{"id":"https://openalex.org/W4312655527","doi":"https://doi.org/10.1109/tmm.2022.3227416","title":"Transferring Image-CLIP to Video-Text Retrieval via Temporal Relations","display_name":"Transferring Image-CLIP to Video-Text Retrieval via Temporal Relations","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4312655527","doi":"https://doi.org/10.1109/tmm.2022.3227416"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3227416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3227416","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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":null,"display_name":"Han Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Fang","raw_affiliation_strings":["China Telecom Corporation Ltd. Digital Intelligence Technology Company, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Digital Intelligence Technology Company, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065035829","display_name":"Pengfei Xiong","orcid":null},"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":"Pengfei Xiong","raw_affiliation_strings":["Tencent Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Technology, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063529024","display_name":"Luhui Xu","orcid":"https://orcid.org/0000-0002-2478-1978"},"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":"Luhui Xu","raw_affiliation_strings":["Tencent Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2478-1978","affiliations":[{"raw_affiliation_string":"Tencent Technology, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004450394","display_name":"Wenhan Luo","orcid":"https://orcid.org/0000-0002-5697-4168"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Luo","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-5697-4168","affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7414,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91811107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"7772","last_page":"7785"},"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":0.984000027179718,"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":0.977400004863739,"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":0.8858058452606201},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6299228668212891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6092996597290039},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4980278015136719},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.46750888228416443},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3617042303085327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3431665301322937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3357667922973633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8858058452606201},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6299228668212891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6092996597290039},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4980278015136719},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46750888228416443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3617042303085327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3431665301322937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357667922973633},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2022.3227416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3227416","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-139218","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-139218","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"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":99,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1893116441","https://openalex.org/W1927052826","https://openalex.org/W2342543219","https://openalex.org/W2425121537","https://openalex.org/W2625366777","https://openalex.org/W2735673432","https://openalex.org/W2753311918","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2842511635","https://openalex.org/W2883891001","https://openalex.org/W2885775891","https://openalex.org/W2897439619","https://openalex.org/W2914699769","https://openalex.org/W2951019013","https://openalex.org/W2962784628","https://openalex.org/W2963017553","https://openalex.org/W2963521717","https://openalex.org/W2975813532","https://openalex.org/W2980037812","https://openalex.org/W2981578854","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2990503944","https://openalex.org/W2996478685","https://openalex.org/W2999004587","https://openalex.org/W3002095953","https://openalex.org/W3003460937","https://openalex.org/W3015686016","https://openalex.org/W3035265375","https://openalex.org/W3035303837","https://openalex.org/W3035356601","https://openalex.org/W3035454331","https://openalex.org/W3035516727","https://openalex.org/W3035552787","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3043990051","https://openalex.org/W3080184051","https://openalex.org/W3081484346","https://openalex.org/W3086629156","https://openalex.org/W3088460296","https://openalex.org/W3088744711","https://openalex.org/W3102887392","https://openalex.org/W3103668594","https://openalex.org/W3105232955","https://openalex.org/W3107973541","https://openalex.org/W3135773387","https://openalex.org/W3137120824","https://openalex.org/W3145807616","https://openalex.org/W3152798676","https://openalex.org/W3153005511","https://openalex.org/W3168640669","https://openalex.org/W3173223111","https://openalex.org/W3174873881","https://openalex.org/W3175939205","https://openalex.org/W3176398504","https://openalex.org/W3176896951","https://openalex.org/W3180463990","https://openalex.org/W3197804339","https://openalex.org/W3204588463","https://openalex.org/W3207439579","https://openalex.org/W3212304713","https://openalex.org/W3216905989","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4210900713","https://openalex.org/W4214612132","https://openalex.org/W4225414521","https://openalex.org/W4225845939","https://openalex.org/W4226289673","https://openalex.org/W4285345750","https://openalex.org/W4287704005","https://openalex.org/W4297808394","https://openalex.org/W4312372711","https://openalex.org/W4312999114","https://openalex.org/W4394659899","https://openalex.org/W6631516269","https://openalex.org/W6684090549","https://openalex.org/W6739901393","https://openalex.org/W6750041603","https://openalex.org/W6753351450","https://openalex.org/W6766582784","https://openalex.org/W6768851824","https://openalex.org/W6772527114","https://openalex.org/W6773523483","https://openalex.org/W6780226713","https://openalex.org/W6781860016","https://openalex.org/W6784184991","https://openalex.org/W6784333009","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6792275077","https://openalex.org/W6793759846","https://openalex.org/W6801013943","https://openalex.org/W6803545775","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2372403409","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W4242726756","https://openalex.org/W2355048207","https://openalex.org/W3126051647","https://openalex.org/W2750422482"],"abstract_inverted_index":{"We":[0,144],"present":[1],"a":[2,41,56,91,105],"novel":[3],"network":[4],"to":[5,11,27,96,110,137],"transfer":[6],"the":[7,21,29,48,78,112,121,134,165],"image-language":[8,50],"pre-trained":[9,49],"model":[10,89,136],"video-text":[12,43,73],"retrieval":[13,170],"in":[14,20],"an":[15],"end-to-end":[16],"manner.":[17],"Leading":[18],"approaches":[19],"domain":[22],"of":[23,61,114],"video-and-language":[24],"learning":[25,131],"try":[26],"distill":[28],"spatio-temporal":[30],"video":[31,70,102,115],"features":[32],"and":[33,38,52,63,65,72,104,117,119,132,152,158,168,176],"multi-modal":[34],"interaction":[35],"between":[36,69],"videos":[37],"language":[39],"from":[40],"large-scale":[42],"dataset.":[44],"Differently,":[45],"we":[46],"leverage":[47],"model,":[51,87],"simplify":[53],"it":[54],"as":[55],"two-stage":[57],"framework":[58],"including":[59,149,172],"co-learning":[60],"image":[62],"text,":[64],"enhancing":[66],"temporal":[67,101,126],"relations":[68],"frames":[71],"respectively.":[74],"Specifically,":[75],"based":[76],"on":[77,140,164],"spatial":[79],"semantics":[80],"captured":[81],"by":[82],"Contrastive":[83],"Language-Image":[84],"Pre-training":[85],"(CLIP)":[86],"our":[88,159],"involves":[90],"Temporal":[92,106],"Difference":[93],"Block":[94,108],"(TDB)":[95],"capture":[97],"motions":[98],"at":[99],"fine":[100],"frames,":[103],"Alignment":[107],"(TAB)":[109],"re-align":[111],"tokens":[113],"clips":[116],"phrases":[118],"enhance":[120],"cross-modal":[122],"correlation.":[123],"These":[124],"two":[125],"blocks":[127],"efficiently":[128],"realize":[129],"video-language":[130],"enable":[133],"proposed":[135,160],"scale":[138],"well":[139],"comparatively":[141],"small":[142],"datasets.":[143],"conduct":[145],"extensive":[146],"experimental":[147],"studies":[148,151],"ablation":[150],"comparisons":[153],"with":[154],"existing":[155],"SOTA":[156],"methods,":[157],"approach":[161],"outperforms":[162],"them":[163],"popularly-employed":[166],"text-to-video":[167],"video-to-text":[169],"benchmarks,":[171],"MSR-VTT,":[173],"MSVD,":[174],"LSMDC,":[175],"VATEX.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}