{"id":"https://openalex.org/W4405095890","doi":"https://doi.org/10.1109/wacv61042.2026.00550","title":"Grounding Descriptions in Images informs Zero-Shot Visual Recognition","display_name":"Grounding Descriptions in Images informs Zero-Shot Visual Recognition","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4405095890","doi":"https://doi.org/10.1109/wacv61042.2026.00550"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00550","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.04429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004427805","display_name":"Shaunak Halbe","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaunak Halbe","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101061351","display_name":"Junjiao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junjiao Tian","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037701886","display_name":"K. J. Joseph","orcid":"https://orcid.org/0000-0003-0369-2674"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K J Joseph","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":null,"display_name":"James Seale Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Seale Smith","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035914973","display_name":"Katherine Stevo","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Stevo","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107297524","display_name":"Vineeth N Balasubramanian","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineeth N Balasubramanian","raw_affiliation_strings":["Indian Institute of Technology,Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088892134","display_name":"Zsolt Kira","orcid":"https://orcid.org/0000-0002-2626-2004"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zsolt Kira","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5672","last_page":"5681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.8791999816894531,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.8791999816894531,"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":0.8536999821662903,"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"}},{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.8353999853134155,"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/shot","display_name":"Shot (pellet)","score":0.6923657655715942},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6410449743270874},{"id":"https://openalex.org/keywords/ground-zero","display_name":"Ground zero","score":0.49508824944496155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47517862915992737},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44933342933654785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4455293118953705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32102811336517334},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21228036284446716},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.11445102095603943},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1006748378276825},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07022574543952942}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6923657655715942},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6410449743270874},{"id":"https://openalex.org/C2780518707","wikidata":"https://www.wikidata.org/wiki/Q685332","display_name":"Ground zero","level":2,"score":0.49508824944496155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47517862915992737},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44933342933654785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4455293118953705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32102811336517334},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21228036284446716},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11445102095603943},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1006748378276825},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07022574543952942},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00550","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"},{"id":"pmh:oai:arXiv.org:2412.04429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04429","pdf_url":"https://arxiv.org/pdf/2412.04429","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.04429","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.04429","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.04429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04429","pdf_url":"https://arxiv.org/pdf/2412.04429","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"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":["https://openalex.org/W4300821880","https://openalex.org/W4402779703","https://openalex.org/W4313594480","https://openalex.org/W2285651113","https://openalex.org/W4256031153","https://openalex.org/W3279617","https://openalex.org/W4293365998","https://openalex.org/W2327903337","https://openalex.org/W2768862283","https://openalex.org/W2168002573"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"like":[3,219],"CLIP":[4],"have":[5],"been":[6],"cherished":[7],"for":[8],"their":[9],"ability":[10,200],"to":[11,54,68,88,128,157,172,201],"perform":[12],"zero-shot":[13,166],"visual":[14],"recognition":[15],"on":[16,207,215],"open-vocabulary":[17],"concepts.":[18],"This":[19],"is":[20],"achieved":[21,211],"by":[22,61,72,205,212,229],"selecting":[23],"the":[24,31,35,62,164,223],"object":[25],"category":[26,74],"whose":[27],"textual":[28,95,131],"representation":[29],"bears":[30],"highest":[32],"similarity":[33],"with":[34,46,137,141],"query":[36],"image.":[37],"While":[38],"successful":[39],"in":[40,133],"some":[41],"domains,":[42],"this":[43,105,147],"method":[44],"struggles":[45],"identifying":[47],"fine-grained":[48],"entities":[49],"as":[50,52],"well":[51],"generalizing":[53],"unseen":[55],"concepts":[56,204],"that":[57],"are":[58],"not":[59],"captured":[60],"training":[63],"distribution.":[64],"Recent":[65],"works":[66],"attempt":[67],"mitigate":[69],"these":[70,85,203],"challenges":[71],"integrating":[73],"descriptions":[75,132],"at":[76,115,118,234],"test":[77],"time,":[78],"albeit":[79],"yielding":[80],"modest":[81],"improvements.":[82],"We":[83,162],"attribute":[84],"limited":[86],"gains":[87],"a":[89,110,187],"misalignment":[90],"between":[91],"image":[92,134,143,180],"regions":[93,135],"and":[94,121,196],"descriptions,":[96],"which":[97],"stems":[98],"from":[99],"CLIP\u2019s":[100],"global":[101,142],"alignment":[102],"objective.":[103],"In":[104],"paper,":[106],"we":[107,149,184],"propose":[108],"GRAIN,":[109],"new":[111],"pretraining":[112],"strategy":[113],"aimed":[114],"aligning":[116,138],"representations":[117,227],"both":[119],"fine":[120],"coarse":[122],"levels":[123],"simultaneously.":[124],"Our":[125],"approach":[126],"learns":[127],"jointly":[129],"ground":[130],"along":[136],"overarching":[139],"captions":[140],"representations.":[144],"To":[145],"drive":[146],"pre-training,":[148],"leverage":[150],"frozen":[151],"Multimodal":[152],"Large":[153],"Language":[154],"Models":[155],"(MLLMs)":[156],"derive":[158],"large-scale":[159],"synthetic":[160],"annotations.":[161],"demonstrate":[163],"enhanced":[165],"performance":[167],"of":[168,226],"our":[169,198,213,230],"model":[170,214],"compared":[171],"current":[173],"state-of-the":[174],"art":[175],"methods":[176],"across":[177],"11":[178],"diverse":[179],"classification":[181],"datasets.":[182],"Additionally,":[183],"introduce":[185],"Products-2023,":[186],"newly":[188],"curated,":[189],"manually":[190],"labeled":[191],"dataset":[192],"featuring":[193],"novel":[194],"concepts,":[195],"showcase":[197],"model\u2019s":[199],"recognize":[202],"benchmarking":[206],"it.":[208],"Significant":[209],"improvements":[210],"other":[216],"downstream":[217],"tasks":[218],"retrieval":[220],"further":[221],"highlight":[222],"superior":[224],"quality":[225],"learned":[228],"approach.":[231],"Code":[232],"available":[233],"https://github.com/shaunak27/grain-clip.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}