{"id":"https://openalex.org/W4415536836","doi":"https://doi.org/10.1145/3746027.3755041","title":"Character-Centric Understanding of Animated Movies","display_name":"Character-Centric Understanding of Animated Movies","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536836","doi":"https://doi.org/10.1145/3746027.3755041"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755041","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755041","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755041","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114368382","display_name":"Zhongrui Gui","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhongrui Gui","raw_affiliation_strings":["VGG, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-8005-0471","affiliations":[{"raw_affiliation_string":"VGG, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101281862","display_name":"Junyu Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junyu Xie","raw_affiliation_strings":["VGG, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0002-1123-493X","affiliations":[{"raw_affiliation_string":"VGG, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075613881","display_name":"Tengda Han","orcid":"https://orcid.org/0000-0002-1874-9664"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tengda Han","raw_affiliation_strings":["VGG, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1874-9664","affiliations":[{"raw_affiliation_string":"VGG, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053549250","display_name":"Weidi Xie","orcid":"https://orcid.org/0009-0002-8609-6826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["SAI, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-8609-6826","affiliations":[{"raw_affiliation_string":"SAI, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["VGG, University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8945-8573","affiliations":[{"raw_affiliation_string":"VGG, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3300","last_page":"3309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T12390","display_name":"Comics and Graphic Narratives","score":0.9898999929428101,"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/T11448","display_name":"Face recognition and analysis","score":0.972599983215332,"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/pipeline","display_name":"Pipeline (software)","score":0.7222999930381775},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7175999879837036},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5666000247001648},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4984999895095825},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.438400000333786},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.40630000829696655},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39410001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376999855041504},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7222999930381775},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7175999879837036},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.301800012588501},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.2768000066280365},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755041","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755041","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755041","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755041","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2963457656","https://openalex.org/W2969985801","https://openalex.org/W3034552680","https://openalex.org/W3092721056","https://openalex.org/W3095481265","https://openalex.org/W4286378963"],"related_works":[],"abstract_inverted_index":{"Animated":[0],"movies":[1,145],"are":[2],"captivating":[3],"for":[4,17,93,119,126,161],"their":[5,38],"unique":[6],"character":[7,57,78,99,108],"designs":[8],"and":[9,41,54,59,89,123,158,171],"imaginative":[10],"storytelling,":[11],"yet":[12],"they":[13],"pose":[14],"significant":[15,153],"challenges":[16],"existing":[18],"recognition":[19,30,100],"systems.":[20],"Unlike":[21],"the":[22,72,127,169],"consistent":[23],"visual":[24,87],"patterns":[25],"detected":[26],"by":[27],"conventional":[28],"face":[29],"methods,":[31],"animated":[32,56,65,144,162],"characters":[33],"exhibit":[34],"extreme":[35],"diversity":[36],"in":[37,133,155],"appearance,":[39],"motion,":[40],"deformation.":[42],"In":[43],"this":[44,134],"work,":[45],"we":[46,110,136],"propose":[47],"an":[48,76],"audio-visual":[49,77],"pipeline":[50,151],"to":[51,68],"enable":[52],"automatic":[53,73],"robust":[55],"recognition,":[58,109],"thereby":[60],"enhance":[61],"character-centric":[62,150],"understanding":[63],"of":[64,75,142],"movies.":[66],"Central":[67],"our":[69],"approach":[70],"is":[71],"construction":[74],"bank":[79,84],"from":[80],"online":[81],"sources.":[82],"This":[83],"contains":[85],"both":[86,156],"exemplars":[88],"voice":[90],"(audio)":[91],"samples":[92],"each":[94],"character,":[95],"enabling":[96],"subsequent":[97],"multi-modal":[98],"despite":[101],"long-tailed":[102],"appearance":[103],"distributions.":[104],"Building":[105],"on":[106],"accurate":[107],"explore":[111],"two":[112],"downstream":[113],"applications:":[114],"Audio":[115],"Description":[116],"(AD)":[117],"generation":[118],"visually":[120],"impaired":[121],"audiences,":[122],"character-aware":[124],"subtitling":[125],"hearing":[128],"impaired.":[129],"To":[130],"support":[131],"research":[132],"domain,":[135],"introduce":[137],"CMD-AM,":[138],"a":[139],"new":[140],"dataset":[141],"75":[143],"with":[146],"comprehensive":[147],"annotations.":[148],"Our":[149],"demonstrates":[152],"improvements":[154],"accessibility":[157],"narrative":[159],"comprehension":[160],"content":[163],"over":[164],"prior":[165],"face-detection-based":[166],"approaches.":[167],"For":[168],"code":[170],"dataset,":[172],"visit":[173],"https://www.robots.ox.ac.uk/~vgg/research/animated_ad/.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
