{"id":"https://openalex.org/W4404628297","doi":"https://doi.org/10.1109/ipta62886.2024.10755555","title":"Data Processing Techniques for Modern Multimodal Models","display_name":"Data Processing Techniques for Modern Multimodal Models","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4404628297","doi":"https://doi.org/10.1109/ipta62886.2024.10755555"},"language":"en","primary_location":{"id":"doi:10.1109/ipta62886.2024.10755555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta62886.2024.10755555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Thirteenth International Conference on Image Processing Theory, Tools and Applications (IPTA)","raw_type":"proceedings-article"},"type":"article","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/A5082841573","display_name":"Yinheng Li","orcid":"https://orcid.org/0000-0002-7740-2484"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yinheng Li","raw_affiliation_strings":["Columbia University,New York,NY,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,New York,NY,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617197","display_name":"Han Ding","orcid":"https://orcid.org/0000-0003-3170-0723"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Ding","raw_affiliation_strings":["Columbia University,New York,NY,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,New York,NY,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064360714","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0001-8979-182X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["Columbia University,New York,NY,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,New York,NY,USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082841573"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":1.0848,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82307565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.12470000237226486,"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"}},"topics":[{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.12470000237226486,"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":0.6746240854263306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32681339979171753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746240854263306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32681339979171753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipta62886.2024.10755555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta62886.2024.10755555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Thirteenth International Conference on Image Processing Theory, Tools and Applications (IPTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0],"processing":[1,22,88],"plays":[2],"an":[3,16],"significant":[4],"role":[5],"in":[6,25,63,70],"current":[7],"multimodal":[8,27,37,82],"model":[9,28],"training.":[10],"In":[11],"this":[12],"paper.":[13],"we":[14],"provide":[15,79],"comprehensive":[17],"review":[18],"of":[19,66,73],"common":[20],"data":[21,49,51,53,56,67,87],"techniques":[23,45],"used":[24],"modern":[26],"training":[29],"with":[30,85],"a":[31],"focus":[32],"on":[33],"diffusion":[34],"models":[35,40,83],"and":[36,55],"large":[38],"language":[39],"(MLLMs).":[41],"We":[42,58],"summarized":[43],"all":[44],"into":[46],"four":[47],"categories:":[48],"quality,":[50],"quantity,":[52],"distribution":[54],"safety.":[57],"further":[59],"present":[60],"our":[61],"findings":[62],"the":[64],"choice":[65],"process":[68],"methods":[69],"different":[71],"type":[72],"models.":[74],"This":[75],"study":[76],"aims":[77],"to":[78,81],"guidance":[80],"developers":[84],"effective":[86],"techniques.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}