{"id":"https://openalex.org/W4290097518","doi":"https://doi.org/10.1145/3524273.3528181","title":"CrispSearch","display_name":"CrispSearch","publication_year":2022,"publication_date":"2022-06-14","ids":{"openalex":"https://openalex.org/W4290097518","doi":"https://doi.org/10.1145/3524273.3528181"},"language":"en","primary_location":{"id":"doi:10.1145/3524273.3528181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524273.3528181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM Multimedia Systems Conference","raw_type":"proceedings-article"},"type":"article","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/A5101545956","display_name":"Zhiming Hu","orcid":"https://orcid.org/0000-0002-5105-9753"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhiming Hu","raw_affiliation_strings":["Samsung AI Centre, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre, Toronto, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115393939","display_name":"Lan Xiao","orcid":"https://orcid.org/0009-0007-0265-0727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan Xiao","raw_affiliation_strings":["Pinterest, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Pinterest, Toronto, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043133820","display_name":"Mete Kemertas","orcid":"https://orcid.org/0009-0007-1314-1602"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mete Kemertas","raw_affiliation_strings":["Samsung AI Centre, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre, Toronto, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115393943","display_name":"Caleb Phillips","orcid":"https://orcid.org/0009-0008-9612-8821"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Caleb Phillips","raw_affiliation_strings":["Samsung AI Centre, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre, Toronto, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025164458","display_name":"Iqbal Mohomed","orcid":"https://orcid.org/0009-0008-0598-8966"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Iqbal Mohomed","raw_affiliation_strings":["Samsung AI Centre, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre, Toronto, Canada","institution_ids":["https://openalex.org/I4210123574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017305009","display_name":"Afsaneh Fazly","orcid":"https://orcid.org/0000-0002-4479-4901"},"institutions":[{"id":"https://openalex.org/I4210123574","display_name":"Centre for Social Innovation","ror":"https://ror.org/03trz9s27","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210123574"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Afsaneh Fazly","raw_affiliation_strings":["Samsung AI Centre, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Samsung AI Centre, Toronto, Canada","institution_ids":["https://openalex.org/I4210123574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101545956"],"corresponding_institution_ids":["https://openalex.org/I4210123574"],"apc_list":null,"apc_paid":null,"fwci":0.302,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53588401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"72"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9945999979972839,"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":0.8902601003646851},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5733522772789001},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5624982714653015},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5344831943511963},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5244748592376709},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4789305627346039},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.44539833068847656},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4284884035587311},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.417322039604187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39196494221687317},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32649117708206177},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2443934679031372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8902601003646851},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5733522772789001},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5624982714653015},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5344831943511963},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5244748592376709},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4789305627346039},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.44539833068847656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4284884035587311},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.417322039604187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39196494221687317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32649117708206177},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2443934679031372},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524273.3528181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524273.3528181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM Multimedia Systems Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2185175083","https://openalex.org/W2508429489","https://openalex.org/W2559655401","https://openalex.org/W2745461083","https://openalex.org/W2963341956","https://openalex.org/W3016923549","https://openalex.org/W3035588244","https://openalex.org/W3091588028","https://openalex.org/W3166304536"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2798997222","https://openalex.org/W2798198862","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W2611989081"],"abstract_inverted_index":{"Advances":[0],"in":[1,15,25,126,167,255],"deep":[2],"learning":[3,55],"have":[4],"enabled":[5],"accurate":[6],"language-based":[7,172],"search":[8,43,289],"and":[9,67,103,185,222,249,290],"retrieval,":[10],"e.g.,":[11],"over":[12,263],"user":[13],"photos,":[14],"the":[16,26,72,136,161,198,206,238,264],"cloud.":[17],"Many":[18],"users":[19],"prefer":[20],"to":[21,29,124,181,224,260,287],"store":[22],"their":[23],"photos":[24],"home":[27],"due":[28],"privacy":[30],"concerns.":[31],"As":[32],"such,":[33],"a":[34,64,76,84,98,127,131,155,183,190,195,214,225,256,284],"need":[35],"arises":[36],"for":[37,141,145,170,228,237],"models":[38,50,236],"that":[39,58,89,158,252],"can":[40],"perform":[41],"cross-modal":[42,48,147],"on":[44,149,242],"resource-limited":[45],"devices.":[46,151],"State-of-the-art":[47],"retrieval":[49,79,148,162],"achieve":[51],"high":[52,78],"accuracy":[53,169],"through":[54],"entangled":[56],"representations":[57],"enable":[59],"fine-grained":[60],"similarity":[61],"calculation":[62],"between":[63],"language":[65,196],"query":[66],"an":[68,104],"image,":[69],"but":[70,96],"at":[71],"expense":[73],"of":[74,87,106,116,118,135,205,216,258,279],"having":[75],"prohibitively":[77],"latency.":[80],"Alternatively,":[81],"there":[82],"is":[83,180],"new":[85],"class":[86],"methods":[88,138,267],"exhibits":[90],"good":[91],"performance":[92,270],"with":[93,164,189,233,268],"low":[94],"latency,":[95],"requires":[97],"lot":[99],"more":[100,108],"computational":[101],"resources,":[102],"order":[105],"magnitude":[107],"training":[109,280],"data":[110],"(i.e.":[111],"large":[112],"web-scraped":[113],"datasets":[114,246],"consisting":[115],"millions":[117,278],"image-caption":[119],"pairs)":[120],"making":[121,282],"them":[122],"infeasible":[123],"use":[125],"commercial":[128,143],"context.":[129],"From":[130],"pragmatic":[132,285],"perspective,":[133],"none":[134],"existing":[137],"are":[139],"suitable":[140],"developing":[142],"applications":[144],"low-latency":[146],"low-resource":[150],"We":[152],"propose":[153],"CrispSearch,":[154],"cascaded":[156],"approach":[157,179],"greatly":[159],"reduces":[160],"latency":[163],"minimal":[165],"loss":[166],"ranking":[168],"on-device":[171,288],"image":[173,208],"retrieval.":[174,291],"The":[175],"idea":[176],"behind":[177],"our":[178,273],"combine":[182],"light-weight":[184],"runtime-efficient":[186],"coarse":[187,199],"model":[188,200,227],"fine":[191,226,239,266],"re-ranking":[192,240],"stage.":[193],"Given":[194],"query,":[197],"effectively":[201],"filters":[202],"out":[203],"many":[204],"irrelevant":[207],"candidates.":[209],"After":[210],"this":[211],"filtering,":[212],"only":[213],"handful":[215],"strong":[217],"candidates":[218],"will":[219],"be":[220],"selected":[221],"sent":[223],"re-ranking.":[229],"Extensive":[230],"experimental":[231],"results":[232,254],"two":[234,243],"SOTA":[235,265],"stage,":[241],"standard":[244],"benchmark":[245],"(namely,":[247],"MSCOCO":[248],"Flickr30k)":[250],"show":[251],"CrispSearch":[253],"speedup":[257],"up":[259],"38":[261],"times":[262],"negligible":[269],"degradation.":[271],"Moreover,":[272],"method":[274],"does":[275],"not":[276],"require":[277],"instances,":[281],"it":[283],"solution":[286]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-08-06T00:00:00"}