{"id":"https://openalex.org/W4379806334","doi":"https://doi.org/10.1145/3591106.3592238","title":"CMMT: Cross-Modal Meta-Transformer for Video-Text Retrieval","display_name":"CMMT: Cross-Modal Meta-Transformer for Video-Text Retrieval","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806334","doi":"https://doi.org/10.1145/3591106.3592238"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592238","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5101551422","display_name":"Yizhao Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yizhao Gao","raw_affiliation_strings":["Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-6903-2962","affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085349794","display_name":"Zhiwu Lu","orcid":"https://orcid.org/0000-0003-0280-7724"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Lu","raw_affiliation_strings":["Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0003-0280-7724","affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101551422"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.3532,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57923312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"84"},"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8553147912025452},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.7461133599281311},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5297713279724121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4557170867919922},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41940781474113464},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41414502263069153},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3859291672706604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3581075072288513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553147912025452},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.7461133599281311},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5297713279724121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4557170867919922},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41940781474113464},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41414502263069153},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3859291672706604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3581075072288513},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592238","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2886641317","https://openalex.org/W2897439619","https://openalex.org/W2963017553","https://openalex.org/W2963078860","https://openalex.org/W2963350370","https://openalex.org/W2963916161","https://openalex.org/W2964105864","https://openalex.org/W2964241990","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W3034312118","https://openalex.org/W3035265375","https://openalex.org/W3035370595","https://openalex.org/W3043840704","https://openalex.org/W3105232955","https://openalex.org/W3154682722","https://openalex.org/W3155119115","https://openalex.org/W3174873881","https://openalex.org/W3176196997","https://openalex.org/W3176398504","https://openalex.org/W6600018615","https://openalex.org/W6600175564","https://openalex.org/W6600194071","https://openalex.org/W6600648412","https://openalex.org/W6604895162","https://openalex.org/W6629651325"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2350469024","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W2057384895"],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1,279],"has":[2,168,257],"drawn":[3],"great":[4],"attention":[5],"due":[6],"to":[7,43,61,82,199,226],"the":[8,18,37,157,189,214],"prosperity":[9],"of":[10,97,111,216],"online":[11],"video":[12,19,28,51,65,71,98,114,119,123,164,172,176],"contents.":[13],"Most":[14],"existing":[15],"methods":[16],"extract":[17],"embeddings":[20],"by":[21],"densely":[22],"sampling":[23],"abundant":[24],"(generally":[25],"dozens":[26],"of)":[27],"clips,":[29,72],"which":[30,104],"acquires":[31],"tremendous":[32],"computational":[33],"cost.":[34],"To":[35,211],"reduce":[36],"resource":[38],"consumption,":[39],"recent":[40],"works":[41],"propose":[42,129],"sparsely":[44,87],"sample":[45,94],"fewer":[46],"clips":[47,99,173],"from":[48,100],"each":[49,101,117,146,179,233],"raw":[50,102,118],"with":[52,67,162,184],"a":[53,63,95,112,121,130,141,151,221],"narrow":[54],"time":[55,92],"span.":[56],"However,":[57],"they":[58],"still":[59],"struggle":[60],"learn":[62,207],"reliable":[64],"representation":[66],"such":[68,126],"locally":[69],"sampled":[70,171],"especially":[73],"when":[74],"testing":[75],"on":[76,202,239],"cross-dataset":[77,251,276],"setting.":[78],"In":[79],"this":[80,84,192],"work,":[81],"overcome":[83],"problem,":[85],"we":[86,128,149,219,264],"and":[88,205,277],"globally":[89],"(with":[90],"wide":[91],"span)":[93],"handful":[96],"video,":[103],"can":[105,137],"be":[106,138],"regarded":[107],"as":[108],"different":[109],"samples":[110],"pseudo":[113,122,163,175],"class":[115,165],"(i.e.,":[116],"denotes":[120],"class).":[124,177],"From":[125],"viewpoint,":[127],"novel":[131],"Cross-Modal":[132],"Meta-Transformer":[133],"(CMMT)":[134],"model":[135,198,230,245],"that":[136,243,255,266],"trained":[139],"in":[140,145,250,260],"meta-learning":[142,194,269],"paradigm.":[143],"Concretely,":[144],"training":[147],"step,":[148],"conduct":[150],"cross-modal":[152],"fine-grained":[153],"classification":[154,180],"task":[155,181],"where":[156],"text":[158,235],"queries":[159],"are":[160],"classified":[161],"prototypes":[166],"(each":[167],"aggregated":[169],"all":[170],"per":[174],"Since":[178],"is":[182],"defined":[183],"different/new":[185],"videos":[186],"(by":[187],"simulating":[188],"evaluation":[190],"setting),":[191],"task-based":[193],"process":[195],"enables":[196],"our":[197,217,229,244,267],"generalize":[200],"well":[201],"new":[203,247,268],"tasks":[204],"thus":[206],"generalizable":[208],"video/text":[209],"representations.":[210],"further":[212],"enhance":[213],"generalizability":[215,259],"model,":[218],"induce":[220],"token-aware":[222],"adaptive":[223],"Transformer":[224],"module":[225],"dynamically":[227],"update":[228],"(prototypes)":[231],"for":[232],"individual":[234],"query.":[236],"Extensive":[237],"experiments":[238],"three":[240],"benchmarks":[241],"show":[242],"achieves":[246],"state-of-the-art":[248],"results":[249],"video-text":[252,261],"retrieval,":[253],"demonstrating":[254],"it":[256],"more":[258],"retrieval.":[262],"Importantly,":[263],"find":[265],"paradigm":[270],"indeed":[271],"brings":[272],"improvements":[273],"under":[274],"both":[275],"in-dataset":[278],"settings.":[280]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}