{"id":"https://openalex.org/W4416035803","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1209","title":"Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents","display_name":"Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035803","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1209"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1209","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1209","pdf_url":"https://aclanthology.org/2025.emnlp-main.1209.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1209.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061124954","display_name":"Xueqiao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xueqiao Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460139","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-1018-4144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047346314","display_name":"Jingtao Xu","orcid":"https://orcid.org/0000-0003-2307-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingtao Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054450188","display_name":"Yifan Zhu","orcid":"https://orcid.org/0000-0002-4587-4305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091299418","display_name":"X. Shi","orcid":"https://orcid.org/0000-0001-9910-9345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102822513","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0002-1682-1957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010961909","display_name":"Yawei Luo","orcid":"https://orcid.org/0000-0002-7037-1806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yawei Luo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5061124954"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35901258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23688","last_page":"23714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5766000151634216,"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":0.5766000151634216,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.1581999957561493,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.07819999754428864,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2870999872684479},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2660999894142151},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24729999899864197},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.24549999833106995},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.24459999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5924999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41920000314712524},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24729999899864197},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24549999833106995},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.24459999799728394},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.23770000040531158},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.23720000684261322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1209","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1209","pdf_url":"https://aclanthology.org/2025.emnlp-main.1209.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1209","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1209","pdf_url":"https://aclanthology.org/2025.emnlp-main.1209.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035803.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}