{"id":"https://openalex.org/W4387185454","doi":"https://doi.org/10.3233/faia230560","title":"Using Self-Supervised Dual Constraint Contrastive Learning for Cross-Modal Retrieval","display_name":"Using Self-Supervised Dual Constraint Contrastive Learning for Cross-Modal Retrieval","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185454","doi":"https://doi.org/10.3233/faia230560"},"language":"en","primary_location":{"id":"doi:10.3233/faia230560","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230560","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230560","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230560","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100783581","display_name":"Xintong Wang","orcid":"https://orcid.org/0000-0002-2038-8028"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xintong Wang","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101610687","display_name":"Xiaoyu Li","orcid":"https://orcid.org/0000-0002-0947-3491"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Xiaoyu Li","raw_affiliation_strings":["Department of Computer Science, Technical University Berlin","School of Computer Sciences and Technology, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technical University Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"School of Computer Sciences and Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751872","display_name":"Ding Liang","orcid":"https://orcid.org/0000-0001-9774-4687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Ding","raw_affiliation_strings":["JD Explore Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106686348","display_name":"Sanyuan Zhao","orcid":"https://orcid.org/0000-0001-9386-9677"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanyuan Zhao","raw_affiliation_strings":["School of Computer Sciences and Technology, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Sciences and Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Language Technology Group, Department of Informatics, University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Department of Informatics, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5092,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88654925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9932000041007996,"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":0.992900013923645,"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/overfitting","display_name":"Overfitting","score":0.845645546913147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556112408638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6505062580108643},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5173094272613525},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5151230692863464},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4818074107170105},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.448669970035553},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41257569193840027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3886373043060303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32283198833465576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10925573110580444},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10174316167831421},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08915704488754272}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.845645546913147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556112408638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6505062580108643},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5173094272613525},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5151230692863464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4818074107170105},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.448669970035553},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41257569193840027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3886373043060303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32283198833465576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10925573110580444},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10174316167831421},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08915704488754272},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230560","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230560","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230560","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230560","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230560","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230560","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185454.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2109586012","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2481240925","https://openalex.org/W2774267535","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2913946806","https://openalex.org/W2964303773","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W3014611590","https://openalex.org/W3016923549","https://openalex.org/W3020257313","https://openalex.org/W3030163527","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3126792443","https://openalex.org/W3135367836","https://openalex.org/W3166396011","https://openalex.org/W3184735396","https://openalex.org/W3198377975","https://openalex.org/W3208314443","https://openalex.org/W4200629441","https://openalex.org/W4224951189","https://openalex.org/W4225323055","https://openalex.org/W4226182655","https://openalex.org/W4229042118","https://openalex.org/W4292779060","https://openalex.org/W4292945941","https://openalex.org/W4312884055","https://openalex.org/W4319453767","https://openalex.org/W4320722432","https://openalex.org/W4322718191","https://openalex.org/W4360891262","https://openalex.org/W4366241040"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"a":[5,132,139],"self-supervised":[6,85,125],"dual":[7,86],"constraint":[8],"contrastive":[9,87],"method":[10,144],"for":[11,161],"efficiently":[12],"fine-tuning":[13,93],"the":[14,46,56,61,103,119,148,162],"vision-language":[15],"pre-trained":[16,32,57],"(VLP)":[17],"models":[18,33,59,150],"that":[19,83,123],"have":[20],"achieved":[21],"great":[22],"success":[23],"on":[24,95,102,118,131],"various":[25],"cross-modal":[26,104],"tasks,":[27],"since":[28],"full":[29],"fine-tune":[30],"these":[31],"is":[34,145],"computationally":[35],"expensive":[36],"and":[37,48,64,68,75,98,151],"tend":[38],"to":[39,72,147],"result":[40],"in":[41,113,168],"catastrophic":[42],"forgetting":[43],"restricted":[44],"by":[45],"size":[47],"quality":[49],"of":[50,165],"labeled":[51,79],"datasets.":[52],"Our":[53],"approach":[54,126],"freezes":[55],"VLP":[58,158,169],"as":[60],"fundamental,":[62],"generalized,":[63],"transferable":[65],"multimodal":[66],"representation":[67],"incorporates":[69],"lightweight":[70],"parameters":[71],"learn":[73],"domain":[74],"task-specific":[76],"features":[77],"without":[78,136],"data.":[80],"We":[81],"demonstrated":[82],"our":[84,124,142],"model":[88],"performs":[89],"better":[90],"than":[91],"previous":[92],"methods":[94],"MS":[96],"COCO":[97],"Flickr":[99],"30K":[100],"datasets":[101],"retrieval":[105],"task,":[106],"with":[107,156],"an":[108],"even":[109],"more":[110],"pronounced":[111],"improvement":[112],"zero-shot":[114],"performance.":[115],"Furthermore,":[116],"experiments":[117],"MOTIF":[120],"dataset":[121,135],"prove":[122],"remains":[127],"effective":[128],"when":[129],"trained":[130],"small,":[133],"out-of-domain":[134],"overfitting.":[137],"As":[138],"plug-and-play":[140],"method,":[141],"proposed":[143],"agnostic":[146],"underlying":[149],"can":[152],"be":[153],"easily":[154],"integrated":[155],"different":[157],"models,":[159],"allowing":[160],"potential":[163],"incorporation":[164],"future":[166],"advancements":[167],"models.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}