{"id":"https://openalex.org/W2913568332","doi":"https://doi.org/10.24963/ijcai.2020/338","title":"Embodied Multimodal Multitask Learning","display_name":"Embodied Multimodal Multitask Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2913568332","doi":"https://doi.org/10.24963/ijcai.2020/338","mag":"2913568332"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/338","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/338","pdf_url":"https://www.ijcai.org/proceedings/2020/0338.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0338.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016223957","display_name":"Devendra Singh Chaplot","orcid":null},"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":"Devendra Singh Chaplot","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529103","display_name":"Lisa Lee","orcid":"https://orcid.org/0000-0001-5058-9464"},"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":"Lisa Lee","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"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":"Ruslan Salakhutdinov","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050342343","display_name":"Devi Parikh","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devi Parikh","raw_affiliation_strings":["Georgia Institute of Technology & Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology & Facebook AI Research","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":"https://orcid.org/0000-0002-1358-0011"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Georgia Institute of Technology & Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology & Facebook AI Research","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2442","last_page":"2448"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9943000078201294,"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":0.802955687046051},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6672431826591492},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5900619626045227},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5793014168739319},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5745232105255127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5559779405593872},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4676515460014343},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42772209644317627},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.42307764291763306},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3726980686187744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802955687046051},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6672431826591492},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5900619626045227},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5793014168739319},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5745232105255127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559779405593872},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4676515460014343},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42772209644317627},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.42307764291763306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3726980686187744},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2020/338","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/338","pdf_url":"https://www.ijcai.org/proceedings/2020/0338.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.01385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.01385","pdf_url":"https://arxiv.org/pdf/1902.01385","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":"","raw_type":"text"},{"id":"mag:2913568332","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1902.01385","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1902.01385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.01385","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/338","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/338","pdf_url":"https://www.ijcai.org/proceedings/2020/0338.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2913568332.pdf","grobid_xml":"https://content.openalex.org/works/W2913568332.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1478687540","https://openalex.org/W1538131130","https://openalex.org/W1757796397","https://openalex.org/W2156387975","https://openalex.org/W2172140247","https://openalex.org/W2257979135","https://openalex.org/W2362143032","https://openalex.org/W2412400526","https://openalex.org/W2553701371","https://openalex.org/W2604608429","https://openalex.org/W2611884151","https://openalex.org/W2627585944","https://openalex.org/W2736601468","https://openalex.org/W2760103357","https://openalex.org/W2772390515","https://openalex.org/W2783375473","https://openalex.org/W2785955089","https://openalex.org/W2786209943","https://openalex.org/W2797263747","https://openalex.org/W2803325309","https://openalex.org/W2950697717","https://openalex.org/W2950872548","https://openalex.org/W2951660448","https://openalex.org/W2952791429","https://openalex.org/W2953326374","https://openalex.org/W2962684798","https://openalex.org/W2962747693","https://openalex.org/W2962887844","https://openalex.org/W2963656855","https://openalex.org/W2964043796","https://openalex.org/W2964084698"],"related_works":["https://openalex.org/W3034419097","https://openalex.org/W3186513731","https://openalex.org/W2618235849","https://openalex.org/W2968543045","https://openalex.org/W3035337174","https://openalex.org/W1481820510","https://openalex.org/W2767800181","https://openalex.org/W3184053512","https://openalex.org/W2952928463","https://openalex.org/W3108086142","https://openalex.org/W2994713247","https://openalex.org/W3034982658","https://openalex.org/W2963104543","https://openalex.org/W3033837109","https://openalex.org/W2997547717","https://openalex.org/W2936420065","https://openalex.org/W2916723116","https://openalex.org/W2609689588","https://openalex.org/W3207311065","https://openalex.org/W2252238675"],"abstract_inverted_index":{"Visually-grounded":[0],"embodied":[1],"language":[2],"learning":[3,12],"models":[4],"have":[5],"recently":[6],"shown":[7],"to":[8,38,50,52,95,133],"be":[9],"effective":[10],"at":[11],"multiple":[13],"multimodal":[14],"tasks":[15,45,76],"such":[16],"as":[17],"following":[18],"navigational":[19],"instructions":[20,134],"and":[21,46,55,83,93,100,127],"answering":[22],"questions.":[23],"In":[24],"this":[25,119],"paper,":[26],"we":[27],"address":[28],"two":[29],"key":[30],"limitations":[31],"of":[32,81,109,121],"these":[33],"models,":[34],"(a)":[35],"the":[36,40,48,79,87,103],"inability":[37,49],"transfer":[39,51,74,99,132],"grounded":[41],"knowledge":[42,73,80,98],"across":[43,75],"different":[44],"(b)":[47],"new":[53,136],"words":[54,82],"concepts":[56],"not":[57],"seen":[58],"during":[59],"training":[60],"using":[61],"only":[62],"a":[63,68,107],"few":[64],"examples.":[65],"We":[66,90,115],"propose":[67],"multitask":[69],"model":[70,105,125],"which":[71,129],"facilitates":[72],"by":[77],"disentangling":[78],"visual":[84],"attributes":[85],"in":[86,111],"intermediate":[88],"representations.":[89],"create":[91],"scenarios":[92],"datasets":[94],"quantify":[96],"cross-task":[97],"show":[101,117],"that":[102,118],"proposed":[104],"outperforms":[106],"range":[108],"baselines":[110],"simulated":[112],"3D":[113],"environments.":[114],"also":[116],"disentanglement":[120],"representations":[122],"makes":[123],"our":[124],"modular":[126],"interpretable":[128],"allows":[130],"for":[131],"containing":[135],"concepts.":[137]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}