{"id":"https://openalex.org/W4391164059","doi":"https://doi.org/10.1109/tmm.2024.3358112","title":"Vision-and-Language Navigation via Latent Semantic Alignment Learning","display_name":"Vision-and-Language Navigation via Latent Semantic Alignment Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391164059","doi":"https://doi.org/10.1109/tmm.2024.3358112"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3358112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3358112","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/A5030444210","display_name":"Siying Wu","orcid":"https://orcid.org/0000-0002-9752-258X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Siying Wu","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079007635","display_name":"Xueyang Fu","orcid":"https://orcid.org/0000-0001-8036-4071"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyang Fu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030444210"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2436,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88433876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"8406","last_page":"8418"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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":0.9957000017166138,"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":0.8874742984771729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6099233627319336},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5616064667701721},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4975323975086212},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4816361963748932},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4597170352935791},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45455941557884216},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4446997046470642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40991079807281494},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3772197961807251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8874742984771729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6099233627319336},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5616064667701721},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4975323975086212},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4816361963748932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4597170352935791},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45455941557884216},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4446997046470642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40991079807281494},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3772197961807251},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3358112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3358112","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G575396328","display_name":null,"funder_award_id":"62225207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6082284406","display_name":null,"funder_award_id":"62276243","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W2069830673","https://openalex.org/W2095784398","https://openalex.org/W2125409550","https://openalex.org/W2143864104","https://openalex.org/W2251512949","https://openalex.org/W2593841437","https://openalex.org/W2745461083","https://openalex.org/W2884565639","https://openalex.org/W2887585070","https://openalex.org/W2896457183","https://openalex.org/W2926977875","https://openalex.org/W2938603906","https://openalex.org/W2942395934","https://openalex.org/W2951973805","https://openalex.org/W2962744691","https://openalex.org/W2963541336","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2987401211","https://openalex.org/W2987914945","https://openalex.org/W2997591391","https://openalex.org/W3026441479","https://openalex.org/W3034475678","https://openalex.org/W3034500398","https://openalex.org/W3035232877","https://openalex.org/W3035365026","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105136412","https://openalex.org/W3107069568","https://openalex.org/W3109097593","https://openalex.org/W3135254306","https://openalex.org/W3145807616","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3173332661","https://openalex.org/W3174887918","https://openalex.org/W3181758331","https://openalex.org/W3192009892","https://openalex.org/W3195026654","https://openalex.org/W3206064582","https://openalex.org/W4304099262","https://openalex.org/W4312238277","https://openalex.org/W4312938887","https://openalex.org/W6692846177","https://openalex.org/W6748848655","https://openalex.org/W6751885507","https://openalex.org/W6753516098","https://openalex.org/W6757724268","https://openalex.org/W6762521896","https://openalex.org/W6766904570","https://openalex.org/W6767279747","https://openalex.org/W6769627184","https://openalex.org/W6770783600","https://openalex.org/W6780226713","https://openalex.org/W6784287907","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6803039797"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"requires":[3],"that":[4],"an":[5],"agent":[6,42],"can":[7],"comprehensively":[8],"understand":[9],"the":[10,14,20,30,41,48,52,67,88,94,129,144,155,159,170,180,186,194,200],"given":[11],"instructions":[12],"and":[13,112,157,191],"immediate":[15],"visual":[16],"information":[17],"obtained":[18],"from":[19],"environment,":[21],"so":[22],"as":[23],"to":[24,28,86,123,134,163],"make":[25],"correct":[26],"actions":[27,161],"achieve":[29],"navigation":[31,49,71],"goal.":[32],"Therefore,":[33],"semantic":[34,55],"alignment":[35,56],"across":[36,139],"modalities":[37],"is":[38,132],"crucial":[39],"for":[40],"understanding":[43],"its":[44],"own":[45],"state":[46],"during":[47],"process.":[50],"However,":[51],"potential":[53],"of":[54,70,109,154,172],"has":[57],"not":[58],"been":[59],"systematically":[60],"explored":[61],"in":[62,93],"current":[63],"studies,":[64],"which":[65],"limits":[66],"further":[68],"improvement":[69],"performance.":[72],"To":[73],"address":[74],"this":[75,142],"issue,":[76],"we":[77,97,178],"propose":[78],"a":[79,151],"new":[80],"Latent":[81,145],"Semantic":[82,146],"Alignment":[83,147],"Learning":[84,148],"method":[85,149],"develop":[87],"semantically":[89,136],"aligned":[90],"relationships":[91],"contained":[92],"environment.":[95],"Specifically,":[96],"introduce":[98],"three":[99],"novel":[100],"pre-training":[101],"tasks:":[102],"Trajectory-conditioned":[103],"Masked":[104,110],"Fragment":[105],"Modeling,":[106],"Action":[107],"Prediction":[108],"Observation,":[111],"Hierarchical":[113],"Triple":[114],"Contrastive":[115],"Learning.":[116],"The":[117],"first":[118],"two":[119],"tasks":[120],"are":[121],"used":[122],"reason":[124],"about":[125],"cross-modal":[126],"dependencies,":[127],"while":[128],"third":[130],"one":[131],"able":[133],"learn":[135],"consistent":[137,152],"representations":[138],"modalities.":[140],"In":[141],"way,":[143],"establishes":[150],"perception":[153],"environment":[156],"makes":[158],"agent's":[160],"easier":[162],"explain.":[164],"Experiments":[165],"on":[166,185,193],"common":[167],"benchmarks":[168],"verify":[169],"effectiveness":[171],"our":[173],"proposed":[174],"methods.":[175],"For":[176],"example,":[177],"improve":[179],"Success":[181],"Rate":[182],"by":[183],"1.6%":[184],"R2R":[187],"validation":[188,196],"unseen":[189,197],"set":[190,198],"4.3%":[192],"R4R":[195],"over":[199],"baseline":[201],"model.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}