{"id":"https://openalex.org/W4284701099","doi":"https://doi.org/10.1145/3477495.3531666","title":"Golden Retriever","display_name":"Golden Retriever","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4284701099","doi":"https://doi.org/10.1145/3477495.3531666"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3531666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531666","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5070253689","display_name":"Florian Schneider","orcid":"https://orcid.org/0000-0002-7052-8404"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Schneider","raw_affiliation_strings":["Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"3245","last_page":"3250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.8279374837875366},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7716931104660034},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5546358227729797},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.536933958530426},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5089988708496094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5038616061210632},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4271402359008789},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41592249274253845},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40284445881843567},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39268431067466736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1150243878364563},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07540366053581238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279374837875366},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7716931104660034},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5546358227729797},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.536933958530426},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5089988708496094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5038616061210632},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4271402359008789},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41592249274253845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40284445881843567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39268431067466736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1150243878364563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07540366053581238},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477495.3531666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531666","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G6276684567","display_name":null,"funder_award_id":"TRR 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2185175083","https://openalex.org/W2493916176","https://openalex.org/W2739351760","https://openalex.org/W2745461083","https://openalex.org/W2747329762","https://openalex.org/W2962828264","https://openalex.org/W2998702515","https://openalex.org/W3023742835","https://openalex.org/W3104033643","https://openalex.org/W3135367836","https://openalex.org/W3213100861","https://openalex.org/W4212774754","https://openalex.org/W4239019441"],"related_works":["https://openalex.org/W1504288058","https://openalex.org/W2331674254","https://openalex.org/W2167293474","https://openalex.org/W3042897387","https://openalex.org/W2048505601","https://openalex.org/W2017205855","https://openalex.org/W2979079341","https://openalex.org/W2358403311","https://openalex.org/W2031347084","https://openalex.org/W2891108385"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,58,75,91,117],"present":[4],"the":[5,34,53,62,72,77,81,85,100,119,145,151,153,170],"Golden":[6,120,171],"Retriever,":[7],"a":[8,68,88,93,123,139,176],"system":[9,24,154],"leveraging":[10],"state-of-the-art":[11],"visio-linguistic":[12],"models":[13],"(VLMs)":[14],"for":[15,107,130],"real-time":[16,50],"text-image":[17],"retrieval.":[18],"The":[19],"unique":[20],"feature":[21],"of":[22,64,87,102,112,175],"our":[23],"is":[25,122,147],"that":[26],"it":[27],"can":[28,155],"focus":[29],"on":[30,99],"words":[31,132],"contained":[32],"in":[33,71],"textual":[35,109],"query,":[36],"i.e.,":[37],"locate":[38],"and":[39,52,79,95],"high-light":[40],"them":[41],"within":[42,133],"retrieved":[43,166],"images.":[44],"An":[45],"efficient":[46,96],"two-stage":[47],"process":[48],"implements":[49],"capability":[51],"ability":[54],"to":[55,104,137],"focus.":[56],"Therefore,":[57],"first":[59],"drastically":[60],"reduce":[61],"number":[63],"images":[65,78,106,163],"processed":[66],"by":[67],"VLM.":[69,89],"Then,":[70],"second":[73],"stage,":[74],"rank":[76],"highlight":[80],"focussed":[82],"word":[83],"using":[84],"outputs":[86],"Further,":[90],"introduce":[92],"new":[94],"algorithm":[97],"based":[98],"idea":[101],"TF-IDF":[103],"retrieve":[105],"short":[108],"queries.":[110],"One":[111],"multiple":[113],"use":[114],"cases":[115],"where":[116,127,162],"employ":[118],"Retriever":[121,172],"language":[124],"learner":[125],"scenario,":[126],"visual":[128],"cues":[129],"\"difficult\"":[131],"sentences":[134],"are":[135],"provided":[136],"improve":[138],"user's":[140],"reading":[141],"comprehension.":[142],"However,":[143],"since":[144],"backend":[146],"completely":[148],"decoupled":[149],"from":[150],"frontend,":[152],"be":[156,165],"integrated":[157],"into":[158],"any":[159],"other":[160],"application":[161],"must":[164],"fast.":[167],"We":[168],"demonstrate":[169],"with":[173],"screenshots":[174],"minimalistic":[177],"user":[178],"interface.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-08T00:00:00"}