{"id":"https://openalex.org/W4312295286","doi":"https://doi.org/10.1007/978-3-031-20059-5_22","title":"Multimodal Transformer with\u00a0Variable-Length Memory for\u00a0Vision-and-Language Navigation","display_name":"Multimodal Transformer with\u00a0Variable-Length Memory for\u00a0Vision-and-Language Navigation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312295286","doi":"https://doi.org/10.1007/978-3-031-20059-5_22"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-20059-5_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-20059-5_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5100443730","display_name":"Chuang Lin","orcid":"https://orcid.org/0000-0002-3726-7601"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Chuang Lin","raw_affiliation_strings":["Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3726-7601","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003190764","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0002-2133-8719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Jiang","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2133-8719","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635804","display_name":"Jianfei Cai","orcid":"https://orcid.org/0000-0002-9444-3763"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianfei Cai","raw_affiliation_strings":["Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9444-3763","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008486397","display_name":"Lizhen Qu","orcid":"https://orcid.org/0000-0002-7764-431X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lizhen Qu","raw_affiliation_strings":["Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7764-431X","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gholamreza Haffari","raw_affiliation_strings":["Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7326-8380","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039592275","display_name":"Zehuan Yuan","orcid":"https://orcid.org/0000-0002-0349-9367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehuan Yuan","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0349-9367","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100443730"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"397"},"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":0.9955000281333923,"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":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.8682445287704468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225641131401062},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48170238733291626},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4790407419204712},{"id":"https://openalex.org/keywords/dynamic-random-access-memory","display_name":"Dynamic random-access memory","score":0.42747795581817627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3610379993915558},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35106292366981506},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32453951239585876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8682445287704468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225641131401062},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48170238733291626},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4790407419204712},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.42747795581817627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3610379993915558},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35106292366981506},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32453951239585876},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-20059-5_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-20059-5_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2006354339","https://openalex.org/W2118781169","https://openalex.org/W2194775991","https://openalex.org/W2236233024","https://openalex.org/W2260756217","https://openalex.org/W2732026016","https://openalex.org/W2904451048","https://openalex.org/W2926977875","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2964343989","https://openalex.org/W2964935470","https://openalex.org/W2967186499","https://openalex.org/W2970231061","https://openalex.org/W2970340522","https://openalex.org/W2974759213","https://openalex.org/W2979727876","https://openalex.org/W2987914945","https://openalex.org/W2997168619","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3034376488","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3090449556","https://openalex.org/W3100923070","https://openalex.org/W3109097593","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3179213173","https://openalex.org/W3195026654","https://openalex.org/W3203034343","https://openalex.org/W3204359931","https://openalex.org/W3204763493","https://openalex.org/W3205276578","https://openalex.org/W3211887611","https://openalex.org/W4214700710","https://openalex.org/W4226024706","https://openalex.org/W6600159499","https://openalex.org/W6600654476","https://openalex.org/W6601283680","https://openalex.org/W6702248584","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2518930778","https://openalex.org/W2109193182","https://openalex.org/W4310420093","https://openalex.org/W3154635860","https://openalex.org/W4226332880","https://openalex.org/W4298054035","https://openalex.org/W2979599569","https://openalex.org/W2064920663","https://openalex.org/W2945849683","https://openalex.org/W2894473080"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
