{"id":"https://openalex.org/W4412377833","doi":"https://doi.org/10.1145/3726302.3730326","title":"Assessing Effective Token Length of Multimodal Models for Text-to-Image Retrieval","display_name":"Assessing Effective Token Length of Multimodal Models for Text-to-Image Retrieval","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377833","doi":"https://doi.org/10.1145/3726302.3730326"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730326","doi":"https://doi.org/10.1145/3726302.3730326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730326","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730326","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027893567","display_name":"Le Nguyen","orcid":"https://orcid.org/0009-0000-1133-7918","observed_orcids":["https://orcid.org/0009-0000-1133-7918"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Nguyen","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0009-0000-1133-7918","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Preet Jain","orcid":"https://orcid.org/0009-0005-1398-8411","observed_orcids":["https://orcid.org/0009-0005-1398-8411"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preet Jain","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, USA"],"raw_orcid":"https://orcid.org/0009-0005-1398-8411","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krutik Panchal","orcid":"https://orcid.org/0009-0004-2138-5920","observed_orcids":["https://orcid.org/0009-0004-2138-5920"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krutik Panchal","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, USA"],"raw_orcid":"https://orcid.org/0009-0004-2138-5920","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045927406","display_name":"Tanvirul Alam","orcid":"https://orcid.org/0000-0003-4284-2743","observed_orcids":["https://orcid.org/0000-0003-4284-2743"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Tanvirul Alam","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-4284-2743","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001140269","display_name":"Nidhi Rastogi","orcid":"https://orcid.org/0000-0002-2002-3213","observed_orcids":["https://orcid.org/0000-0002-2002-3213"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhi Rastogi","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2002-3213","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13851065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3173","last_page":"3182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.9980000257492065,"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":0.000699999975040555,"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":0.0006000000284984708,"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/text-to-image-retrieval","display_name":"text-to-image retrieval","score":0.8709999918937683},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.828000009059906},{"id":"https://openalex.org/keywords/domain-specific-languages","display_name":"domain-specific languages","score":0.9810000061988831}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8266406059265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640089988708496},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6415666341781616},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5154936909675598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45897525548934937},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4407123029232025},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3837069272994995},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1185096800327301}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730326","doi":"https://doi.org/10.1145/3726302.3730326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730326","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730326","doi":"https://doi.org/10.1145/3726302.3730326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730326","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377833.pdf","grobid_xml":"https://content.openalex.org/works/W4412377833.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2886641317","https://openalex.org/W2897980926","https://openalex.org/W2990138404","https://openalex.org/W4225166070","https://openalex.org/W4376226279","https://openalex.org/W4385612782","https://openalex.org/W4386065512","https://openalex.org/W4396821179","https://openalex.org/W4399759483","https://openalex.org/W4400104247","https://openalex.org/W4400231894","https://openalex.org/W4400528838","https://openalex.org/W4401750770","https://openalex.org/W4403841197","https://openalex.org/W4406387563"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344"],"abstract_inverted_index":{"Multimodal":[0],"embedding":[1],"models":[2,67,119,164],"have":[3],"been":[4],"widely":[5,64],"adopted":[6],"in":[7,82,121],"text-toimage":[8],"retrieval,":[9],"enabling":[10],"direct":[11],"comparison":[12],"between":[13],"text":[14,23,169,192],"and":[15,58,68,86],"image":[16],"modalities.However,":[17],"how":[18,77,190],"well":[19],"they":[20],"handle":[21],"long":[22],"is":[24,150,202],"poorly":[25],"understood.For":[26],"instance,":[27],"Long-CLIP":[28,56],"found":[29],"that":[30,129,145,162,170,178],"OpenAI's":[31],"CLIP":[32],"model,":[33],"despite":[34],"having":[35],"a":[36,98,126,140,193],"77-token":[37],"input":[38,155],"limit,":[39],"maintains":[40],"optimal":[41],"performance":[42,199],"for":[43,158,204],"only":[44],"20":[45],"tokens-its":[46],"effective":[47,71,83,104,132,147,180],"token":[48,72,84,105,133,148,156,181],"length.In":[49],"this":[50],"paper,":[51],"we":[52,75,96,124],"build":[53],"on":[54,90,93],"the":[55,60,114,131,146,154,168,179],"study,":[57],"extend":[59],"analysis":[61],"to":[62,174],"other":[63],"used":[65,120],"multimodal":[66,118,137],"find":[69,177],"their":[70],"length.Unlike":[73],"Long-CLIP,":[74],"examine":[76],"domain-specific":[78,187],"language":[79,188],"influences":[80],"changes":[81],"length":[85,106,134,149,182],"explore":[87],"its":[88],"implications":[89],"different":[91,108],"domains.Based":[92],"our":[94],"findings,":[95],"create":[97],"comprehensive":[99],"reference":[100],"of":[101,117,135],"various":[102],"models'":[103],"across":[107],"domains;":[109],"offering":[110],"deeper":[111],"insights":[112],"into":[113],"true":[115],"limitations":[116],"text-to-image":[122],"retrieval.Finally,":[123],"introduce":[125],"systematic":[127],"benchmark":[128],"determines":[130],"any":[136],"model":[138,194],"using":[139],"given":[141,173],"dataset.Our":[142],"results":[143],"show":[144],"consistently":[151],"lower":[152],"than":[153],"limit":[157],"all":[159,167],"models,":[160],"meaning":[161],"these":[163],"cannot":[165],"utilize":[166],"can":[171,195],"be":[172],"them.We":[175],"also":[176],"varies":[183],"by":[184],"dataset,":[185],"with":[186],"influencing":[189],"much":[191],"use":[196],"before":[197],"retrieval":[198],"plateaus.Our":[200],"code":[201],"available":[203],"reproducibility":[205],"at":[206],"https://github.com/aiforsec/EffectiveTokenLength-MModels":[207]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-10-10T00:00:00"}