{"id":"https://openalex.org/W4372346856","doi":"https://doi.org/10.1109/icassp49357.2023.10097061","title":"Trust Your Partner\u2019s Friends: Hierarchical Cross-Modal Contrastive Pre-Training for Video-Text Retrieval","display_name":"Trust Your Partner\u2019s Friends: Hierarchical Cross-Modal Contrastive Pre-Training for Video-Text Retrieval","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346856","doi":"https://doi.org/10.1109/icassp49357.2023.10097061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109601974","display_name":"Yuhan Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Xiang","raw_affiliation_strings":["School of Infomatics, Xiamen University,Media Analytics and Computing Lab,Department of Artificial Intelligence,P.R. China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Infomatics, Xiamen University,Media Analytics and Computing Lab,Department of Artificial Intelligence,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859270","display_name":"Kaijian Liu","orcid":"https://orcid.org/0009-0004-8324-3637"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaijian Liu","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030884047","display_name":"Shixiang Tang","orcid":"https://orcid.org/0009-0005-0067-339X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shixiang Tang","raw_affiliation_strings":["The University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028486493","display_name":"Lei Bai","orcid":"https://orcid.org/0000-0003-3378-7201"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Bai","raw_affiliation_strings":["The University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860742","display_name":"Feng Zhu","orcid":"https://orcid.org/0009-0002-5759-9176"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhu","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024522346","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0001-5874-131X"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101445574","display_name":"Xianming Lin","orcid":"https://orcid.org/0000-0003-4739-8936"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianming Lin","raw_affiliation_strings":["School of Infomatics, Xiamen University,Media Analytics and Computing Lab,Department of Artificial Intelligence,P.R. China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Infomatics, Xiamen University,Media Analytics and Computing Lab,Department of Artificial Intelligence,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48598679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8219503164291382},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6520633697509766},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6287544965744019},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.552115261554718},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5476278066635132},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5339953303337097},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47517719864845276},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.4521799087524414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4364001154899597},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37222370505332947},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3215232491493225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219503164291382},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6520633697509766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6287544965744019},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.552115261554718},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5476278066635132},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5339953303337097},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47517719864845276},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.4521799087524414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4364001154899597},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37222370505332947},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3215232491493225},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2741903908","https://openalex.org/W2750526644","https://openalex.org/W2885775891","https://openalex.org/W2952132648","https://openalex.org/W2957775769","https://openalex.org/W2962934715","https://openalex.org/W2963524571","https://openalex.org/W2984008963","https://openalex.org/W3035635319","https://openalex.org/W3122640483","https://openalex.org/W3158986867","https://openalex.org/W3176398504","https://openalex.org/W3203711169","https://openalex.org/W4312384316","https://openalex.org/W4312974690","https://openalex.org/W6631516269","https://openalex.org/W6784184991"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2491583298","https://openalex.org/W2036154621","https://openalex.org/W2327827625","https://openalex.org/W2395860100","https://openalex.org/W795077857","https://openalex.org/W2376416463","https://openalex.org/W2007338512","https://openalex.org/W627697492"],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1],"has":[2],"greatly":[3],"benefited":[4],"from":[5,23],"the":[6,14,20,24,34,49,66,70,73,93,99,123],"massive":[7],"web":[8],"video":[9,53,113],"in":[10,45,92],"recent":[11],"years,":[12],"while":[13],"performance":[15],"is":[16],"still":[17],"limited":[18],"to":[19,32,61,88],"weak":[21],"supervision":[22],"uncurated":[25],"data.":[26],"In":[27],"this":[28],"work,":[29],"we":[30,79],"propose":[31],"leverage":[33],"well-represented":[35],"information":[36,44],"of":[37,48,69,76],"each":[38],"original":[39],"modality":[40],"and":[41,55,112,116],"exploit":[42],"complementary":[43],"two":[46],"views":[47],"same":[50,124],"video,":[51],"i.e.,":[52],"clips":[54],"captions,":[56],"by":[57],"using":[58],"one":[59],"view":[60],"obtain":[62],"positive":[63],"samples":[64,68],"with":[65],"neighboring":[67],"other.":[71],"Respecting":[72],"hierarchical":[74,83],"organization":[75],"real-world":[77],"data,":[78],"further":[80],"design":[81],"a":[82],"cross-modal":[84],"pre-training":[85],"method":[86,118],"(HCP)":[87],"learn":[89],"good":[90],"representations":[91],"common":[94],"embedding":[95],"space.":[96],"We":[97],"evaluate":[98],"pre-trained":[100],"model":[101],"on":[102],"three":[103],"downstream":[104],"tasks,":[105],"i.e.":[106],"text-to-video":[107],"retrieval,":[108],"action":[109],"step":[110],"localization":[111],"question":[114],"answering":[115],"our":[117],"outperforms":[119],"previous":[120],"works":[121],"under":[122],"setting.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}