{"id":"https://openalex.org/W4403791263","doi":"https://doi.org/10.1145/3664647.3681502","title":"Neighbor Does Matter: Curriculum Global Positive-Negative Sampling for Vision-Language Pre-training","display_name":"Neighbor Does Matter: Curriculum Global Positive-Negative Sampling for Vision-Language Pre-training","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791263","doi":"https://doi.org/10.1145/3664647.3681502"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681502","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681502","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681502","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101401100","display_name":"Bin Huang","orcid":"https://orcid.org/0009-0000-2504-3689"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Huang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100538836","display_name":"He Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng He","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100537256","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0003-2044-9238"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002254187","display_name":"Guohao Li","orcid":"https://orcid.org/0000-0001-7796-5378"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059003026","display_name":"Zhifan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifan Feng","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101401100"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54507314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8005","last_page":"8014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/training","display_name":"Training (meteorology)","score":0.6942251324653625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6358365416526794},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5682166814804077},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5063961744308472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4953669309616089},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33629530668258667},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.31365811824798584},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.274061381816864},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.16358956694602966},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08638179302215576}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6942251324653625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6358365416526794},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5682166814804077},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5063961744308472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4953669309616089},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33629530668258667},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31365811824798584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.274061381816864},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.16358956694602966},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08638179302215576},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681502","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681502","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681502","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681502","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"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":24,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1977556410","https://openalex.org/W2277195237","https://openalex.org/W2296073425","https://openalex.org/W2886641317","https://openalex.org/W2984008963","https://openalex.org/W2998702515","https://openalex.org/W3142849873","https://openalex.org/W3158714121","https://openalex.org/W3212687458","https://openalex.org/W4300011764","https://openalex.org/W4304080781","https://openalex.org/W4304092657","https://openalex.org/W4312784228","https://openalex.org/W4312877428","https://openalex.org/W4312887799","https://openalex.org/W4382462100","https://openalex.org/W4387967986","https://openalex.org/W4387968116","https://openalex.org/W4388221290","https://openalex.org/W4393157099","https://openalex.org/W4396843671","https://openalex.org/W4402754238"],"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/W3204019825"],"abstract_inverted_index":{"Sampling":[0,75],"strategies":[1,19,48],"have":[2,11],"been":[3],"widely":[4],"adopted":[5,20],"in":[6,27,51,66,88],"Vision-Language":[7],"Pre-training":[8],"(VLP)":[9],"and":[10,85,168,188],"achieved":[12],"great":[13],"success":[14],"recently.":[15],"However,":[16],"the":[17,38,52,89,94,110,115,156,173,176,189,196],"sampling":[18,47,87,106,128,140],"by":[21,180],"current":[22],"VLP":[23],"works":[24],"are":[25,49],"limited":[26],"two":[28],"ways:":[29],"i)":[30],"they":[31],"only":[32],"focus":[33],"on":[34,93,155,183],"negative":[35,86,139,144],"sampling,":[36],"ignoring":[37],"importance":[39],"of":[40,96,112,125,175],"more":[41,166],"informative":[42,167],"positive":[43,84,127],"samples;":[44],"ii)":[45],"their":[46],"conducted":[50],"local":[53],"in-batch":[54],"level,":[55,91],"which":[56,81,164],"may":[57],"lead":[58],"to":[59,129,141],"sub-optimal":[60],"results.":[61],"To":[62],"tackle":[63],"these":[64],"problems,":[65],"this":[67],"paper,":[68],"we":[69,100],"propose":[70],"a":[71,161],"curriculum-based":[72],"Global":[73],"Positive-Negative":[74],"(GPN-S)":[76],"framework":[77,122,179],"for":[78,152],"vision-language":[79,153],"pre-training,":[80],"conducts":[82],"both":[83],"global":[90],"grounded":[92],"notion":[95],"neighborhood":[97],"relationships.":[98],"Additionally,":[99],"incorporate":[101],"curriculum":[102],"learning":[103],"into":[104],"our":[105,119],"strategy,":[107],"progressively":[108],"increasing":[109],"complexity":[111],"samples":[113,133,145],"as":[114,135,137],"training":[116],"progresses.":[117],"Specifically,":[118],"proposed":[120,177],"GPN-S":[121,178],"is":[123],"capable":[124],"utilizing":[126],"bring":[130],"semantically":[131],"equivalent":[132],"closer,":[134],"well":[136],"employing":[138],"push":[142],"challenging":[143],"farther":[146],"away.":[147],"We":[148,171],"jointly":[149],"consider":[150],"them":[151],"pre-training":[154],"global-level":[157],"perspective":[158],"rather":[159],"than":[160],"local-level":[162],"mini-batch,":[163],"provides":[165],"diverse":[169],"samples.":[170],"evaluate":[172],"effectiveness":[174],"conducting":[181],"experiments":[182],"several":[184],"common":[185],"downstream":[186],"tasks,":[187],"results":[190],"demonstrate":[191],"significant":[192],"performance":[193],"improvement":[194],"over":[195],"existing":[197],"models.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}