{"id":"https://openalex.org/W4392903672","doi":"https://doi.org/10.1109/icassp48485.2024.10446850","title":"Graph-Based Environment Representation for Vision-and-Language Navigation in Continuous Environments","display_name":"Graph-Based Environment Representation for Vision-and-Language Navigation in Continuous Environments","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903672","doi":"https://doi.org/10.1109/icassp48485.2024.10446850"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100428005","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0003-2679-6556"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ting Wang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Westlake University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061590256","display_name":"Zongkai Wu","orcid":"https://orcid.org/0000-0001-8141-1108"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongkai Wu","raw_affiliation_strings":["Westlake University,Hangzhou,China","Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102710880","display_name":"Feiyu Yao","orcid":"https://orcid.org/0000-0002-1432-1644"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Yao","raw_affiliation_strings":["Huawei Technologies Co., Ltd,2012 Lab,Beijing,China","2012 Lab, Huawei Technologies Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd,2012 Lab,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Lab, Huawei Technologies Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665183","display_name":"Donglin Wang","orcid":"https://orcid.org/0000-0003-1359-6440"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Wang","raw_affiliation_strings":["Westlake University,Hangzhou,China","Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100428005"],"corresponding_institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.2662,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79522268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8331","last_page":"8335"},"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":0.9980000257492065,"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":0.8126243948936462},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.545756459236145},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5326945781707764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4484165906906128},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4410381317138672},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.42378729581832886},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4177822172641754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37784531712532043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32332003116607666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24234169721603394},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0727296769618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126243948936462},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.545756459236145},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5326945781707764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4484165906906128},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4410381317138672},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.42378729581832886},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4177822172641754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37784531712532043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32332003116607666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24234169721603394},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0727296769618988},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2953127211","https://openalex.org/W2962744691","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964935470","https://openalex.org/W3009928773","https://openalex.org/W3105966348","https://openalex.org/W3109085430","https://openalex.org/W3127526611","https://openalex.org/W3174887918","https://openalex.org/W3192009892","https://openalex.org/W3203338521","https://openalex.org/W3205276578","https://openalex.org/W3206064582","https://openalex.org/W3206064780","https://openalex.org/W3213722353","https://openalex.org/W4312253995","https://openalex.org/W4312618696","https://openalex.org/W4313130367","https://openalex.org/W4321649625","https://openalex.org/W4386065347","https://openalex.org/W6620707391","https://openalex.org/W6640212811","https://openalex.org/W6748555532","https://openalex.org/W6751885507","https://openalex.org/W6757724268","https://openalex.org/W6784287907","https://openalex.org/W6787340103","https://openalex.org/W6803123405","https://openalex.org/W6850485090"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W3205686722","https://openalex.org/W3196817267","https://openalex.org/W1976600725","https://openalex.org/W4392007279","https://openalex.org/W4387129494"],"abstract_inverted_index":{"The":[0],"Vision-and-Language":[1],"Navigation":[2],"in":[3,16,66,76,138],"Continuous":[4],"Environments":[5],"(VLN-CE)":[6],"task":[7],"requires":[8],"an":[9,54],"agent":[10],"to":[11,62,88,104],"follow":[12],"a":[13,17,47,90,110,123],"language":[14,39],"instruction":[15],"realistic":[18],"environment.":[19],"Understanding":[20],"the":[21,36,64,77,97,106,133],"environment":[22,49,65,107,120],"is":[23,116],"crucial,":[24],"yet":[25],"current":[26],"methods":[27],"are":[28,79],"relatively":[29],"simple":[30],"and":[31,41,74,122],"direct,":[32],"without":[33],"delving":[34],"into":[35],"interplay":[37],"between":[38],"instructions":[40],"visual":[42],"context.":[43],"Therefore,":[44],"we":[45,52,95],"propose":[46,53],"novel":[48],"representation.":[50,108],"First,":[51],"Environment":[55],"Representation":[56],"Graph":[57,82],"(ERG)":[58],"through":[59,81],"object":[60,101],"detection":[61],"express":[63],"semantic":[67],"level.":[68],"Then,":[69],"relational":[70],"representations":[71],"of":[72,135],"object-object":[73],"object-agent":[75],"ERG":[78,92,98,128],"learned":[80],"Convolution":[83],"Network":[84],"(GCN),":[85],"so":[86],"as":[87],"obtain":[89,105],"continuous":[91],"expression.":[93],"Sequentially,":[94],"combine":[96],"expression":[99],"with":[100],"label":[102],"embeddings":[103],"Finally,":[109],"new":[111],"cross-modal":[112],"attention":[113],"navigation":[114],"framework":[115],"proposed,":[117],"incorporating":[118],"our":[119,136],"representation":[121],"specialized":[124],"loss":[125],"function":[126],"for":[127],"training.":[129],"Experimental":[130],"results":[131],"demonstrate":[132],"effectiveness":[134],"approach":[137],"achieving":[139],"commendable":[140],"performance":[141],"on":[142],"VLN-CE":[143],"tasks.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}