{"id":"https://openalex.org/W4387168132","doi":"https://doi.org/10.1007/s10791-023-09425-2","title":"Multimodal video retrieval with CLIP: a user study","display_name":"Multimodal video retrieval with CLIP: a user study","publication_year":2023,"publication_date":"2023-09-29","ids":{"openalex":"https://openalex.org/W4387168132","doi":"https://doi.org/10.1007/s10791-023-09425-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-023-09425-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-023-09425-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-023-09425-2.pdf","source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10791-023-09425-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070623225","display_name":"Tayfun Alpay","orcid":null},"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":true,"raw_author_name":"Tayfun Alpay","raw_affiliation_strings":["HITeC - Hamburger Informatik Technologie-Center e.V., University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HITeC - Hamburger Informatik Technologie-Center e.V., University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015567592","display_name":"Sven Magg","orcid":"https://orcid.org/0000-0002-0589-6585"},"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":"Sven Magg","raw_affiliation_strings":["HITeC - Hamburger Informatik Technologie-Center e.V., University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HITeC - Hamburger Informatik Technologie-Center e.V., University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092966186","display_name":"Philipp Broze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philipp Broze","raw_affiliation_strings":["Nachtblau GmbH, Stra\u00dfenbahnring 18, 20251, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nachtblau GmbH, Stra\u00dfenbahnring 18, 20251, Hamburg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056460243","display_name":"Daniel Speck","orcid":null},"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":"Daniel Speck","raw_affiliation_strings":["HITeC - Hamburger Informatik Technologie-Center e.V., University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HITeC - Hamburger Informatik Technologie-Center e.V., University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070623225"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":{"value":3290,"currency":"USD","value_usd":3290},"fwci":1.0739,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76206187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"26","issue":"1-2","first_page":null,"last_page":null},"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/T11439","display_name":"Video Analysis and Summarization","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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9944000244140625,"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":0.9213528633117676},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5738883018493652},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5508997440338135},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.516664981842041},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.47169116139411926},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.45284193754196167},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.44725093245506287},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.41874775290489197},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3967255651950836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9213528633117676},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5738883018493652},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5508997440338135},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.516664981842041},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.47169116139411926},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.45284193754196167},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.44725093245506287},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.41874775290489197},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3967255651950836},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10791-023-09425-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-023-09425-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-023-09425-2.pdf","source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10791-023-09425-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-023-09425-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-023-09425-2.pdf","source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387168132.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1985816353","https://openalex.org/W2016053056","https://openalex.org/W2808399042","https://openalex.org/W2811088668","https://openalex.org/W2895817099","https://openalex.org/W2950077968","https://openalex.org/W2963469388","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W2981716253","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2998702515","https://openalex.org/W3011906630","https://openalex.org/W3043840704","https://openalex.org/W3091588028","https://openalex.org/W3123404882","https://openalex.org/W3126291783","https://openalex.org/W3126792443","https://openalex.org/W3128108348","https://openalex.org/W3135367836","https://openalex.org/W3154596443","https://openalex.org/W3173909648","https://openalex.org/W3175939205","https://openalex.org/W3183241901","https://openalex.org/W3201264086","https://openalex.org/W4212774754","https://openalex.org/W4214612132","https://openalex.org/W4237212714","https://openalex.org/W4285606530","https://openalex.org/W4297081765","https://openalex.org/W4312560592","https://openalex.org/W4361854723","https://openalex.org/W6603229541","https://openalex.org/W6778883912","https://openalex.org/W6803376173","https://openalex.org/W6912494966"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W655728004","https://openalex.org/W2046272293"],"abstract_inverted_index":{"Abstract":[0],"Recent":[1],"machine":[2],"learning":[3],"advances":[4],"demonstrate":[5],"the":[6,19,46,50,53,148,155,176,191,214],"effectiveness":[7],"of":[8,15,40,49,67,122,179,216],"zero-shot":[9],"models":[10,229],"trained":[11],"on":[12,37,175],"large":[13,228],"amounts":[14],"data":[16,164],"collected":[17,163],"from":[18],"internet.":[20],"Among":[21],"these,":[22],"CLIP":[23,76,123,232],"(Contrastive":[24],"Language-Image":[25],"Pre-training)":[26],"has":[27],"been":[28],"introduced":[29],"as":[30,231],"a":[31,38,85,110,137],"multimodal":[32,81],"model":[33,51],"with":[34,140,190],"high":[35],"accuracy":[36],"number":[39],"different":[41],"tasks":[42],"and":[43,119,144,168,186,206,219],"domains.":[44],"However,":[45],"unconstrained":[47],"nature":[48],"begs":[52],"question":[54],"whether":[55,75],"it":[56],"can":[57,77],"be":[58,78,224],"deployed":[59],"in":[60,65,84,109,147,234],"open-domain":[61,158],"real-word":[62],"applications":[63],"effectively":[64,233],"front":[66],"non-technical":[68],"users.":[69],"In":[70],"this":[71,89],"paper,":[72],"we":[73,91,129,162],"evaluate":[74],"used":[79],"for":[80,124],"video":[82,125,141,159],"retrieval":[83,98,126,133,160,180,184],"real-world":[86,235],"environment.":[87],"For":[88],"purpose,":[90],"implemented":[92,105],"impa":[93],",":[94],"an":[95,117],"efficient":[96,120,208,220],"shot-based":[97],"system":[99,134],"powered":[100],"by":[101,135],"CLIP.":[102],"We":[103,194],"additionally":[104],"advanced":[106,198],"query":[107],"functionality":[108],"unified":[111],"graphical":[112],"user":[113,138,204,221],"interface":[114],"to":[115,223,226],"facilitate":[116],"intuitive":[118,218],"usage":[121],"tasks.":[127],"Finally,":[128],"empirically":[130],"evaluated":[131],"our":[132,197,211],"performing":[136],"study":[139],"editing":[142],"professionals":[143],"journalists":[145],"working":[146],"TV":[149],"news":[150],"media":[151],"industry.":[152],"After":[153],"having":[154],"participants":[156],"solve":[157],"tasks,":[161],"via":[165],"questionnaires,":[166],"interviews,":[167],"UI":[169],"interaction":[170],"logs.":[171],"Our":[172],"evaluation":[173],"focused":[174],"perceived":[177],"intuitiveness":[178],"using":[181],"natural":[182],"language,":[183],"accuracy,":[185,203],"how":[187],"users":[188],"interacted":[189],"system\u2019s":[192],"UI.":[193],"found":[195],"that":[196],"features":[199],"yield":[200],"higher":[201],"task":[202],"ratings,":[205],"more":[207],"queries.":[209],"Overall,":[210],"results":[212],"show":[213],"importance":[215],"designing":[217],"interfaces":[222],"able":[225],"deploy":[227],"such":[230],"scenarios.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
