{"id":"https://openalex.org/W4376607849","doi":"https://doi.org/10.1109/tip.2023.3275071","title":"End-to-End Pre-Training With Hierarchical Matching and Momentum Contrast for Text-Video Retrieval","display_name":"End-to-End Pre-Training With Hierarchical Matching and Momentum Contrast for Text-Video Retrieval","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4376607849","doi":"https://doi.org/10.1109/tip.2023.3275071","pmid":"https://pubmed.ncbi.nlm.nih.gov/37186535"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3275071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3275071","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5026647439","display_name":"Wenxue Shen","orcid":"https://orcid.org/0000-0002-5136-5865"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxue Shen","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5136-5865","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079828357","display_name":"Xiaosu Zhu","orcid":"https://orcid.org/0000-0001-7728-2518"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosu Zhu","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7728-2518","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003577897","display_name":"Gongfu Li","orcid":"https://orcid.org/0000-0003-0655-5317"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongfu Li","raw_affiliation_strings":["Corporate Development Group, Tencent Inc., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate Development Group, Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026647439"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.1195,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89236773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"5017","last_page":"5030"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"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":0.793405294418335},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5741422176361084},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5629675984382629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5479016304016113},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49770548939704895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48586294054985046},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4758301079273224},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4673946797847748},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.4568338096141815},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4430120587348938},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.41939878463745117},{"id":"https://openalex.org/keywords/explicit-semantic-analysis","display_name":"Explicit semantic analysis","score":0.41511255502700806},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.24724441766738892},{"id":"https://openalex.org/keywords/semantic-technology","display_name":"Semantic technology","score":0.16801822185516357},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.09827882051467896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793405294418335},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5741422176361084},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5629675984382629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479016304016113},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49770548939704895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48586294054985046},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4758301079273224},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4673946797847748},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.4568338096141815},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4430120587348938},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.41939878463745117},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.41511255502700806},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.24724441766738892},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.16801822185516357},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.09827882051467896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3275071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3275071","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:37186535","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37186535","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5133417063","display_name":null,"funder_award_id":"2018AAA0102200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G680623718","display_name":null,"funder_award_id":"U22A2097","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6864684409","display_name":null,"funder_award_id":"62122018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6971015501","display_name":null,"funder_award_id":"171106","funder_id":"https://openalex.org/F4320334945","funder_display_name":"Fok Ying Tong Education Foundation"},{"id":"https://openalex.org/G7314976618","display_name":null,"funder_award_id":"61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334945","display_name":"Fok Ying Tong Education Foundation","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":103,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W2138621090","https://openalex.org/W2170605888","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2786585376","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2885775891","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2914699769","https://openalex.org/W2952132648","https://openalex.org/W2952370363","https://openalex.org/W2963263347","https://openalex.org/W2963293463","https://openalex.org/W2963843782","https://openalex.org/W2963916161","https://openalex.org/W2965373594","https://openalex.org/W2965458216","https://openalex.org/W2975357369","https://openalex.org/W2975813532","https://openalex.org/W2979579363","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2998702515","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3035265375","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3094751268","https://openalex.org/W3099677434","https://openalex.org/W3105232955","https://openalex.org/W3122640483","https://openalex.org/W3145450063","https://openalex.org/W3145807616","https://openalex.org/W3153005511","https://openalex.org/W3154596443","https://openalex.org/W3160566314","https://openalex.org/W3166396011","https://openalex.org/W3167366812","https://openalex.org/W3168640669","https://openalex.org/W3171007011","https://openalex.org/W3171927989","https://openalex.org/W3174873881","https://openalex.org/W3175939205","https://openalex.org/W3176481196","https://openalex.org/W3176780013","https://openalex.org/W3176799298","https://openalex.org/W3180463990","https://openalex.org/W3197804339","https://openalex.org/W3198659451","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3206020652","https://openalex.org/W3207750165","https://openalex.org/W3209229003","https://openalex.org/W3210514413","https://openalex.org/W3213351348","https://openalex.org/W4200139856","https://openalex.org/W4210352519","https://openalex.org/W4213304546","https://openalex.org/W4225414521","https://openalex.org/W4225674167","https://openalex.org/W4225832925","https://openalex.org/W4226143692","https://openalex.org/W4283798613","https://openalex.org/W4285606530","https://openalex.org/W4286745719","https://openalex.org/W4292779060","https://openalex.org/W4294691145","https://openalex.org/W4295036294","https://openalex.org/W4297808394","https://openalex.org/W4304014690","https://openalex.org/W4312372711","https://openalex.org/W4312384316","https://openalex.org/W4385245566","https://openalex.org/W4394659899","https://openalex.org/W6631516269","https://openalex.org/W6684723771","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6766582784","https://openalex.org/W6766673545","https://openalex.org/W6767853649","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6778883912","https://openalex.org/W6784184991","https://openalex.org/W6784761581","https://openalex.org/W6791353385","https://openalex.org/W6793736971","https://openalex.org/W6794295097","https://openalex.org/W6797148833","https://openalex.org/W6801013943","https://openalex.org/W6803728867","https://openalex.org/W6840361807","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W2103835134","https://openalex.org/W2146812779","https://openalex.org/W1965623300","https://openalex.org/W2907506409","https://openalex.org/W1979325497","https://openalex.org/W2361271045","https://openalex.org/W4387489691","https://openalex.org/W2084010214","https://openalex.org/W2388581364","https://openalex.org/W2145769341"],"abstract_inverted_index":{"Lately,":[0],"video-language":[1,23,200],"pre-training":[2,24,53],"and":[3,41,58,81,117,138,216],"text-video":[4],"retrieval":[5,224],"have":[6,111],"attracted":[7],"significant":[8],"attention":[9],"with":[10,55,114],"the":[11,17,27,30,69,88,105,115,153,190,210,228],"explosion":[12],"of":[13,29,192,230],"multimedia":[14],"data":[15],"on":[16,220],"Internet.":[18],"However,":[19],"existing":[20],"approaches":[21],"for":[22,184],"typically":[25],"limit":[26],"exploitation":[28],"hierarchical":[31,70],"semantic":[32,39,44,71,77,112,212],"information":[33,40,72],"in":[34,73,107,123],"videos,":[35],"such":[36],"as":[37],"frame":[38],"global":[42],"video":[43,93,109],"information.":[45],"In":[46],"this":[47,108],"work,":[48],"we":[49],"present":[50],"an":[51],"end-to-end":[52],"network":[54],"Hierarchical":[56,126],"Matching":[57,136,140,147],"Momentum":[59],"Contrast":[60],"named":[61,206],"HMMC.":[62],"The":[63],"key":[64],"idea":[65],"is":[66,85,128,149],"to":[67,151,170,179,189,208],"explore":[68,209],"videos":[74,80,215],"via":[75],"multilevel":[76,211],"matching":[78,127],"between":[79,214],"texts.":[82,217],"This":[83],"design":[84],"motivated":[86],"by":[87,131],"observation":[89],"that":[90],"if":[91],"a":[92,96,100,172,197],"semantically":[94],"matches":[95],"text":[97,116],"(can":[98],"be":[99],"title,":[101],"tag":[102],"or":[103],"caption),":[104],"frames":[106,122],"usually":[110],"connections":[113,213],"show":[118],"higher":[119],"similarity":[120],"than":[121],"other":[124],"videos.":[125],"mainly":[129],"realized":[130],"two":[132,221],"proxy":[133,143],"tasks:":[134],"Video-Text":[135],"(VTM)":[137],"Frame-Text":[139],"(FTM).":[141],"Another":[142],"task:":[144],"Frame":[145],"Adjacency":[146],"(FAM)":[148],"proposed":[150],"enhance":[152],"single":[154],"visual":[155],"modality":[156],"representations":[157],"while":[158],"training":[159],"from":[160],"scratch.":[161],"Furthermore,":[162],"momentum":[163,174],"contrast":[164,175],"framework":[165],"was":[166],"introduced":[167],"into":[168],"HMMC":[169,178],"form":[171],"multimodal":[173],"framework,":[176],"enabling":[177],"incorporate":[180],"more":[181],"negative":[182],"samples":[183],"contrastive":[185],"learning":[186],"which":[187],"contributes":[188],"generalization":[191],"representations.":[193],"We":[194,233],"also":[195],"collected":[196],"large-scale":[198],"Chinese":[199],"dataset":[201],"(over":[202],"763k":[203],"unique":[204],"videos)":[205],"CHVTT":[207],"Experimental":[218],"results":[219],"major":[222],"Text-video":[223],"benchmark":[225],"datasets":[226],"demonstrate":[227],"advantages":[229],"our":[231,235],"methods.":[232],"release":[234],"code":[236],"at":[237],"https://github.com/cheetah003/HMMC.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}