{"id":"https://openalex.org/W2964018203","doi":"https://doi.org/10.18653/v1/w18-5015","title":"Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog","display_name":"Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2964018203","doi":"https://doi.org/10.18653/v1/w18-5015","mag":"2964018203"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5015","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5015","pdf_url":"https://www.aclweb.org/anthology/W18-5015.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 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5015.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101399865","display_name":"Jiaping Zhang","orcid":"https://orcid.org/0000-0002-0595-7202"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaping Zhang","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114246802","display_name":"Tiancheng Zhao","orcid":"https://orcid.org/0000-0002-7443-0666"},"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":"Tiancheng Zhao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.293,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89854858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"150"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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/dialog-box","display_name":"Dialog box","score":0.908934473991394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8295760154724121},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.762980580329895},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6589028835296631},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6435180902481079},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6257532835006714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5836868286132812},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5452961325645447},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4725959897041321},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4393799304962158},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43038347363471985},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07387065887451172}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.908934473991394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295760154724121},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.762980580329895},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6589028835296631},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6435180902481079},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6257532835006714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5836868286132812},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5452961325645447},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4725959897041321},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4393799304962158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43038347363471985},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07387065887451172},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-5015","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5015","pdf_url":"https://www.aclweb.org/anthology/W18-5015.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 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5015","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5015","pdf_url":"https://www.aclweb.org/anthology/W18-5015.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 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964018203.pdf","grobid_xml":"https://content.openalex.org/works/W2964018203.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1681299129","https://openalex.org/W1686810756","https://openalex.org/W1777239053","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2005814556","https://openalex.org/W2088923570","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2145339207","https://openalex.org/W2153385324","https://openalex.org/W2160371091","https://openalex.org/W2201581102","https://openalex.org/W2231198303","https://openalex.org/W2412899141","https://openalex.org/W2438667436","https://openalex.org/W2481240925","https://openalex.org/W2558809543","https://openalex.org/W2563399268","https://openalex.org/W2583186419","https://openalex.org/W2594164766","https://openalex.org/W2603266952","https://openalex.org/W2622980782","https://openalex.org/W2741363662","https://openalex.org/W2746553466","https://openalex.org/W2768661419","https://openalex.org/W2770171824","https://openalex.org/W2774397635","https://openalex.org/W2962776342","https://openalex.org/W2963306198","https://openalex.org/W2963351776","https://openalex.org/W2963477884","https://openalex.org/W2963546667","https://openalex.org/W2963643760","https://openalex.org/W2963735856","https://openalex.org/W2964046741","https://openalex.org/W2964080167","https://openalex.org/W2964179661"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W2735573723","https://openalex.org/W3133893348"],"abstract_inverted_index":{"Creating":[0],"an":[1,110],"intelligent":[2],"conversational":[3],"system":[4],"that":[5,50],"understands":[6],"vision":[7,53],"and":[8,54,69,80,104,114],"language":[9,55],"is":[10],"one":[11],"of":[12],"the":[13,64,70,95,101,105],"ultimate":[14],"goals":[15],"in":[16,37,94,109],"Artificial":[17],"Intelligence":[18],"(AI)":[19],"Extensive":[20],"research":[21,29],"has":[22,30],"focused":[23],"on":[24,32],"vision-tolanguage":[25],"generation,":[26],"however,":[27],"limited":[28],"touched":[31],"combining":[33],"these":[34],"two":[35],"modalities":[36],"a":[38,44,85],"goal-driven":[39],"dialog":[40,66,72,77,96],"context.":[41],"We":[42,82,99],"propose":[43,84],"multimodal":[45,65],"hierarchical":[46,71],"reinforcement":[47],"learning":[48],"framework":[49,61,103],"dynamically":[51],"integrates":[52],"for":[56],"task-oriented":[57],"visual":[58],"dialog.":[59],"The":[60],"jointly":[62],"learns":[63],"state":[67,88,97,106],"representation":[68],"policy":[73],"to":[74,90],"improve":[75],"both":[76],"task":[78],"success":[79],"efficiency.":[81],"also":[83],"new":[86],"technique,":[87],"adaptation,":[89],"integrate":[91],"context":[92],"awareness":[93],"representation.":[98],"evaluate":[100],"proposed":[102],"adaptation":[107],"technique":[108],"image":[111],"guessing":[112],"game":[113],"achieve":[115],"promising":[116],"results.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
