{"id":"https://openalex.org/W3175482402","doi":"https://doi.org/10.1109/lra.2021.3092686","title":"CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation","display_name":"CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3175482402","doi":"https://doi.org/10.1109/lra.2021.3092686","mag":"3175482402"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3092686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3092686","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5039713129","display_name":"Aly Magassouba","orcid":"https://orcid.org/0000-0002-0895-5982"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aly Magassouba","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0895-5982","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033744547","display_name":"Komei Sugiura","orcid":"https://orcid.org/0000-0002-0261-0510"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Komei Sugiura","raw_affiliation_strings":["Keio University, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0261-0510","affiliations":[{"raw_affiliation_string":"Keio University, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2242,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.81343122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"6","issue":"4","first_page":"6258","last_page":"6265"},"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":0.9955999851226807,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"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/transformer","display_name":"Transformer","score":0.5763424038887024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4845546782016754},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3884983956813812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37848758697509766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33141255378723145},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2221769392490387},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1872095763683319},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1074548065662384}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5763424038887024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4845546782016754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3884983956813812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37848758697509766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33141255378723145},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2221769392490387},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1872095763683319},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1074548065662384}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3092686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3092686","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2367706801","display_name":"Adversarial Data Augmentation for Multimodal Language Understanding","funder_award_id":"20H04269","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321680","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2069809153","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2193945050","https://openalex.org/W2236233024","https://openalex.org/W2302255633","https://openalex.org/W2506483933","https://openalex.org/W2805984364","https://openalex.org/W2896457183","https://openalex.org/W2926977875","https://openalex.org/W2945260553","https://openalex.org/W2951973805","https://openalex.org/W2953626316","https://openalex.org/W2963177331","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963726321","https://openalex.org/W2963800628","https://openalex.org/W2963922343","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2971274815","https://openalex.org/W2987914945","https://openalex.org/W2991186560","https://openalex.org/W2997591391","https://openalex.org/W2998903229","https://openalex.org/W3008374555","https://openalex.org/W3013640429","https://openalex.org/W3034500398","https://openalex.org/W3035232877","https://openalex.org/W3035691840","https://openalex.org/W3090449556","https://openalex.org/W3101045333","https://openalex.org/W3107094551","https://openalex.org/W3109097593","https://openalex.org/W3121465735","https://openalex.org/W3147794100","https://openalex.org/W3156559819","https://openalex.org/W3192162805","https://openalex.org/W3198196812","https://openalex.org/W4385245566","https://openalex.org/W6667981000","https://openalex.org/W6682631176","https://openalex.org/W6690047748","https://openalex.org/W6698183232","https://openalex.org/W6725318829","https://openalex.org/W6739901393","https://openalex.org/W6751885507","https://openalex.org/W6755207826","https://openalex.org/W6762122294","https://openalex.org/W6766071559","https://openalex.org/W6770775884","https://openalex.org/W6773526284","https://openalex.org/W6773815586","https://openalex.org/W6774605722","https://openalex.org/W6774906915","https://openalex.org/W6776721752","https://openalex.org/W6776907606","https://openalex.org/W6786303254"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Navigation":[0,69],"guided":[1],"by":[2,90],"natural":[3,36],"language":[4,37,98],"instructions":[5,92,156,159],"is":[6,125],"particularly":[7],"suitable":[8],"for":[9,142],"Domestic":[10],"Service":[11],"Robots":[12],"that":[13,28,60,131],"interacts":[14],"naturally":[15],"with":[16],"users.":[17],"This":[18],"task":[19,41],"involves":[20],"the":[21,44,53,58,63,76,79,83,91,95,106,112,168],"prediction":[22],"of":[23,26,46,52,78,86,170,175],"a":[24,31,35,87,120,128,146],"sequence":[25],"actions":[27],"leads":[29],"to":[30,93,117,127],"specified":[32,89],"destination":[33],"given":[34],"navigation":[38,133],"instruction.":[39],"The":[40,65,122,135,164],"thus":[42],"requires":[43,75],"understanding":[45,177],"instructions,":[47],"such":[48],"as":[49],"\u201cWalk":[50],"out":[51],"bathroom":[54],"and":[55,67,81,99,114,178],"wait":[56],"on":[57,62],"stairs":[59],"are":[61,153,160],"right\u201d.":[64],"Visual":[66],"Language":[68],"remains":[70],"challenging,":[71],"notably":[72],"because":[73],"it":[74],"exploration":[77],"environment":[80],"at":[82],"accurate":[84],"following":[85],"path":[88],"model":[94],"relationship":[96],"between":[97],"vision.":[100],"To":[101],"address":[102],"this,":[103],"we":[104],"propose":[105],"CrossMap":[107,123],"Transformer":[108],"network,":[109],"which":[110],"encodes":[111],"linguistic":[113],"visual":[115],"features":[116],"sequentially":[118],"generate":[119],"path.":[121,163],"transformer":[124],"tied":[126],"Transformer-based":[129],"speaker":[130],"generates":[132],"instructions.":[134],"two":[136],"networks":[137],"share":[138],"common":[139],"latent":[140],"features,":[141],"mutual":[143],"enhancement":[144],"through":[145],"double":[147],"back":[148],"translation":[149],"model:":[150],"Generated":[151],"paths":[152],"translated":[154,161],"into":[155,162],"while":[157],"generated":[158],"experimental":[165],"results":[166],"show":[167],"benefits":[169],"our":[171],"approach":[172],"in":[173],"terms":[174],"instruction":[176,179],"generation.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}