{"id":"https://openalex.org/W4304014690","doi":"https://doi.org/10.1145/3503161.3547910","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","display_name":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304014690","doi":"https://doi.org/10.1145/3503161.3547910"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547910","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073144816","display_name":"Yiwei Ma","orcid":"https://orcid.org/0000-0002-8744-3423"},"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":"Yiwei Ma","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067500978","display_name":"Guohai Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohai Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"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":"Xiaoshuai Sun","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329266","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-3835-7975"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"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":"Rongrong Ji","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.7201,"has_fulltext":false,"cited_by_count":288,"citation_normalized_percentile":{"value":0.99483855,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"638","last_page":"647"},"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":0.9993000030517578,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9975000023841858,"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":0.8202552795410156},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7341833114624023},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.729398787021637},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5674561262130737},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5613839030265808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49150311946868896},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4840802252292633},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.477373331785202},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4517754912376404},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3662912845611572},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17263787984848022},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15031397342681885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202552795410156},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7341833114624023},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.729398787021637},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5674561262130737},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5613839030265808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49150311946868896},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4840802252292633},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.477373331785202},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4517754912376404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3662912845611572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17263787984848022},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15031397342681885},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547910","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1893116441","https://openalex.org/W1927052826","https://openalex.org/W2425121537","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2897439619","https://openalex.org/W2962964995","https://openalex.org/W2963017553","https://openalex.org/W2975813532","https://openalex.org/W2981851019","https://openalex.org/W3021397474","https://openalex.org/W3034730770","https://openalex.org/W3035265375","https://openalex.org/W3035309251","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3091588028","https://openalex.org/W3145450063","https://openalex.org/W3153005511","https://openalex.org/W3155119115","https://openalex.org/W3167939936","https://openalex.org/W3168640669","https://openalex.org/W3174873881","https://openalex.org/W3175824375","https://openalex.org/W3175939205","https://openalex.org/W3176824248","https://openalex.org/W3180463990","https://openalex.org/W3199493219","https://openalex.org/W3204670646","https://openalex.org/W4205480697","https://openalex.org/W4226200183","https://openalex.org/W4238846128","https://openalex.org/W4283271696"],"related_works":["https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W2358990940","https://openalex.org/W2004323682","https://openalex.org/W2093931120","https://openalex.org/W2349116365","https://openalex.org/W3021708704","https://openalex.org/W2004231473","https://openalex.org/W2060895226","https://openalex.org/W2642562988"],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1,16,169,187],"has":[2,17,47],"been":[3,18,49],"a":[4,102],"crucial":[5],"and":[6,44,68,72,126,157,166,174,206],"fundamental":[7],"task":[8],"in":[9,51,116],"multi-modal":[10,23],"research.":[11,53],"The":[12],"development":[13],"of":[14,94,163],"video-text":[15,110,186],"considerably":[19],"promoted":[20],"by":[21,83],"large-scale":[22],"contrastive":[24,105],"pre-training,":[25],"which":[26,37,121],"primarily":[27],"focuses":[28],"on":[29,151,168,183],"coarse-grained":[30,42,58,66,85],"or":[31,57],"fine-grained":[32,45,56,70,80,125],"contrast.":[33],"However,":[34,112],"cross-grained":[35,60,127],"contrast,":[36],"is":[38,73],"the":[39,63,78,84,92,117,139,148,152,161,175],"contrast":[40,61,153,173],"between":[41,65,154],"representations":[43],"representations,":[46],"rarely":[48],"explored":[50],"prior":[52],"Compared":[54],"with":[55],"contrasts,":[59],"calculate":[62],"correlation":[64],"features":[67,81],"each":[69],"feature,":[71],"able":[74],"to":[75,123,130,146],"filter":[76],"out":[77],"unnecessary":[79,164],"guided":[82],"feature":[86],"during":[87],"similarity":[88,118,128],"calculation,":[89],"thus":[90,159],"improving":[91],"accuracy":[93],"retrieval.":[95,111],"To":[96,133],"this":[97,99,135],"end,":[98],"paper":[100],"presents":[101],"novel":[103],"multi-grained":[104,172],"model,":[106],"namely":[107],"X-CLIP,":[108],"for":[109],"another":[113],"challenge":[114],"lies":[115],"aggregation":[119],"problem,":[120],"aims":[122],"aggregate":[124],"matrices":[129],"instance-level":[131],"similarity.":[132],"address":[134],"challenge,":[136],"we":[137],"propose":[138],"Attention":[140],"Over":[141],"Similarity":[142],"Matrix":[143],"(AOSM)":[144],"module":[145],"make":[147],"model":[149],"focus":[150],"essential":[155],"frames":[156,165],"words,":[158],"lowering":[160],"impact":[162],"words":[167],"results.":[170],"With":[171],"proposed":[176],"AOSM":[177],"module,":[178],"X-CLIP":[179],"achieves":[180],"outstanding":[181],"performance":[182],"five":[184],"widely-used":[185],"datasets,":[188],"including":[189],"MSR-VTT":[190],"(49.3":[191],"[email":[192,196,200,204,209],"protected]),":[193,197,201],"MSVD":[194],"(50.4":[195],"LSMDC":[198],"(26.1":[199],"DiDeMo":[202],"(47.8":[203],"protected])":[205],"ActivityNet":[207],"(46.2":[208],"protected]).":[210]},"counts_by_year":[{"year":2026,"cited_by_count":53},{"year":2025,"cited_by_count":88},{"year":2024,"cited_by_count":106},{"year":2023,"cited_by_count":41}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}