/W4413147823","https://openalex.org/W4413155953","https://openalex.org/W4414198027","https://openalex.org/W7133182950","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133198646","https://openalex.org/W7155054664","https://openalex.org/W7160143101"],"related_works":[],"abstract_inverted_index":{"Video":[0],"question":[1,131],"answering":[2],"is":[3],"a":[4,77,84,97,165],"non-trivial":[5],"task":[6],"that":[7,100],"demands":[8],"joint":[9],"understanding":[10],"of":[11,80,169],"visual":[12,73,135],"contents":[13],"and":[14,83,132,162],"linguistic":[15],"questions":[16],"as":[17,19],"well":[18],"temporal":[20,49,64,146],"reasoning":[21,33],"across":[22,39,51,156],"video":[23,58],"frames.":[24,52],"Recent":[25],"agent-based":[26],"approaches":[27],"address":[28],"this":[29],"by":[30,43,121],"conducting":[31],"multi-step":[32],"with":[34,108,164],"large":[35,85],"language":[36,59],"models":[37,60],"(LLMs)":[38],"frame-level":[40],"captions":[41],"generated":[42],"vision-language":[44],"models,":[45],"but":[46,69],"encounter":[47],"limited":[48],"coherence":[50],"A":[53],"possible":[54],"direction":[55],"based":[56],"on":[57,87],"(VideoLMs)":[61],"directly":[62],"captures":[63],"dynamics":[65],"via":[66],"video-level":[67],"descriptions,":[68],"often":[70],"lacks":[71],"fine-grained":[72],"cues":[74],"due":[75],"to":[76],"restricted":[78],"number":[79],"input":[81,88],"frames":[82],"dependency":[86],"prompts.":[89],"To":[90],"tackle":[91],"these":[92],"challenges,":[93],"we":[94],"propose":[95],"RefineVQA,":[96],"training-free":[98],"framework":[99],"can":[101],"easily":[102],"be":[103],"plugged":[104],"into":[105,149],"existing":[106],"VideoLMs":[107],"iterative,":[109],"LLM-guided":[110],"description":[111,127,142],"refinements.":[112],"Specifically,":[113],"the":[114,126,130,141],"VideoLM":[115],"produces":[116],"an":[117],"initial":[118],"description,":[119],"followed":[120],"LLM":[122,168],"feedback":[123],"determining":[124],"whether":[125],"suffices":[128],"for":[129],"guiding":[133],"further":[134],"extraction,":[136],"which":[137],"in":[138],"turn":[139],"enhances":[140],"quality":[143],"while":[144],"preserving":[145],"context.":[147],"Plugged":[148],"state-of-the-art":[150],"VideoLMs,":[151],"ReFineVQA":[152],"yields":[153],"consistent":[154],"gains":[155],"diverse":[157],"benchmarks\u2013NExT-QA,":[158],"EgoSchema,":[159],"VideoMME,":[160],"ActivityNet,":[161],"StreamingBench\u2013even":[163],"small":[166],"external":[167],"3.8B":[170],"parameters.":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}