{"id":"https://openalex.org/W3199741300","doi":"https://doi.org/10.1145/3474085.3475493","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","display_name":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3199741300","doi":"https://doi.org/10.1145/3474085.3475493","mag":"3199741300"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.11243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xun Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xun Gao","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhao","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Longjun Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longjun Cai","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.5813,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68795993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3380","last_page":"3389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T11439","display_name":"Video Analysis and Summarization","score":0.9970999956130981,"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/task","display_name":"Task (project management)","score":0.6516000032424927},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6499000191688538},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6100999712944031},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.521399974822998},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4260999858379364},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3986999988555908},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646999716758728},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018000245094299},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3986999988555908},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.11243","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.11243","pdf_url":"https://arxiv.org/pdf/2109.11243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.11243","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.11243","pdf_url":"https://arxiv.org/pdf/2109.11243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1555767263","https://openalex.org/W1606493646","https://openalex.org/W1892323599","https://openalex.org/W1981918162","https://openalex.org/W1985867508","https://openalex.org/W2008933718","https://openalex.org/W2044807399","https://openalex.org/W2053101950","https://openalex.org/W2063249218","https://openalex.org/W2083021723","https://openalex.org/W2094637479","https://openalex.org/W2104084893","https://openalex.org/W2135964285","https://openalex.org/W2136548587","https://openalex.org/W2149628368","https://openalex.org/W2153597356","https://openalex.org/W2331327135","https://openalex.org/W2341528187","https://openalex.org/W2391561377","https://openalex.org/W2519818067","https://openalex.org/W2546649374","https://openalex.org/W2609468337","https://openalex.org/W2612395950","https://openalex.org/W2745497104","https://openalex.org/W2782828077","https://openalex.org/W2798536775","https://openalex.org/W2888683367","https://openalex.org/W2912990735","https://openalex.org/W2940963663","https://openalex.org/W2962794823","https://openalex.org/W2963091558","https://openalex.org/W2963351113","https://openalex.org/W2963542293","https://openalex.org/W2969985801","https://openalex.org/W2981851019","https://openalex.org/W2982598795","https://openalex.org/W2983347580","https://openalex.org/W2996209825","https://openalex.org/W3001529617","https://openalex.org/W3016928440","https://openalex.org/W3034520808","https://openalex.org/W3034702511"],"related_works":[],"abstract_inverted_index":{"Recognizing":[0],"the":[1,37,41,54,82,87,101,140,178,182,198,205,228],"emotional":[2,38],"state":[3],"of":[4,63,66,111,170,230],"people":[5],"is":[6,51,120],"a":[7,20,46,105,121,161,166,216],"basic":[8],"but":[9,91],"challenging":[10,90],"task":[11,22,33,88,221],"in":[12,23,45,93,222],"video":[13,48,131,136,150,223],"understanding.":[14],"In":[15,185],"this":[16,24],"paper,":[17],"we":[18,103,164],"propose":[19,165],"new":[21,106,217],"field,":[25],"named":[26],"Pairwise":[27],"Emotional":[28,109],"Relationship":[29],"Recognition":[30],"(PERR).":[31],"This":[32],"aims":[34],"to":[35,81,176,187,213],"recognize":[36],"relationship":[39],"between":[40],"two":[42],"interactive":[43],"characters":[44],"given":[47],"clip.":[49],"It":[50],"different":[52],"from":[53,139],"traditional":[55],"emotion":[56],"and":[57,117,152,158,225],"social":[58],"relation":[59],"recognition":[60],"task.":[61,184],"Varieties":[62],"information,":[64],"consisting":[65],"character":[67],"appearance,":[68],"behaviors,":[69],"facial":[70],"emotions,":[71],"dialogues,":[72],"background":[73],"music":[74],"as":[75,77,207,209],"well":[76,208],"subtitles":[78],"contribute":[79],"differently":[80],"final":[83],"results,":[84],"which":[85,128],"makes":[86],"more":[89,95],"meaningful":[92],"developing":[94],"advanced":[96],"multi-modal":[97,123,179,231],"models.":[98],"To":[99],"facilitate":[100],"task,":[102,127],"develop":[104],"dataset":[107,124],"called":[108],"RelAtionship":[110],"inTeractiOn":[112],"(ERATO)":[113],"based":[114],"on":[115],"dramas":[116],"movies.":[118],"ERATO":[119,143,206],"large-scale":[122],"for":[125,181,219],"PERR":[126,183,220],"has":[129],"31,182":[130],"clips,":[132],"lasting":[133],"about":[134,201],"203":[135],"hours.":[137],"Different":[138],"existing":[141],"datasets,":[142],"contains":[144],"interaction-centric":[145],"videos":[146],"with":[147],"multi-shots,":[148],"varied":[149],"length,":[151],"multiple":[153],"modalities":[154],"including":[155],"visual,":[156],"audio":[157],"text.":[159],"As":[160],"minor":[162],"contribution,":[163],"baseline":[167],"model":[168],"composed":[169],"Synchronous":[171],"Modal-Temporal":[172],"Attention":[173],"(SMTA)":[174],"unit":[175],"fuse":[177],"information":[180],"contrast":[186],"other":[188],"prevailing":[189],"attention":[190],"mechanisms,":[191],"our":[192,210],"proposed":[193,211],"SMTA":[194,212],"can":[195],"steadily":[196],"improve":[197,227],"performance":[199],"by":[200],"1%.":[202],"We":[203],"expect":[204],"open":[214],"up":[215],"way":[218],"understanding":[224],"further":[226],"research":[229],"fusion":[232],"methodology.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-09-27T00:00:00"}