{"id":"https://openalex.org/W4415536262","doi":"https://doi.org/10.1145/3746027.3755098","title":"<i>RealSyn</i> : An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","display_name":"<i>RealSyn</i> : An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536262","doi":"https://doi.org/10.1145/3746027.3755098"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755098","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755098","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 33rd 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/10.1145/3746027.3755098","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101333470","display_name":"Tiancheng Gu","orcid":"https://orcid.org/0009-0001-2302-246X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Tiancheng Gu","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0001-2302-246X","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114226088","display_name":"Kaicheng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaicheng Yang","raw_affiliation_strings":["DeepGlint, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6073-9014","affiliations":[{"raw_affiliation_string":"DeepGlint, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080719369","display_name":"Chaoyi Zhang","orcid":"https://orcid.org/0000-0001-8492-9711"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chaoyi Zhang","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8492-9711","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102498940","display_name":"Yin Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Xie","raw_affiliation_strings":["DeepGlint, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0966-5569","affiliations":[{"raw_affiliation_string":"DeepGlint, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075570318","display_name":"Xiang An","orcid":"https://orcid.org/0009-0008-4652-8296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang An","raw_affiliation_strings":["DeepGlint, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4652-8296","affiliations":[{"raw_affiliation_string":"DeepGlint, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100531299","display_name":"Ziyong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyong Feng","raw_affiliation_strings":["DeepGlint, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8689-8366","affiliations":[{"raw_affiliation_string":"DeepGlint, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027686620","display_name":"Dongnan Liu","orcid":"https://orcid.org/0000-0001-8102-3949"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dongnan Liu","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8102-3949","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076697411","display_name":"Weidong Cai","orcid":"https://orcid.org/0000-0003-3706-8896"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weidong Cai","raw_affiliation_strings":["The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3706-8896","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073110676","display_name":"Jiankang Deng","orcid":"https://orcid.org/0000-0002-3709-6216"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiankang Deng","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3709-6216","affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101333470"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28546144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3487","last_page":"3496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/pipeline","display_name":"Pipeline (software)","score":0.6144000291824341},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6140000224113464},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4514999985694885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.385699987411499},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3691999912261963},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.36309999227523804},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.3573000133037567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496999740600586},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6144000291824341},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6140000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633999705314636},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43059998750686646},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755098","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755098","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755098","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755098","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2250384498","https://openalex.org/W2560730294","https://openalex.org/W2998702515","https://openalex.org/W4239072543","https://openalex.org/W4310494058","https://openalex.org/W4386065556","https://openalex.org/W4386075908","https://openalex.org/W4399197779","https://openalex.org/W4402667093","https://openalex.org/W4402727780","https://openalex.org/W4402727932","https://openalex.org/W4402952414","https://openalex.org/W4404575065","https://openalex.org/W4409363896","https://openalex.org/W4413429290"],"related_works":[],"abstract_inverted_index":{"After":[0],"pre-training":[1],"on":[2,13,109,147],"extensive":[3,168],"image-text":[4],"pairs,":[5],"Contrastive":[6],"Language-Image":[7],"Pre-training":[8],"(CLIP)":[9],"demonstrates":[10,180],"promising":[11],"performance":[12,152],"a":[14,20,43,57,93,115],"wide":[15],"variety":[16],"of":[17,23,105,139],"benchmarks.":[18],"However,":[19],"substantial":[21],"volume":[22],"multimodal":[24],"interleaved":[25],"documents":[26],"remains":[27],"underutilized":[28],"for":[29,86,142],"contrastive":[30,175],"vision-language":[31,176],"representation":[32,177],"learning.":[33],"To":[34,72],"fully":[35],"leverage":[36],"these":[37,110],"unpaired":[38],"documents,":[39],"we":[40,55,78,91,112],"initially":[41],"establish":[42],"Real-World":[44],"Data":[45],"Extraction":[46],"pipeline":[47],"to":[48,61,98],"extract":[49],"high-quality":[50],"images":[51],"and":[52,119,128,164,179],"texts.":[53,71],"Then":[54],"design":[56],"hierarchical":[58],"retrieval":[59],"method":[60],"efficiently":[62],"associate":[63],"each":[64],"image":[65,81],"with":[66,134],"multiple":[67],"semantically":[68],"relevant":[69],"realistic":[70,118],"further":[73],"enhance":[74],"fine-grained":[75],"visual":[76],"information,":[77],"propose":[79],"an":[80],"semantic":[82,94],"augmented":[83],"generation":[84],"module":[85],"synthetic":[87,120],"text":[88],"production.":[89],"Furthermore,":[90,167],"employ":[92],"balance":[95],"sampling":[96],"strategy":[97],"improve":[99],"dataset":[100,116,133],"diversity,":[101],"enabling":[102],"better":[103],"learning":[104,178],"long-tail":[106],"concepts.":[107],"Based":[108],"innovations,":[111],"construct":[113],"RealSyn,":[114],"combining":[117],"texts,":[121],"available":[122],"in":[123,188],"three":[124],"scales:":[125],"15M,":[126],"30M,":[127],"100M.":[129],"We":[130],"compare":[131],"our":[132],"other":[135],"widely":[136],"used":[137],"datasets":[138],"equivalent":[140],"scale":[141],"CLIP":[143],"training.":[144],"Models":[145],"pre-trained":[146],"RealSyn":[148,172],"consistently":[149],"achieve":[150],"state-of-the-art":[151],"across":[153],"various":[154],"downstream":[155],"tasks,":[156],"including":[157],"linear":[158],"probe,":[159],"zero-shot":[160,162,165],"transfer,":[161],"robustness,":[163],"retrieval.":[166],"experiments":[169],"confirm":[170],"that":[171],"significantly":[173],"enhances":[174],"robust":[181],"scalability.":[182],"The":[183],"code":[184],"will":[185],"be":[186],"released":[187],"https://garygutc.github.io/RealSyn.":[189]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}