{"id":"https://openalex.org/W4400528710","doi":"https://doi.org/10.1145/3626772.3657987","title":"Multimodal Representation and Retrieval [MRR 2024]","display_name":"Multimodal Representation and Retrieval [MRR 2024]","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400528710","doi":"https://doi.org/10.1145/3626772.3657987"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657987","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657987","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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657987","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102586120","display_name":"Xinliang Zhu","orcid":"https://orcid.org/0000-0002-4544-2078"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinliang Zhu","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4544-2078","affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055026781","display_name":"Arnab Dhua","orcid":"https://orcid.org/0009-0007-8233-4301"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnab Dhua","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-8233-4301","affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103324588","display_name":"Douglas Gray","orcid":"https://orcid.org/0009-0007-3509-582X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Gray","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-3509-582X","affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078197885","display_name":"\u0130smet Zeki Yaln\u0131z","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Zeki Yalniz","raw_affiliation_strings":["Meta, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6582-3863","affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101289356","display_name":"Tan Yu","orcid":"https://orcid.org/0009-0002-5729-0945"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tan Yu","raw_affiliation_strings":["Nvidia, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0002-5729-0945","affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohamed Elhoseiny","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9659-1551","affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061227594","display_name":"Bryan A. Plummer","orcid":"https://orcid.org/0000-0002-7074-3219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Plummer","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7074-3219","affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7112,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68173092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3047","last_page":"3050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9110999703407288,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9110999703407288,"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":0.6503955125808716},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5425385236740112},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4661029577255249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4108927249908447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33407795429229736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503955125808716},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5425385236740112},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4661029577255249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108927249908447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33407795429229736},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657987","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657987","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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657987","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657987","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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"data":[1,25],"is":[2],"available":[3],"in":[4],"many":[5],"applications":[6],"like":[7],"e-commerce":[8],"production":[9],"listings,":[10],"social":[11],"media":[12],"posts":[13],"and":[14,35,52,71,84,102,111],"short":[15],"videos.":[16],"However,":[17],"existing":[18],"algorithms":[19],"dealing":[20],"with":[21],"those":[22],"types":[23],"of":[24,59,78,99],"still":[26],"focus":[27],"on":[28,96],"uni-modal":[29],"representation":[30,83,101],"learning":[31],"by":[32],"vision-language":[33],"alignment":[34],"cross-modal":[36],"retrieval.":[37,103],"In":[38],"this":[39],"workshop,":[40],"we":[41,74],"target":[42],"to":[43],"bring":[44],"a":[45,76,91],"new":[46,79],"retrieval":[47,67,85],"problem":[48],"where":[49],"both":[50],"queries":[51],"documents":[53],"are":[54],"multimodal.":[55],"With":[56],"the":[57,97],"popularity":[58],"vision":[60],"language":[61,64],"modeling,":[62],"large":[63],"models":[65],"(LLMs),":[66],"augmented":[68],"generation":[69],"(RAG),":[70],"multimodal":[72,82,100],"LLM,":[73],"see":[75],"lot":[77],"opportunities":[80],"for":[81],"tasks.":[86],"This":[87],"event":[88],"will":[89],"be":[90],"comprehensive":[92],"half-day":[93],"workshop":[94],"focusing":[95],"subject":[98],"The":[104],"agenda":[105],"includes":[106],"keynote":[107],"speeches,":[108],"oral":[109],"presentations,":[110],"an":[112],"interactive":[113],"panel":[114],"discussion.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
