{"id":"https://openalex.org/W4405429615","doi":"https://doi.org/10.1109/access.2024.3517625","title":"An Image Grid Can Be Worth a Video: Zero-Shot Video Question Answering Using a VLM","display_name":"An Image Grid Can Be Worth a Video: Zero-Shot Video Question Answering Using a VLM","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4405429615","doi":"https://doi.org/10.1109/access.2024.3517625"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3517625","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3517625","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3517625","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074088627","display_name":"Wonkyun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonkyun Kim","raw_affiliation_strings":["Department of Intelligence and Information, Seoul National University, Gwanak-gu, Seoul, South Korea","Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-2318-9554","affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113155098","display_name":"Changin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changin Choi","raw_affiliation_strings":["Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-gu, Seoul, South Korea","Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wonseok Lee","orcid":"https://orcid.org/0009-0004-8995-339X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonseok Lee","raw_affiliation_strings":["Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-gu, Seoul, South Korea","Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0004-8995-339X","affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056032525","display_name":"Wonjong Rhee","orcid":"https://orcid.org/0000-0002-2590-8774"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjong Rhee","raw_affiliation_strings":["Department of Intelligence and Information, Seoul National University, Gwanak-gu, Seoul, South Korea","Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-2590-8774","affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.2766,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95934002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"193057","last_page":"193075"},"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":0.9973000288009644,"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":0.9973000288009644,"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":0.984499990940094,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9797999858856201,"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":0.7259274125099182},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6932334899902344},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.524752140045166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48182645440101624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4189172089099884},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.41332244873046875},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39623790979385376},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3554859757423401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12179678678512573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259274125099182},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6932334899902344},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.524752140045166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48182645440101624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189172089099884},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41332244873046875},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39623790979385376},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3554859757423401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12179678678512573},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3517625","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3517625","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:736f770188dd4642a0176fad10df08bd","is_oa":true,"landing_page_url":"https://doaj.org/article/736f770188dd4642a0176fad10df08bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 193057-193075 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3517625","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3517625","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6869896014","display_name":null,"funder_award_id":"NRF-2020R1A2C2007139","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2765716052","https://openalex.org/W2963293463","https://openalex.org/W2963541336","https://openalex.org/W2964220823","https://openalex.org/W3175961224","https://openalex.org/W3205786327","https://openalex.org/W4385570088","https://openalex.org/W4386065596","https://openalex.org/W4386066385","https://openalex.org/W4386076140","https://openalex.org/W4389519587","https://openalex.org/W4389520080","https://openalex.org/W4390872747","https://openalex.org/W4390889724","https://openalex.org/W4393178509","https://openalex.org/W4402727142","https://openalex.org/W4402754220","https://openalex.org/W6778883912","https://openalex.org/W6798182279","https://openalex.org/W6800139874","https://openalex.org/W6803023527","https://openalex.org/W6810081322","https://openalex.org/W6810162553","https://openalex.org/W6810334672","https://openalex.org/W6810452849","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6838434436","https://openalex.org/W6838865847","https://openalex.org/W6846867676","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851948999","https://openalex.org/W6852060543","https://openalex.org/W6852776751","https://openalex.org/W6852800892","https://openalex.org/W6852818750","https://openalex.org/W6852932568","https://openalex.org/W6852952677","https://openalex.org/W6853116092","https://openalex.org/W6853515732","https://openalex.org/W6854917811","https://openalex.org/W6856126884","https://openalex.org/W6856295045","https://openalex.org/W6856656568","https://openalex.org/W6857054612","https://openalex.org/W6858543224","https://openalex.org/W6858826905","https://openalex.org/W6859099255","https://openalex.org/W6859124043","https://openalex.org/W6859125261","https://openalex.org/W6859490940","https://openalex.org/W6859823276"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2384605597","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2387743295","https://openalex.org/W2366718574","https://openalex.org/W2359774528"],"abstract_inverted_index":{"Stimulated":[0],"by":[1,139],"the":[2,92,118,123,162,173,177,181,216,225,255],"sophisticated":[3],"reasoning":[4],"capabilities":[5],"of":[6,14,101,111,126,164,188,231],"recent":[7],"Large":[8],"Language":[9,28,83,221],"Models":[10,29],"(LLMs),":[11],"a":[12,33,73,80,96,99,132,135,165,189],"variety":[13],"strategies":[15],"for":[16,65,242],"bridging":[17],"video":[18,37,97,112,133],"modality":[19,66],"have":[20],"been":[21],"devised.":[22],"A":[23],"prominent":[24],"strategy":[25,49,77],"involves":[26],"Video":[27],"(VideoLMs),":[30],"which":[31],"train":[32],"learnable":[34],"interface":[35],"with":[36,44,106,122],"data":[38],"to":[39],"connect":[40],"advanced":[41],"vision":[42],"encoders":[43],"LLMs.":[45],"Recently,":[46],"an":[47,155,247],"alternative":[48],"has":[50],"surfaced,":[51],"employing":[52],"readily":[53],"available":[54,261],"foundation":[55],"models,":[56],"such":[57],"as":[58,154],"VideoLMs":[59],"and":[60,210,245,252],"LLMs,":[61],"across":[62,202],"multiple":[63,141],"stages":[64],"bridging.":[67],"In":[68],"this":[69],"study,":[70],"we":[71,130],"introduce":[72],"simple":[74],"yet":[75],"novel":[76],"where":[78],"only":[79],"single":[81,136,150,190],"Vision":[82,220],"Model":[84,222],"(VLM)":[85],"is":[86,91,152,259],"utilized.":[87],"Our":[88,198,257],"starting":[89],"point":[90],"plain":[93],"insight":[94],"that":[95,215,250],"comprises":[98],"series":[100],"images,":[102],"or":[103],"frames,":[104],"interwoven":[105],"temporal":[107,119,170],"information.":[108],"The":[109,148],"essence":[110],"comprehension":[113],"lies":[114],"in":[115,143,228],"adeptly":[116],"managing":[117],"aspects":[120],"along":[121],"spatial":[124],"details":[125],"each":[127],"frame.":[128],"Initially,":[129],"transform":[131],"into":[134],"composite":[137],"image":[138,151,156,182],"arranging":[140],"frames":[142],"our":[144],"proposed":[145,217],"grid":[146,174,183],"layout.":[147],"resulting":[149],"termed":[153],"grid.":[157],"This":[158],"format,":[159],"while":[160],"maintaining":[161],"appearance":[163],"solitary":[166],"image,":[167],"effectively":[168],"retains":[169],"information":[171],"within":[172],"structure":[175],"at":[176],"pixel":[178],"level.":[179],"Therefore,":[180],"approach":[184],"enables":[185],"direct":[186],"application":[187],"high-performance":[191],"VLM":[192],"without":[193],"necessitating":[194],"any":[195],"video-data":[196],"training.":[197],"extensive":[199],"experimental":[200],"analysis":[201],"ten":[203,232],"zero-shot":[204],"VQA":[205],"benchmarks,":[206,213],"including":[207],"five":[208,211],"open-ended":[209],"multiple-choice":[212],"reveals":[214],"Image":[218],"Grid":[219],"(IG-VLM)":[223],"surpasses":[224],"existing":[226],"methods":[227],"nine":[229],"out":[230],"benchmarks.":[233],"We":[234],"also":[235],"discuss":[236],"how":[237],"IG-VLM":[238],"can":[239],"be":[240],"extended":[241],"long":[243],"videos":[244],"provide":[246],"extension":[248],"method":[249],"consistently":[251],"reliably":[253],"improves":[254],"performance.":[256],"code":[258],"are":[260],"at:":[262],"<uri":[263],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[264],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/imagegridworth/IG-VLM</uri>":[265]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}