{"id":"https://openalex.org/W4392025629","doi":"https://doi.org/10.1109/aipr60534.2023.10440710","title":"Exploring CLIP for Real World, Text-based Image Retrieval","display_name":"Exploring CLIP for Real World, Text-based Image Retrieval","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4392025629","doi":"https://doi.org/10.1109/aipr60534.2023.10440710"},"language":"en","primary_location":{"id":"doi:10.1109/aipr60534.2023.10440710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aipr60534.2023.10440710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","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/A5000967930","display_name":"Manal Sultan","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manal Sultan","raw_affiliation_strings":["California Institute of Technology,Computer Science,Pasadena,California","Computer Science, California Institute of Technology, Pasadena, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Computer Science,Pasadena,California","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Computer Science, California Institute of Technology, Pasadena, California","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111133547","display_name":"Lia Jacobs","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lia Jacobs","raw_affiliation_strings":["Ohio State University,Computer Science,Columbus,Ohio","Computer Science, Ohio State University, Columbus, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University,Computer Science,Columbus,Ohio","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Computer Science, Ohio State University, Columbus, Ohio","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069295854","display_name":"Abby Stylianou","orcid":"https://orcid.org/0000-0002-4387-028X"},"institutions":[{"id":"https://openalex.org/I47838141","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08","country_code":"US","type":"education","lineage":["https://openalex.org/I47838141"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abby Stylianou","raw_affiliation_strings":["Saint Louis University,Computer Science,Saint Louis,Missouri","Computer Science, Saint Louis University, Saint Louis, Missouri"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Louis University,Computer Science,Saint Louis,Missouri","institution_ids":["https://openalex.org/I47838141"]},{"raw_affiliation_string":"Computer Science, Saint Louis University, Saint Louis, Missouri","institution_ids":["https://openalex.org/I47838141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051490260","display_name":"Robert Pless","orcid":"https://orcid.org/0000-0001-5775-8216"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Pless","raw_affiliation_strings":["George Washington University,Computer Science,Washington, DC,United States","Computer Science, George Washington University, Washington, DC, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Computer Science,Washington, DC,United States","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Computer Science, George Washington University, Washington, DC, United States","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4592,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73573073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983999729156494,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983999729156494,"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":0.9837999939918518,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9402999877929688,"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":0.7379617094993591},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5783290863037109},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5435090661048889},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4650728702545166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4116981327533722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35568878054618835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379617094993591},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5783290863037109},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5435090661048889},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4650728702545166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4116981327533722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35568878054618835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aipr60534.2023.10440710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aipr60534.2023.10440710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337430","display_name":"National Institute of Justice","ror":"https://ror.org/00v8p7w89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2535196960","https://openalex.org/W2891744193","https://openalex.org/W2903726692","https://openalex.org/W3009047829","https://openalex.org/W3209532394","https://openalex.org/W4224035735","https://openalex.org/W4288058287","https://openalex.org/W4292828970","https://openalex.org/W4306820534","https://openalex.org/W4312933868","https://openalex.org/W4378373043","https://openalex.org/W4378508580","https://openalex.org/W4379089756","https://openalex.org/W4387421691","https://openalex.org/W4390872508","https://openalex.org/W6791353385","https://openalex.org/W6802987763","https://openalex.org/W6809885388","https://openalex.org/W6846007759","https://openalex.org/W6852604893"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,68,90],"consider":[1],"the":[2,33,70,82,100,111],"ability":[3],"of":[4,35,52,72,97,113],"CLIP":[5,46,78],"features":[6,79],"to":[7,21],"support":[8],"text-driven":[9,73],"image":[10,26,37,74,83],"retrieval.":[11],"Traditional":[12],"image-based":[13],"queries":[14],"sometimes":[15],"misalign":[16],"with":[17],"user":[18],"intentions":[19],"due":[20],"their":[22],"focus":[23],"on":[24,49,77],"irrelevant":[25],"components.":[27],"To":[28],"overcome":[29],"this,":[30],"we":[31],"explore":[32,69],"potential":[34],"text-based":[36],"retrieval,":[38],"specifically":[39],"using":[40],"Contrastive":[41],"Language-Image":[42],"Pretraining":[43],"(CLIP)":[44],"models.":[45],"models,":[47],"trained":[48],"large":[50],"datasets":[51],"image-caption":[53],"pairs,":[54],"offer":[55],"a":[56,95,114],"promising":[57],"approach":[58],"by":[59,80],"allowing":[60],"natural":[61],"language":[62],"descriptions":[63],"for":[64,85],"more":[65,87],"targeted":[66],"queries.":[67,89],"effectiveness":[71],"retrieval":[75],"based":[76],"evaluating":[81],"similarity":[84],"progressively":[86],"detailed":[88],"find":[91,107],"that":[92,102,108],"there":[93],"is":[94],"sweet-spot":[96],"detail":[98],"in":[99,123],"text":[101],"gives":[103],"best":[104],"results":[105],"and":[106],"words":[109],"describing":[110],"\"tone\"":[112],"scene":[115],"(such":[116],"as":[117],"messy,":[118],"dingy)":[119],"are":[120],"quite":[121],"important":[122],"maximizing":[124],"text-image":[125],"similarity.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
