{"id":"https://openalex.org/W4410636968","doi":"https://doi.org/10.1145/3701716.3717661","title":"GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task","display_name":"GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636968","doi":"https://doi.org/10.1145/3701716.3717661"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717661","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717661","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108769217","display_name":"Ning Ding","orcid":"https://orcid.org/0000-0001-8064-7311"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Ding","raw_affiliation_strings":["Peking University, Peking, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Peking, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038232518","display_name":"Yehui Tang","orcid":"https://orcid.org/0000-0002-0322-4283"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehui Tang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063417011","display_name":"Zhongqian Lv","orcid":"https://orcid.org/0009-0009-9587-8265"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqian Fu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100561659","display_name":"Chao Xu","orcid":"https://orcid.org/0000-0002-1743-7087"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Xu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784732","display_name":"Kai Han","orcid":"https://orcid.org/0000-0002-9761-2702"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Han","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100727356","display_name":"Yunhe Wang","orcid":"https://orcid.org/0000-0002-0142-509X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhe Wang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108769217"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05257384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2056","last_page":"2065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.7709550261497498},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7405248880386353},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6982365846633911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354939103126526},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40338897705078125},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39619773626327515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33134663105010986},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16695624589920044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07918775081634521},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06502518057823181}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709550261497498},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7405248880386353},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6982365846633911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354939103126526},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40338897705078125},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39619773626327515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33134663105010986},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16695624589920044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07918775081634521},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06502518057823181},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3717661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717661","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717661","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636968.pdf","grobid_xml":"https://content.openalex.org/works/W4410636968.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2995715529","https://openalex.org/W2997591391","https://openalex.org/W3035524453","https://openalex.org/W3138516171","https://openalex.org/W3173220247","https://openalex.org/W3177174258","https://openalex.org/W3184439416","https://openalex.org/W4225323055","https://openalex.org/W4225832925","https://openalex.org/W4287113019","https://openalex.org/W4297833882","https://openalex.org/W4312605942"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W2961085424","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W4387697615","https://openalex.org/W2598946408","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"The":[0],"upsurge":[1],"in":[2],"pre-trained":[3,40,118,133,174,218],"large":[4,75,117,132],"models":[5,18,79,105,134,210],"started":[6],"by":[7,111,156,203],"ChatGPT":[8],"has":[9],"swept":[10],"across":[11],"the":[12,33,44,64,77,99,115,128,131,182,215,225,228],"entire":[13],"deep":[14],"learning":[15,123],"community.Such":[16],"powerful":[17],"demonstrate":[19],"advanced":[20],"generative":[21],"ability":[22,101],"and":[23,59,68,83,140,145,196],"multimodal":[24,159],"understanding":[25],"capability,":[26],"which":[27],"quickly":[28],"set":[29,155],"new":[30,122],"state":[31],"of":[32,38,71,102,114,130,185,217,227],"arts":[34],"on":[35,106,231],"a":[36,47,74,121,151,158,173],"variety":[37],"benchmarks.The":[39],"LLM":[41,160],"usually":[42],"plays":[43],"role":[45],"as":[46,81,192],"universal":[48],"AI":[49],"model":[50,238],"that":[51,180],"can":[52],"conduct":[53,220],"various":[54,232],"tasks":[55,108,235],"like":[56],"article":[57],"analysis":[58],"image":[60,200],"comprehension.However,":[61],"due":[62],"to":[63,97,137,161,176,223],"prohibitively":[65],"high":[66,152],"memory":[67],"computational":[69],"cost":[70],"implementing":[72],"such":[73],"model,":[76],"conventional":[78],"(such":[80],"CNN":[82],"ViT)":[84],"are":[85,135,170],"still":[86],"essential":[87],"for":[88,164,236],"many":[89],"visual":[90,233],"perception":[91,107,234],"tasks.In":[92],"this":[93],"paper,":[94],"we":[95,149],"propose":[96],"enhance":[98],"representation":[100],"ordinary":[103],"vision":[104,204,209],"(e.g.image":[109],"classification)":[110],"taking":[112],"advantage":[113],"off-the-shelf":[116],"models.We":[119],"present":[120],"framework,":[124],"dubbed":[125],"GPT4Image,":[126],"where":[127],"knowledge":[129],"extracted":[136],"help":[138],"CNNs":[139],"ViTs":[141],"learn":[142],"better":[143,212],"representations":[144,201],"achieve":[146,211],"higher":[147],"performance.Firstly,":[148],"curate":[150],"quality":[153],"description":[154],"prompting":[157],"generate":[162],"descriptions":[163,169],"training":[165],"images.Then,":[166],"these":[167],"detailed":[168],"fed":[171],"into":[172],"encoder":[175],"extract":[177],"text":[178,188],"embeddings":[179,189],"encodes":[181],"rich":[183],"semantics":[184],"images.During":[186],"training,":[187],"will":[190],"serve":[191],"extra":[193],"supervising":[194],"signal":[195],"be":[197],"aligned":[198],"with":[199,214],"learned":[202],"models.The":[205],"alignment":[206],"process":[207],"helps":[208],"performance":[213],"aid":[216],"LLMs.We":[219],"extensive":[221],"experiments":[222],"verify":[224],"effectiveness":[226],"proposed":[229],"algorithm":[230],"heterogeneous":[237],"architectures.":[239]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}