{"id":"https://openalex.org/W4417166450","doi":"https://doi.org/10.1109/iccv51701.2025.02128","title":"HRScene: How Far are VLMs from Effective High-Resolution Image Understanding?","display_name":"HRScene: How Far are VLMs from Effective High-Resolution Image Understanding?","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417166450","doi":"https://doi.org/10.1109/iccv51701.2025.02128"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.18406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038357504","display_name":"Yusen Zhang","orcid":"https://orcid.org/0000-0003-3842-1153"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yusen Zhang","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenliang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenliang Zheng","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120733756","display_name":"Aashrith Madasu","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aashrith Madasu","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739668","display_name":"Peng Shi","orcid":"https://orcid.org/0000-0001-8218-586X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Shi","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062976255","display_name":"Ryo Kamoi","orcid":"https://orcid.org/0000-0002-8442-4171"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryo Kamoi","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020063371","display_name":"Hao Zhou","orcid":"https://orcid.org/0009-0006-1673-5564"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103265020","display_name":"Zhuoyang Zou","orcid":"https://orcid.org/0000-0002-9039-0844"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoyang Zou","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100661274","display_name":"Shu Zhao","orcid":"https://orcid.org/0000-0001-7647-3603"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu Zhao","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067607594","display_name":"Sarkar Snigdha Sarathi Das","orcid":"https://orcid.org/0000-0003-1052-4142"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarkar Snigdha Sarathi Das","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050995253","display_name":"Vipul Gupta","orcid":"https://orcid.org/0000-0001-9738-7181"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipul Gupta","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101086021","display_name":"Xiaoxin Lu","orcid":"https://orcid.org/0009-0008-9546-6052"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxin Lu","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331307","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0002-9675-5322"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077801273","display_name":"Ranran Haoran Zhang","orcid":"https://orcid.org/0000-0002-1005-9757"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranran Haoran Zhang","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Avitej Iyer","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avitej Iyer","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109731561","display_name":"Renze Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renze Lou","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051704887","display_name":"Wenpeng Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenpeng Yin","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100422075","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-6974-5516"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5038357504"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37314323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22922","last_page":"22933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7656000256538391,"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":0.7656000256538391,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.057100001722574234,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.03269999846816063,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7598000168800354},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.6262999773025513},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.3582000136375427},{"id":"https://openalex.org/keywords/image-registration","display_name":"Image registration","score":0.32089999318122864},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7598000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7091000080108643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6427000164985657},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.6262999773025513},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5900999903678894},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2809000015258789}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.18406","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.18406","pdf_url":"https://arxiv.org/pdf/2504.18406","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.18406","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.18406","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.18406","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.18406","pdf_url":"https://arxiv.org/pdf/2504.18406","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6163050064","display_name":null,"funder_award_id":"IIS-2338418","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High-resolution":[0],"image":[1,139],"(HRI)":[2],"understanding":[3,67],"aims":[4],"to":[5,50,88,107,202],"process":[6],"images":[7,17,146],"with":[8,68,81,140],"a":[9,42,45,61],"large":[10],"number":[11],"of":[12,23,44,120,182],"pixels,":[13],"such":[14],"as":[15],"pathological":[16],"and":[18,76,95,114,125,144,169,211],"agricultural":[19],"aerial":[20],"images,":[21,109],"both":[22],"which":[24],"can":[25,35],"exceed":[26],"1":[27],"million":[28],"pixels.":[29],"Vision":[30],"Large":[31],"Language":[32],"Models":[33],"(VLMs)":[34],"allegedly":[36],"handle":[37],"HRIs,":[38],"however,":[39],"there":[40],"is":[41,93],"lack":[43],"comprehensive":[46],"benchmark":[47,64],"for":[48,65],"VLMs":[49,177,200],"evaluate":[51],"HRI":[52,66,192,205],"understanding.":[53,193],"To":[54],"address":[55],"this":[56],"gap,":[57],"we":[58],"introduce":[59],"HRScene,":[60],"novel":[62],"unified":[63],"rich":[69],"scenes.":[70],"HRScene":[71,92,173],"incorporates":[72],"25":[73,102],"real-world":[74,121,186],"datasets":[75,80,132,197],"2":[77],"synthetic":[78,196],"diagnostic":[79,130],"resolutions":[82],"ranging":[83,104],"from":[84,105],"1,024":[85,87],"$\\times$":[86,90],"35,503":[89],"26,627.":[91],"collected":[94],"re-annotated":[96],"by":[97,135],"10":[98],"graduate-level":[99],"annotators,":[100],"covering":[101],"scenarios,":[103],"microscopic":[106],"radiology":[108],"street":[110],"views,":[111],"long-range":[112],"pictures,":[113],"telescope":[115],"images.":[116],"It":[117],"includes":[118],"HRIs":[119],"objects,":[122],"scanned":[123],"documents,":[124],"composite":[126],"multi-image.":[127],"The":[128],"two":[129],"evaluation":[131],"are":[133],"synthesized":[134],"combining":[136],"the":[137,141],"target":[138],"gold":[142],"answer":[143],"distracting":[145],"in":[147,156,191],"different":[148],"orders,":[149],"assessing":[150],"how":[151],"well":[152],"models":[153],"utilize":[154,204],"regions":[155],"HRI.":[157],"We":[158],"conduct":[159],"extensive":[160],"experiments":[161],"involving":[162],"28":[163],"VLMs,":[164],"including":[165],"Gemini":[166],"2.0":[167],"Flash":[168],"GPT-4o.":[170],"Experiments":[171],"on":[172,185,195,215],"show":[174],"that":[175,199],"current":[176],"achieve":[178],"an":[179],"average":[180],"accuracy":[181],"around":[183],"50%":[184],"tasks,":[187],"revealing":[188],"significant":[189,208],"gaps":[190],"Results":[194],"reveal":[198],"struggle":[201],"effectively":[203],"regions,":[206],"showing":[207],"Regional":[209],"Divergence":[210],"lost-in-middle,":[212],"shedding":[213],"light":[214],"future":[216],"research.":[217]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}