{"id":"https://openalex.org/W4415310274","doi":"https://doi.org/10.1109/iccv51701.2025.00281","title":"Differential-Informed Sample Selection Accelerates Multimodal Contrastive Learning","display_name":"Differential-Informed Sample Selection Accelerates Multimodal Contrastive Learning","alternate_titles":[],"publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415310274","doi":"https://doi.org/10.1109/iccv51701.2025.00281"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00281","doi":"https://doi.org/10.1109/iccv51701.2025.00281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00281","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4415310274"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102705176","display_name":"Zihua Zhao","orcid":"https://orcid.org/0000-0001-8611-8656","observed_orcids":["https://orcid.org/0000-0001-8611-8656","https://orcid.org/0009-0003-2915-6893"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihua Zhao","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Hong","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618683","display_name":"Mengxi Chen","orcid":"https://orcid.org/0000-0002-1237-9367","observed_orcids":["https://orcid.org/0000-0002-1237-9367"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxi Chen","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengyi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyi Chen","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083757533","display_name":"Benyuan Liu","orcid":"https://orcid.org/0000-0001-5879-4702","observed_orcids":["https://orcid.org/0000-0001-5879-4702","https://orcid.org/0009-0003-2438-8046"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benyuan Liu","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922412","display_name":"Jiangchao Yao","orcid":"https://orcid.org/0000-0001-6115-5194","observed_orcids":["https://orcid.org/0000-0001-6115-5194"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangchao Yao","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627090","display_name":"Zhang Ya","orcid":"https://orcid.org/0000-0002-6345-4494","observed_orcids":["https://orcid.org/0000-0002-6345-4494"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["School of AI, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of AI, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645705","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-3196-2347","observed_orcids":["https://orcid.org/0000-0002-3196-2347"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["School of AI, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of AI, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.0038,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83127439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2930","last_page":"2940"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.961899995803833,"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":0.961899995803833,"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":0.021400000900030136,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.003100000089034438,"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/sample-selection","display_name":"sample selection","score":0.9490000009536743},{"id":"https://openalex.org/keywords/multimodal-contrastive-learning","display_name":"multimodal contrastive learning","score":0.9810000061988831},{"id":"https://openalex.org/keywords/noisy-correspondence","display_name":"noisy correspondence","score":0.8899999856948853},{"id":"https://openalex.org/keywords/training-acceleration","display_name":"training acceleration","score":0.7990000247955322},{"id":"https://openalex.org/keywords/coreset-selection","display_name":"coreset selection","score":0.734000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767300009727478},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.685699999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6747000217437744},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6714000105857849},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6262000203132629},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00281","doi":"https://doi.org/10.1109/iccv51701.2025.00281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00281","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.12998","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12998","pdf_url":"https://arxiv.org/pdf/2507.12998","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2507.12998","doi":"https://doi.org/10.48550/arxiv.2507.12998","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12998","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.12998","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12998","pdf_url":"https://arxiv.org/pdf/2507.12998","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G182816160","display_name":null,"funder_award_id":"62306178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415310274.pdf","grobid_xml":"https://content.openalex.org/works/W4415310274.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2034978228","https://openalex.org/W2177410802","https://openalex.org/W2185175083","https://openalex.org/W2250384498","https://openalex.org/W2606722458","https://openalex.org/W2774918944","https://openalex.org/W2808965408","https://openalex.org/W2886641317","https://openalex.org/W2899335602","https://openalex.org/W2903996579","https://openalex.org/W2908510526","https://openalex.org/W2951970475","https://openalex.org/W2963735582","https://openalex.org/W2970971581","https://openalex.org/W2988823324","https://openalex.org/W2995592331","https://openalex.org/W2996108195","https://openalex.org/W3001279689","https://openalex.org/W3035524453","https://openalex.org/W3102583815","https://openalex.org/W3126337491","https://openalex.org/W3126792443","https://openalex.org/W3130033937","https://openalex.org/W3135367836","https://openalex.org/W3153469116","https://openalex.org/W3177900337","https://openalex.org/W3209532394","https://openalex.org/W3212024868","https://openalex.org/W3212616005","https://openalex.org/W3215230805","https://openalex.org/W4226182655","https://openalex.org/W4283073619","https://openalex.org/W4297808394","https://openalex.org/W4307783342","https://openalex.org/W4318718936","https://openalex.org/W4321488163","https://openalex.org/W4323921995","https://openalex.org/W4327811112","https://openalex.org/W4386065512","https://openalex.org/W4386076401","https://openalex.org/W4386076631","https://openalex.org/W4390873274","https://openalex.org/W4393145123","https://openalex.org/W4399510856","https://openalex.org/W4401023980","https://openalex.org/W4402727366","https://openalex.org/W4402778073","https://openalex.org/W4402915941","https://openalex.org/W4404450416","https://openalex.org/W4405717828","https://openalex.org/W4406032133","https://openalex.org/W4407873490","https://openalex.org/W4409955661","https://openalex.org/W4413145922","https://openalex.org/W4414385814","https://openalex.org/W4415798716","https://openalex.org/W4416422376","https://openalex.org/W7133243546"],"related_works":["https://openalex.org/W4399117945","https://openalex.org/W4390872979","https://openalex.org/W4415800357","https://openalex.org/W4402696041","https://openalex.org/W7160295104","https://openalex.org/W3134623377","https://openalex.org/W4407200775","https://openalex.org/W7033550353","https://openalex.org/W3130418914","https://openalex.org/W7161001297"],"abstract_inverted_index":{"The":[0],"remarkable":[1],"success":[2],"of":[3,111,126,132,172],"contrastive-learning-based":[4],"multimodal":[5],"models":[6],"has":[7,73],"been":[8],"greatly":[9],"driven":[10],"by":[11],"training":[12,34,104],"on":[13,39,45,64,68,114,144,160],"ever-larger":[14],"datasets":[15,163],"with":[16],"expensive":[17],"compute":[18],"consumption.":[19],"Sample":[20,91],"selection":[21,41,66,152],"as":[22],"an":[23,28,46],"alternative":[24],"efficient":[25],"paradigm":[26],"plays":[27],"important":[29],"direction":[30],"to":[31,49,139],"accelerate":[32],"the":[33,59,79,100,109,120,123,127,169],"process.":[35],"However,":[36],"recent":[37],"advances":[38],"sample":[40,141,151],"either":[42],"mostly":[43],"rely":[44],"oracle":[47],"model":[48,70,129,135],"offline":[50],"select":[51],"a":[52,88,133,148],"high-quality":[53],"coreset,":[54],"which":[55,72,95],"is":[56,136,180],"limited":[57],"in":[58],"cold-start":[60],"scenarios,":[61],"or":[62,76],"focus":[63],"online":[65],"based":[67],"real-time":[69],"predictions,":[71],"not":[74],"sufficiently":[75],"efficiently":[77,98],"considered":[78],"noisy":[80,101,112],"correspondence.":[81],"To":[82],"address":[83],"this":[84],"dilemma,":[85],"we":[86,107,146],"propose":[87,118],"novel":[89],"Differential-Informed":[90],"Selection":[92],"(DISSect)":[93],"method,":[94],"accurately":[96],"and":[97,117,130,153,164],"discriminates":[99],"correspondence":[102,113],"for":[103],"acceleration.":[105],"Specifically,":[106],"rethink":[108],"impact":[110],"contrastive":[115],"learning":[116],"that":[119,131],"differential":[121],"between":[122],"predicted":[124],"correlation":[125],"current":[128,175],"historical":[134],"more":[137],"informative":[138],"characterize":[140],"quality.":[142],"Based":[143],"this,":[145],"construct":[147],"robust":[149],"differential-based":[150],"analyze":[154],"its":[155],"theoretical":[156],"insights.":[157],"Extensive":[158],"experiments":[159],"three":[161],"benchmark":[162],"various":[165],"downstream":[166],"tasks":[167],"demonstrate":[168],"consistent":[170],"superiority":[171],"DISSect":[173],"over":[174],"state-of-the-art":[176],"methods.":[177],"Source":[178],"code":[179],"available":[181],"at:":[182],"https://github.com/MediaBrain-SJTU/DISSect.":[183]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4415310274","counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-10-18T00:00:00"}
