{"id":"https://openalex.org/W4411119769","doi":"https://doi.org/10.18653/v1/2025.naacl-long.310","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","display_name":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411119769","doi":"https://doi.org/10.18653/v1/2025.naacl-long.310"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.naacl-long.310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.naacl-long.310","pdf_url":"https://aclanthology.org/2025.naacl-long.310.pdf","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 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.naacl-long.310.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102755689","display_name":"Manan Suri","orcid":"https://orcid.org/0000-0001-5089-2658"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manan Suri","raw_affiliation_strings":["University of Maryland , College Park Adobe Research IGDTUW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park Adobe Research IGDTUW","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113165733","display_name":"Puneet Mathur","orcid":"https://orcid.org/0000-0002-3006-9186"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puneet Mathur","raw_affiliation_strings":["University of Maryland , College Park Adobe Research IGDTUW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park Adobe Research IGDTUW","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028863551","display_name":"Franck Dernoncourt","orcid":"https://orcid.org/0000-0002-1119-1346"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Dernoncourt","raw_affiliation_strings":["University of Maryland , College Park Adobe Research IGDTUW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park Adobe Research IGDTUW","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052023100","display_name":"Kanika Goswami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanika Goswami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009957887","display_name":"Ryan A. Rossi","orcid":"https://orcid.org/0000-0001-9758-0635"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan A. Rossi","raw_affiliation_strings":["University of Maryland , College Park Adobe Research IGDTUW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park Adobe Research IGDTUW","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland , College Park Adobe Research IGDTUW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park Adobe Research IGDTUW","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.2866,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99498661,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6088","last_page":"6109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.991100013256073,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.6930403709411621},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5970959067344666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34805047512054443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930403709411621},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5970959067344666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34805047512054443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.naacl-long.310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.naacl-long.310","pdf_url":"https://aclanthology.org/2025.naacl-long.310.pdf","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 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.naacl-long.310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.naacl-long.310","pdf_url":"https://aclanthology.org/2025.naacl-long.310.pdf","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 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411119769.pdf","grobid_xml":"https://content.openalex.org/works/W4411119769.grobid-xml"},"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":{"Manan":[0],"Suri,":[1],"Puneet":[2],"Mathur,":[3],"Franck":[4],"Dernoncourt,":[5],"Kanika":[6],"Goswami,":[7],"Ryan":[8],"A.":[9],"Rossi,":[10],"Dinesh":[11],"Manocha.":[12],"Proceedings":[13],"of":[14,18,21,25],"the":[15,19,22,26],"2025":[16],"Conference":[17],"Nations":[20],"Americas":[23],"Chapter":[24],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"Human":[31],"Language":[32],"Technologies":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2025.":[38]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}
