{"id":"https://openalex.org/W3207798279","doi":"https://doi.org/10.1145/3474085.3475251","title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","display_name":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207798279","doi":"https://doi.org/10.1145/3474085.3475251","mag":"3207798279"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026404286","display_name":"Yuhao Cui","orcid":"https://orcid.org/0009-0007-3644-7321"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Cui","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104226532","display_name":"Chunqi Wang","orcid":"https://orcid.org/0000-0002-0293-9746"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunqi Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058996194","display_name":"Zhongzhou Zhao","orcid":"https://orcid.org/0000-0002-3519-6301"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhou Zhao","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787171","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0001-6141-239X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5328,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.95110188,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"797","last_page":"806"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9739000201225281,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827867865562439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796120762825012},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5235714316368103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.506817638874054},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4856247007846832},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4618827700614929},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4253963530063629},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.41062474250793457},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15987160801887512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827867865562439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796120762825012},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5235714316368103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.506817638874054},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4856247007846832},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4618827700614929},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4253963530063629},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.41062474250793457},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15987160801887512},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1996219872","https://openalex.org/W2109586012","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2560730294","https://openalex.org/W2599765304","https://openalex.org/W2626778328","https://openalex.org/W2744822616","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2933067512","https://openalex.org/W2950761309","https://openalex.org/W2950813464","https://openalex.org/W2953356739","https://openalex.org/W2954861308","https://openalex.org/W2962835968","https://openalex.org/W2962964995","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2964345792","https://openalex.org/W2966683369","https://openalex.org/W2969862959","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2995460200","https://openalex.org/W2998356391","https://openalex.org/W2998385486","https://openalex.org/W3004349648","https://openalex.org/W3018626069","https://openalex.org/W3024464497","https://openalex.org/W3038476992","https://openalex.org/W3049478012","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092767330","https://openalex.org/W3099839483","https://openalex.org/W3102995547","https://openalex.org/W3106784008","https://openalex.org/W3108319047","https://openalex.org/W3151929433","https://openalex.org/W3174010726","https://openalex.org/W3177224328"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2378211422","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W2745001401","https://openalex.org/W1692008701","https://openalex.org/W2046546488"],"abstract_inverted_index":{"Vision-and-language":[0],"pretraining":[1],"(VLP)":[2],"aims":[3],"to":[4,89,104,113],"learn":[5],"generic":[6],"multimodal":[7],"representations":[8],"from":[9],"massive":[10],"image-text":[11,25,48],"pairs.":[12],"While":[13],"various":[14],"successful":[15],"attempts":[16],"have":[17,39],"been":[18],"proposed,":[19],"learning":[20],"fine-grained":[21],"semantic":[22,92,122,145],"alignments":[23,57,123],"between":[24],"pairs":[26],"plays":[27],"a":[28,71,85,97,111],"key":[29],"role":[30],"in":[31,84,144],"their":[32,64],"approaches.":[33],"Nevertheless,":[34],"most":[35],"existing":[36,157],"VLP":[37,73,159],"approaches":[38],"not":[40],"fully":[41],"utilized":[42],"the":[43,47,52,55,61,79,91,106,121,126,140],"intrinsic":[44],"knowledge":[45,83,100],"within":[46,129],"pairs,":[49],"which":[50,77,119],"limits":[51],"effectiveness":[53,141],"of":[54,63,142],"learned":[56],"and":[58,81,130,136,151],"further":[59],"restricts":[60],"performance":[62],"models.":[65],"To":[66],"this":[67],"end,":[68],"we":[69,95],"introduce":[70,96],"new":[72],"method":[74],"called":[75],"ROSITA,":[76],"integrates":[78],"cross-":[80],"intra-modal":[82],"unified":[86],"scene":[87,107],"graph":[88,108],"enhance":[90],"alignments.":[93,146],"Specifically,":[94],"novel":[98],"structural":[99],"masking":[101],"(SKM)":[102],"strategy":[103],"use":[105],"structure":[109],"as":[110],"priori":[112],"perform":[114],"masked":[115],"language":[116],"(region)":[117],"modeling,":[118],"enhances":[120],"by":[124],"eliminating":[125],"interference":[127],"information":[128],"across":[131],"modalities.":[132],"Extensive":[133],"ablation":[134],"studies":[135],"comprehensive":[137],"analysis":[138],"verifies":[139],"ROSITA":[143,154],"Pretrained":[147],"with":[148],"both":[149],"in-domain":[150],"out-of-domain":[152],"datasets,":[153],"significantly":[155],"outperforms":[156],"state-of-the-art":[158],"methods":[160],"on":[161],"three":[162],"typical":[163],"vision-and-language":[164],"tasks":[165],"over":[166],"six":[167],"benchmark":[168],"datasets.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":13}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}