{"id":"https://openalex.org/W4403791256","doi":"https://doi.org/10.1145/3664647.3681659","title":"Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion","display_name":"Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791256","doi":"https://doi.org/10.1145/3664647.3681659"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5039800314","display_name":"Y.Y. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yingxuan Li","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070532113","display_name":"Ryota Hinami","orcid":"https://orcid.org/0000-0003-1542-2612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryota Hinami","raw_affiliation_strings":["Mantra Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Mantra Inc., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069982192","display_name":"Kiyoharu Aizawa","orcid":"https://orcid.org/0000-0003-2146-6275"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoharu Aizawa","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023905620","display_name":"Yusuke Matsui","orcid":"https://orcid.org/0000-0003-1529-0154"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Matsui","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039800314"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":19.9066,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99191153,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7366","last_page":"7374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12390","display_name":"Comics and Graphic Narratives","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1213","display_name":"Visual Arts and Performing Arts"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12390","display_name":"Comics and Graphic Narratives","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1213","display_name":"Visual Arts and Performing Arts"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9922999739646912,"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/T10759","display_name":"Translation Studies and Practices","score":0.9668999910354614,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.7033994197845459},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6433548927307129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5902896523475647},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5774993300437927},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5387334227561951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5098894834518433},{"id":"https://openalex.org/keywords/comics","display_name":"Comics","score":0.5008425712585449},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4870510399341583},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4854748547077179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4533675014972687},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43917837738990784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.327064573764801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16860011219978333},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10766744613647461}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7033994197845459},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6433548927307129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902896523475647},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5774993300437927},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5387334227561951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5098894834518433},{"id":"https://openalex.org/C529099274","wikidata":"https://www.wikidata.org/wiki/Q1004","display_name":"Comics","level":2,"score":0.5008425712585449},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4870510399341583},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4854748547077179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4533675014972687},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43917837738990784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.327064573764801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16860011219978333},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10766744613647461},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2077069816","https://openalex.org/W2108598243","https://openalex.org/W2115886797","https://openalex.org/W2150593711","https://openalex.org/W2194775991","https://openalex.org/W2579549467","https://openalex.org/W2963536419","https://openalex.org/W3017083351","https://openalex.org/W3035017890","https://openalex.org/W3093203468","https://openalex.org/W3099982213","https://openalex.org/W3174554374","https://openalex.org/W4312443924","https://openalex.org/W4385571689","https://openalex.org/W4402981217"],"related_works":["https://openalex.org/W4234190324","https://openalex.org/W4396668120","https://openalex.org/W2126085626","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W1973693762","https://openalex.org/W208363076","https://openalex.org/W4230495983","https://openalex.org/W2887000230","https://openalex.org/W2141917278"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
