{"id":"https://openalex.org/W4399407106","doi":"https://doi.org/10.1109/tmm.2024.3410532","title":"Lightweight Model Pre-Training via Language Guided Knowledge Distillation","display_name":"Lightweight Model Pre-Training via Language Guided Knowledge Distillation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399407106","doi":"https://doi.org/10.1109/tmm.2024.3410532"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3410532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3410532","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":"https://openalex.org/A5101698381","display_name":"Mingsheng Li","orcid":"https://orcid.org/0009-0004-3758-0018"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Li","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-3758-0018","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017173877","display_name":"Lin Zhang","orcid":"https://orcid.org/0009-0006-5293-9169"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-5293-9169","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032269714","display_name":"Mingzhen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhen Zhu","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101462087","display_name":"Zilong Huang","orcid":"https://orcid.org/0000-0002-6744-0671"},"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":"Zilong Huang","raw_affiliation_strings":["Tencent GY-Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6744-0671","affiliations":[{"raw_affiliation_string":"Tencent GY-Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003400275","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0001-5570-2710"},"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":"Gang Yu","raw_affiliation_strings":["Tencent GY-Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5570-2710","affiliations":[{"raw_affiliation_string":"Tencent GY-Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013595","display_name":"Jiayuan Fan","orcid":"https://orcid.org/0000-0001-7494-0255"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Fan","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7494-0255","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021220108","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0002-0779-9818"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0779-9818","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59017864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"26","issue":null,"first_page":"10720","last_page":"10730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9728000164031982,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9728000164031982,"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/T10028","display_name":"Topic Modeling","score":0.9603000283241272,"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":0.8745420575141907},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5248851180076599},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5210004448890686},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5051723122596741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.502112865447998},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4293982982635498},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39696821570396423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8745420575141907},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5248851180076599},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5210004448890686},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5051723122596741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.502112865447998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4293982982635498},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39696821570396423},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3410532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3410532","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G3977413633","display_name":"\u5b50\u7c7b\u611f\u77e5\u6df1\u5ea6\u5b66\u4e60\u7406\u8bba\u53ca\u5176\u5e94\u7528\u7814\u7a76","funder_award_id":"62071127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5491202952","display_name":"\u9762\u5411\u6709\u9650\u7b97\u529b\u548c\u6570\u636e\u8d44\u6e90\u7684\u591a\u6a21\u6001\u878d\u5408\u4e0e\u77e5\u8bc6\u63a8\u7406\u7814\u7a76","funder_award_id":"23ZR1402900","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G7626924423","display_name":null,"funder_award_id":"62101137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2294370754","https://openalex.org/W2340897893","https://openalex.org/W2560023338","https://openalex.org/W2737258237","https://openalex.org/W2739879705","https://openalex.org/W2896457183","https://openalex.org/W2910628332","https://openalex.org/W2948672349","https://openalex.org/W2962858109","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2991391304","https://openalex.org/W3035524453","https://openalex.org/W3096189675","https://openalex.org/W3171007011","https://openalex.org/W3174102142","https://openalex.org/W3193078976","https://openalex.org/W4213303451","https://openalex.org/W4213304546","https://openalex.org/W4226058394","https://openalex.org/W4226426325","https://openalex.org/W4285288414","https://openalex.org/W4312270234","https://openalex.org/W4312608676","https://openalex.org/W4312818263","https://openalex.org/W4312956471","https://openalex.org/W4313144836","https://openalex.org/W4316661142","https://openalex.org/W4365483249","https://openalex.org/W4378194747","https://openalex.org/W4382999123","https://openalex.org/W4384080288","https://openalex.org/W4385245566","https://openalex.org/W4386065874","https://openalex.org/W4386075705","https://openalex.org/W4387623885","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6730179637","https://openalex.org/W6757817989","https://openalex.org/W6764322716","https://openalex.org/W6769906912","https://openalex.org/W6788280241","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6794071484","https://openalex.org/W6801567822","https://openalex.org/W6803728867","https://openalex.org/W6803953248","https://openalex.org/W6810249204","https://openalex.org/W6840857800","https://openalex.org/W6850787431"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,24,45,48,61,74,81,89,107,114,118,159,181,210,215],"problem":[4,22],"of":[5,27,47,106],"pre-training":[6,202],"for":[7,13,67,80],"small":[8,49,196],"models,":[9],"which":[10,102],"is":[11,65,172,223],"essential":[12],"many":[14],"mobile":[15],"devices.":[16],"Current":[17],"state-of-the-art":[18,220],"methods":[19],"on":[20,51,225],"this":[21,78,123],"transfer":[23],"representational":[25],"knowledge":[26,63,115,171],"a":[28,32,35,39,94,127,139,151,176,187],"large":[29],"network":[30],"(as":[31,38],"Teacher)":[33],"into":[34],"smaller":[36],"model":[37,50,213],"Student)":[40],"using":[41,214],"self-supervised":[42,204],"distillation,":[43,205],"improving":[44],"performance":[46,221],"downstream":[52,71,109,227],"tasks.":[53],"However,":[54],"existing":[55],"approaches":[56],"are":[57],"insufficient":[58],"in":[59,70],"extracting":[60],"crucial":[62],"that":[64,209],"useful":[66],"discerning":[68],"categories":[69],"tasks":[72],"during":[73],"distillation":[75,90],"process.":[76],"In":[77],"paper,":[79],"first":[82],"time,":[83],"we":[84,125,149],"introduce":[85],"language":[86,136],"guidance":[87],"to":[88,111,131,157,179],"process":[91],"and":[92,120,137,191,222,232],"propose":[93],"new":[95],"method":[96,218],"named":[97,164],"Language-Guided":[98,152],"Distillation":[99],"(LGD)":[100],"system,":[101],"uses":[103],"category":[104],"names":[105],"target":[108],"task":[110],"help":[112],"refine":[113],"transferred":[116,173],"between":[117],"teacher":[119,188],"student.":[121],"To":[122],"end,":[124],"utilize":[126],"pre-trained":[128],"text":[129],"encoder":[130,178],"extract":[132],"semantic":[133,141,161],"embeddings":[134],"from":[135],"construct":[138,158],"textual":[140],"space":[142],"called":[143],"Textual":[144],"Semantics":[145,166],"Bank":[146,167],"(TSB).":[147],"Furthermore,":[148],"design":[150],"Knowledge":[153],"Aggregation":[154],"(LGKA)":[155],"module":[156],"visual":[160],"space,":[162],"also":[163],"Visual":[165],"(VSB).":[168],"The":[169],"task-related":[170],"by":[174,186,199],"driving":[175],"student":[177],"mimic":[180],"similarity":[182],"score":[183],"distribution":[184],"inferred":[185],"over":[189],"TSB":[190],"VSB.":[192],"Compared":[193],"with":[194],"other":[195],"models":[197],"obtained":[198],"either":[200],"ImageNet":[201],"or":[203],"experiment":[206],"results":[207],"show":[208],"distilled":[211],"lightweight":[212],"proposed":[216],"LGD":[217],"presents":[219],"validated":[224],"various":[226],"tasks,":[228],"including":[229],"classification,":[230],"detection,":[231],"segmentation.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}