{"id":"https://openalex.org/W4304083153","doi":"https://doi.org/10.1145/3503161.3548345","title":"Spatial-Temporal Aligned Multi-Agent Learning for Visual Dialog Systems","display_name":"Spatial-Temporal Aligned Multi-Agent Learning for Visual Dialog Systems","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304083153","doi":"https://doi.org/10.1145/3503161.3548345"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548345","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548345","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5102906053","display_name":"Yong Zhuang","orcid":"https://orcid.org/0000-0002-7858-5569"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yong Zhuang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767815","display_name":"Tong Yu","orcid":"https://orcid.org/0000-0001-7998-3326"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Yu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035658564","display_name":"Junda Wu","orcid":"https://orcid.org/0000-0001-6464-7813"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junda Wu","raw_affiliation_strings":["New York University, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088671156","display_name":"Shiqu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqu Wu","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424057","display_name":"Shuai Li","orcid":"https://orcid.org/0000-0001-6722-017X"},"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":"Shuai Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102906053"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41665478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9891999959945679,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8123726844787598},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8079507350921631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547200620174408},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4298446774482727},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.412270188331604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3915390968322754},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10994729399681091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123726844787598},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8079507350921631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547200620174408},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4298446774482727},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.412270188331604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3915390968322754},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10994729399681091}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548345","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548345","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4000000059604645,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2603266952","https://openalex.org/W2745461083","https://openalex.org/W2766447205","https://openalex.org/W2949395487","https://openalex.org/W2963448850","https://openalex.org/W2963567240","https://openalex.org/W2971159908","https://openalex.org/W2988617410","https://openalex.org/W3034611340","https://openalex.org/W3034782127","https://openalex.org/W3155674043","https://openalex.org/W3177155667","https://openalex.org/W3177934633","https://openalex.org/W3198585874","https://openalex.org/W3204887981","https://openalex.org/W3205346281","https://openalex.org/W3206128852","https://openalex.org/W3206904785","https://openalex.org/W4213160977","https://openalex.org/W4238846128","https://openalex.org/W4249013746","https://openalex.org/W4288091739","https://openalex.org/W6767327128"],"related_works":["https://openalex.org/W628946606","https://openalex.org/W2500779211","https://openalex.org/W1963944933","https://openalex.org/W2292950558","https://openalex.org/W3174836468","https://openalex.org/W2007632780","https://openalex.org/W1985736913","https://openalex.org/W1989076311","https://openalex.org/W1203121189","https://openalex.org/W1966533968"],"abstract_inverted_index":{"Existing":[0],"interactive":[1,50,68],"learning":[2,58,159,199],"systems":[3,70,103],"usually":[4],"train":[5,48],"models":[6],"on":[7,174],"simulators":[8,23],"as":[9,29,43],"surrogates":[10],"for":[11,66],"real":[12,35],"users.":[13,36],"Due":[14],"to":[15,26,32,40,82,110,161],"the":[16,49,76,114,133,164,190],"limited":[17],"amount":[18,134],"of":[19,78,135,192],"user":[20,53,136],"data,":[21,80],"trained":[22],"may":[24],"lead":[25],"biased":[27],"results":[28],"it":[30,107],"fails":[31],"well":[33],"represent":[34],"One":[37],"solution":[38],"is":[39,71,94,108,138],"model":[41],"users":[42,101],"agents,":[44],"and":[45,52,88,96,102,106,112,124,145,168,186],"then":[46],"simultaneously":[47],"system":[51],"agents":[54,90,123,170],"by":[55],"multi-agent":[56,157,197],"reinforcement":[57,158,198],"(MARL)":[59],"frameworks.":[60],"However,":[61],"developing":[62],"efficient":[63],"MARL":[64],"frameworks":[65],"modern":[67],"multimodal":[69,79,85,120,165],"still":[72],"challenging.":[73],"First,":[74],"given":[75],"existence":[77],"how":[81],"develop":[83,178],"accurate":[84],"fusion":[86,121],"within":[87,167],"between":[89,100,122,169],"in":[91,201],"each":[92],"interaction":[93],"challenging":[95,109],"unclear.":[97],"Second,":[98],"interactions":[99,115],"are":[104],"complex":[105],"track":[111],"synchronize":[113],"over":[116,126,171],"time.":[117,172],"The":[118],"above":[119],"synchronization":[125],"time":[127],"becomes":[128],"even":[129],"more":[130,147],"challenging,":[131],"when":[132],"data":[137,166],"limited.":[139],"To":[140],"jointly":[141],"address":[142],"these":[143],"challenges":[144],"achieve":[146],"sample-efficient":[148,179],"learning,":[149],"we":[150,177,188],"propose":[151],"a":[152],"novel":[153],"spatial-temporal":[154,194],"aligned":[155,195],"sta":[156,196],"framework":[160,200],"better":[162],"align":[163],"Based":[173],"our":[175,193],"framework,":[176],"visual":[180,202],"dialog":[181,203],"systems.":[182,204],"Through":[183],"extensive":[184],"experiments":[185],"analysis,":[187],"validate":[189],"effectiveness":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}