{"id":"https://openalex.org/W4323824539","doi":"https://doi.org/10.1109/iceic57457.2023.10049967","title":"A Unified framework based on Large-scale Momentum Contrastive learning for Text-Video Retrieval","display_name":"A Unified framework based on Large-scale Momentum Contrastive learning for Text-Video Retrieval","publication_year":2023,"publication_date":"2023-02-05","ids":{"openalex":"https://openalex.org/W4323824539","doi":"https://doi.org/10.1109/iceic57457.2023.10049967"},"language":"en","primary_location":{"id":"doi:10.1109/iceic57457.2023.10049967","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic57457.2023.10049967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5089828438","display_name":"Eungyeop Kim","orcid":"https://orcid.org/0009-0003-9881-5362"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Eungyeop Kim","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065547363","display_name":"Na\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-0931-4378"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nahyun Lee","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026518919","display_name":"Yoon-Sik Cho","orcid":"https://orcid.org/0000-0002-9110-7414"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoon-Sik Cho","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089828438"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48720226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9959999918937683,"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":0.7506197094917297},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.6006139516830444},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5420980453491211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.51576828956604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5137075185775757},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4795553386211395},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.46498343348503113},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46418800950050354},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4211026132106781},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3776870369911194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506197094917297},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6006139516830444},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5420980453491211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.51576828956604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5137075185775757},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4795553386211395},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.46498343348503113},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46418800950050354},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4211026132106781},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3776870369911194},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic57457.2023.10049967","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic57457.2023.10049967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321202","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2164290393","https://openalex.org/W2842511635","https://openalex.org/W2984008963","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W4285606530","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6684090549","https://openalex.org/W6784333009","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W2358990940","https://openalex.org/W2093931120","https://openalex.org/W2349116365","https://openalex.org/W3021708704","https://openalex.org/W2004231473","https://openalex.org/W2060895226","https://openalex.org/W2329812990","https://openalex.org/W2151991951"],"abstract_inverted_index":{"Large-scale":[0],"vision-language":[1],"representation":[2],"learning":[3,66,91,148],"has":[4,26],"shown":[5],"dramatic":[6],"advances":[7],"in":[8,31,85,108,162],"image-text":[9],"retrieval":[10,164],"studies.":[11],"On":[12],"top":[13],"of":[14,46,65,89,96,117,132,135],"that,":[15],"it":[16,33],"is":[17,80],"clear":[18],"that":[19,32,155],"the":[20,47,57,105,114,118,129,156],"CLIP":[21,59],"(Contrastive":[22],"Language-Image":[23],"Pre-training)":[24],"[1]":[25],"contributed":[27],"to":[28,61,100,120,123],"this":[29,133],"field":[30],"succeeded":[34],"pre-training":[35],"on":[36,75,165],"tremendous":[37],"web":[38],"multimedia":[39],"data":[40],"with":[41,69,72],"leveraging":[42],"contrastive":[43,90,147],"loss,":[44],"one":[45],"most":[48],"competitive":[49,160],"loss":[50],"for":[51,83],"multimodal":[52],"learning.":[53],"CLIP4CLIP":[54],"[2]":[55],"utilized":[56],"pre-trained":[58],"weight":[60],"appeal":[62],"its":[63],"performance":[64],"video":[67],"representations":[68],"textual":[70],"supervision":[71],"additional":[73],"post-pretraining":[74],"Howto100M":[76],"[3].":[77],"However,":[78],"there":[79],"still":[81],"room":[82],"elevation":[84],"CLIP4Clip":[86],"from":[87],"perspective":[88],"-":[92],"large":[93],"enough":[94],"instances":[95],"negative":[97],"samples":[98],"help":[99],"learn":[101],"better":[102],"representations,":[103],"as":[104],"batch":[106,111],"size":[107],"each":[109],"training":[110],"getting":[112],"larger,":[113],"more":[115,125],"chance":[116],"model":[119,158],"be":[121],"allowed":[122],"contrast":[124],"semantic":[126],"representations.":[127],"In":[128],"same":[130],"queue":[131],"point":[134],"view,":[136],"we":[137],"propose":[138],"CwMTVR":[139,157],"combining":[140],"Momentum":[141],"Contrast":[142],"(MoCo)":[143],"[4],":[144],"cross-modal":[145],"momentum":[146],"framework":[149],"into":[150],"CLIP4Clip.":[151],"Experimental":[152],"results":[153,161],"prove":[154],"achieve":[159],"text-video":[163],"MSVD":[166],"dataset.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}