{"id":"https://openalex.org/W2963287297","doi":"https://doi.org/10.18653/v1/p19-1648","title":"Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog","display_name":"Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963287297","doi":"https://doi.org/10.18653/v1/p19-1648","mag":"2963287297"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1648","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1648","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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1648","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066666034","display_name":"Zhe Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhe Gan","raw_affiliation_strings":["Microsoft Dynamics 365 AI Research,"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI Research,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101580523","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0002-7901-8662"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cheng","raw_affiliation_strings":["Microsoft Dynamics 365 AI Research,"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI Research,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059208041","display_name":"Ahmed El Kholy","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Kholy","raw_affiliation_strings":["Microsoft Dynamics 365 AI Research,"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI Research,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657555","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0003-0867-8863"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":["Microsoft Dynamics 365 AI Research,"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI Research,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442542","display_name":"Jingjing Liu","orcid":"https://orcid.org/0009-0002-6277-5816"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjing Liu","raw_affiliation_strings":["Microsoft Dynamics 365 AI Research,"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI Research,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066666034"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":7.9965,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.97988946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6463","last_page":"6474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9950000047683716,"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/dialog-box","display_name":"Dialog box","score":0.8345804810523987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8216924071311951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6379312872886658},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.6222972869873047},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5979586839675903},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5823544263839722},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.580696702003479},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5100787281990051},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5092116594314575},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4648636281490326},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4606187045574188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44130122661590576},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4266113042831421},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3485981523990631},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11231327056884766}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8345804810523987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216924071311951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6379312872886658},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.6222972869873047},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5979586839675903},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5823544263839722},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.580696702003479},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5100787281990051},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5092116594314575},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4648636281490326},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4606187045574188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44130122661590576},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4266113042831421},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3485981523990631},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11231327056884766},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1648","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1648","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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1648","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1648","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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1959608418","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2099471712","https://openalex.org/W2126209950","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2417356443","https://openalex.org/W2521709538","https://openalex.org/W2532034655","https://openalex.org/W2546696630","https://openalex.org/W2558809543","https://openalex.org/W2563399268","https://openalex.org/W2581637843","https://openalex.org/W2583186419","https://openalex.org/W2599940792","https://openalex.org/W2603266952","https://openalex.org/W2613718673","https://openalex.org/W2622980782","https://openalex.org/W2745461083","https://openalex.org/W2750557179","https://openalex.org/W2750998636","https://openalex.org/W2768661419","https://openalex.org/W2785722920","https://openalex.org/W2798503981","https://openalex.org/W2810840719","https://openalex.org/W2886247548","https://openalex.org/W2888302696","https://openalex.org/W2892245540","https://openalex.org/W2895088466","https://openalex.org/W2915552958","https://openalex.org/W2917061951","https://openalex.org/W2940092135","https://openalex.org/W2949197413","https://openalex.org/W2951527505","https://openalex.org/W2951831170","https://openalex.org/W2962741254","https://openalex.org/W2963131783","https://openalex.org/W2963145877","https://openalex.org/W2963150162","https://openalex.org/W2963187678","https://openalex.org/W2963223524","https://openalex.org/W2963344337","https://openalex.org/W2963363070","https://openalex.org/W2963383024","https://openalex.org/W2963546667","https://openalex.org/W2963623904","https://openalex.org/W2963643760","https://openalex.org/W2963689203","https://openalex.org/W2963769536","https://openalex.org/W2963791035","https://openalex.org/W2963954913","https://openalex.org/W2964004697","https://openalex.org/W2964118342","https://openalex.org/W2964121744","https://openalex.org/W2964218959","https://openalex.org/W2964223283","https://openalex.org/W2964267515","https://openalex.org/W2964268978","https://openalex.org/W2964308564","https://openalex.org/W2964345214","https://openalex.org/W2967045987","https://openalex.org/W2970355596","https://openalex.org/W2981902456","https://openalex.org/W3004349648","https://openalex.org/W3104486441","https://openalex.org/W4293466734","https://openalex.org/W4293749116","https://openalex.org/W4297749157","https://openalex.org/W4302953241","https://openalex.org/W4306716473","https://openalex.org/W4320013936","https://openalex.org/W4394665226"],"related_works":["https://openalex.org/W2964061310","https://openalex.org/W2231285690","https://openalex.org/W4387636010","https://openalex.org/W2963477107","https://openalex.org/W3093385053","https://openalex.org/W4390091918","https://openalex.org/W2553418567","https://openalex.org/W4389682534","https://openalex.org/W2034475059","https://openalex.org/W3045060014"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,19,31,89],"new":[4,90],"model":[5,87],"for":[6,72],"visual":[7,108],"dialog,":[8,32],"Recurrent":[9],"Dual":[10],"Attention":[11],"Network":[12],"(ReDAN),":[13],"using":[14],"multi-step":[15],"reasoning":[16,40,47,74,99],"to":[17,118],"answer":[18,36,121],"series":[20],"of":[21,30,45,52,92],"questions":[22],"about":[23],"an":[24],"image.":[25],"In":[26,42],"each":[27,43],"question-answering":[28],"turn":[29],"ReDAN":[33,86,104],"infers":[34],"the":[35,46,49,53,59,62,67,76,80,84,98,119],"progressively":[37],"through":[38],"multiple":[39],"steps.":[41],"step":[44],"process,":[48],"semantic":[50],"representation":[51,69],"question":[54],"is":[55,70],"updated":[56],"based":[57],"on":[58,97],"image":[60],"and":[61,66,109],"previous":[63],"dialog":[64],"history,":[65],"recurrently-refined":[68],"used":[71],"further":[73,101],"in":[75],"subsequent":[77],"step.":[78],"On":[79],"VisDial":[81],"v1.0":[82],"dataset,":[83],"proposed":[85],"achieves":[88],"state-of-the-art":[91],"64.47%":[93],"NDCG":[94],"score.":[95],"Visualization":[96],"process":[100],"demonstrates":[102],"that":[103],"can":[105,116],"locate":[106],"context-relevant":[107],"textual":[110],"clues":[111],"via":[112],"iterative":[113],"refinement,":[114],"which":[115],"lead":[117],"correct":[120],"step-by-step.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":4}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}