{"id":"https://openalex.org/W4387969487","doi":"https://doi.org/10.1145/3581783.3611877","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","display_name":"CCMB: A Large-scale Chinese Cross-modal Benchmark","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969487","doi":"https://doi.org/10.1145/3581783.3611877"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611877","doi":"https://doi.org/10.1145/3581783.3611877","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611877","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611877","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611877","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045886141","display_name":"Chunyu Xie","orcid":"https://orcid.org/0009-0002-6607-8209","observed_orcids":["https://orcid.org/0009-0002-6607-8209"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyu Xie","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6607-8209","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101803413","display_name":"Heng Cai","orcid":"https://orcid.org/0009-0008-2868-6653","observed_orcids":["https://orcid.org/0009-0008-2868-6653"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Cai","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2868-6653","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102708348","display_name":"Jincheng Li","orcid":"https://orcid.org/0009-0009-3423-786X","observed_orcids":["https://orcid.org/0009-0009-3423-786X","https://orcid.org/0009-0005-7848-2809"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jincheng Li","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-7848-2809","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fanjing Kong","orcid":"https://orcid.org/0009-0007-2262-1990","observed_orcids":["https://orcid.org/0009-0007-2262-1990"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanjing Kong","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2262-1990","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066090542","display_name":"Xiaoyu Wu","orcid":"https://orcid.org/0009-0009-9770-180X","observed_orcids":["https://orcid.org/0009-0009-9770-180X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Wu","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-9770-180X","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060690937","display_name":"Jianfei Song","orcid":"https://orcid.org/0009-0007-2471-2060","observed_orcids":["https://orcid.org/0009-0007-2471-2060"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfei Song","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2471-2060","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028113726","display_name":"Henrique Morimitsu","orcid":"https://orcid.org/0000-0001-9455-8571","observed_orcids":["https://orcid.org/0000-0001-9455-8571"]},"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":"Henrique Morimitsu","raw_affiliation_strings":["360 AI Research & Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9455-8571","affiliations":[{"raw_affiliation_string":"360 AI Research & Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007629","display_name":"Lin Yao","orcid":"https://orcid.org/0000-0002-3437-5607","observed_orcids":["https://orcid.org/0000-0002-3437-5607"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Yao","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3437-5607","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082034927","display_name":"Dexin Wang","orcid":"https://orcid.org/0009-0007-6208-6873","observed_orcids":["https://orcid.org/0009-0007-6208-6873"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dexin Wang","raw_affiliation_strings":["360 Search Department, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6208-6873","affiliations":[{"raw_affiliation_string":"360 Search Department, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090364356","display_name":"Xiangzheng Zhang","orcid":"https://orcid.org/0009-0008-7700-5746","observed_orcids":["https://orcid.org/0009-0008-7700-5746"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangzheng Zhang","raw_affiliation_strings":["360 Search Department, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7700-5746","affiliations":[{"raw_affiliation_string":"360 Search Department, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048962204","display_name":"Dawei Leng","orcid":"https://orcid.org/0009-0000-5461-1681","observed_orcids":["https://orcid.org/0009-0000-5461-1681"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Leng","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5461-1681","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503795","display_name":"Baochang Zhang","orcid":"https://orcid.org/0000-0001-6167-4760","observed_orcids":["https://orcid.org/0000-0001-6167-4760"]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baochang Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6167-4760","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024401174","display_name":"Xiangyang Ji","orcid":"https://orcid.org/0000-0002-7333-9975","observed_orcids":["https://orcid.org/0000-0002-7333-9975"]},"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":"Xiangyang Ji","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7333-9975","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040753258","display_name":"Yafeng Deng","orcid":"https://orcid.org/0000-0003-2416-6913","observed_orcids":["https://orcid.org/0000-0003-2416-6913"]},"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":"Yafeng Deng","raw_affiliation_strings":["360 AI Research & Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2416-6913","affiliations":[{"raw_affiliation_string":"360 AI Research & Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0715,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86205415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4219","last_page":"4227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/vision-language-pre-training","display_name":"vision-language pre-training","score":0.9909999966621399},{"id":"https://openalex.org/keywords/image-text-retrieval","display_name":"image-text retrieval","score":0.7419999837875366},{"id":"https://openalex.org/keywords/image-text-matching","display_name":"image-text matching","score":0.9570000171661377},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.9810000061988831},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/zero-shot-image-classification","display_name":"zero-shot image classification","score":0.9980000257492065},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766038179397583},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6484152674674988},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6183785200119019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5680851936340332},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5191540122032166},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4985954761505127},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.49825549125671387},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4612758159637451},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4105610251426697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3865097165107727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35123521089553833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34134364128112793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08419865369796753},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08247873187065125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06900015473365784},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06739848852157593},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3581783.3611877","doi":"https://doi.org/10.1145/3581783.3611877","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611877","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611877","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.03860","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.03860","pdf_url":"https://arxiv.org/pdf/2205.03860","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.2205.03860","doi":"https://doi.org/10.48550/arxiv.2205.03860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.03860","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":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611877","doi":"https://doi.org/10.1145/3581783.3611877","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611877","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611877","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1349274172","display_name":null,"funder_award_id":"2018AAA0100400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969487.pdf","grobid_xml":"https://content.openalex.org/works/W4387969487.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2596164567","https://openalex.org/W2749708282","https://openalex.org/W2886641317","https://openalex.org/W2963527096","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3034727271","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3130033937","https://openalex.org/W3135099046","https://openalex.org/W3177224328","https://openalex.org/W4250798300","https://openalex.org/W4281643269","https://openalex.org/W4290877962","https://openalex.org/W4312910992"],"related_works":["https://openalex.org/W7133196266","https://openalex.org/W7124420359","https://openalex.org/W4409366962","https://openalex.org/W4221167911","https://openalex.org/W4407461569","https://openalex.org/W4308241978","https://openalex.org/W4379958249","https://openalex.org/W3133825286","https://openalex.org/W4304098627","https://openalex.org/W3134582802"],"abstract_inverted_index":{"Vision-language":[0],"pre-training":[1,25,59],"(VLP)":[2],"on":[3,10,151],"large-scale":[4,24,42],"datasets":[5,26,29,66,87,154],"has":[6],"shown":[7],"premier":[8],"performance":[9,150],"various":[11],"downstream":[12,28,68,97,153],"tasks.":[13,69,98],"In":[14,36],"contrast":[15],"to":[16,117,133],"plenty":[17],"of":[18,83,159],"available":[19,180],"benchmarks":[20],"with":[21,30,76,100],"English":[22],"corpus,":[23],"and":[27,62,122,130,142,170,177],"Chinese":[31,44,95],"corpus":[32],"remain":[33],"largely":[34],"unexplored.":[35],"this":[37],"work,":[38],"we":[39,103,147],"build":[40],"a":[41,106,112,123],"high-quality":[43],"Cross-Modal":[45],"Benchmark":[46],"named":[47,109],"CCMB":[48],"for":[49,67,94],"the":[50,55,84,91,101,136,140,143],"research":[51],"community,":[52],"which":[53],"contains":[54,71],"currently":[56,90],"largest":[57,92],"public":[58],"dataset":[60],"Zero":[61,70,141],"five":[63,85,156],"human-annotated":[64],"fine-tuning":[65,86],"250":[72],"million":[73,78],"images":[74],"paired":[75],"750":[77],"text":[79],"descriptions,":[80],"plus":[81],"two":[82],"are":[88,179],"also":[89,104],"ones":[93],"cross-modal":[96],"Along":[99],"CCMB,":[102],"develop":[105],"VLP":[107,145],"framework":[108],"R2D2,":[110],"applying":[111],"pre-Ranking":[113],"+":[114],"Ranking":[115],"strategy":[116],"learn":[118],"powerful":[119],"vision-language":[120],"representations":[121],"two-way":[124],"distillation":[125],"method":[126],"(i.e.,":[127],"target-guided":[128],"Distillation":[129],"feature-guided":[131],"Distillation)":[132],"further":[134],"enhance":[135],"learning":[137],"capability.":[138],"With":[139],"R2D2":[144],"framework,":[146],"achieve":[148],"state-of-the-art":[149],"twelve":[152],"from":[155],"broad":[157],"categories":[158],"tasks":[160],"including":[161],"image-text":[162,164],"retrieval,":[163],"matching,":[165],"image":[166,172],"caption,":[167],"text-to-image":[168],"generation,":[169],"zero-shot":[171],"classification.":[173],"The":[174],"datasets,":[175],"models,":[176],"codes":[178],"at":[181],"https://github.com/yuxie11/R2D2":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-10-28T00:00:00"}