{"id":"https://openalex.org/W4405785555","doi":"https://doi.org/10.1109/iros58592.2024.10803061","title":"Multiple Visual Features in Topological Map for Vision-and-Language Navigation","display_name":"Multiple Visual Features in Topological Map for Vision-and-Language Navigation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785555","doi":"https://doi.org/10.1109/iros58592.2024.10803061"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10803061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10803061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"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/A5100728392","display_name":"Ruonan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruonan Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055367753","display_name":"Ping Kong","orcid":"https://orcid.org/0000-0003-2843-8787"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Kong","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China,300350","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080634694","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0003-4600-7382"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2136,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85514213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7742","last_page":"7749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9873999953269958,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9873999953269958,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9664000272750854,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9577999711036682,"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":0.6768256425857544},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5666877031326294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5412539839744568},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.4806560277938843},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.42697012424468994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16515541076660156},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08887025713920593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6768256425857544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5666877031326294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5412539839744568},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4806560277938843},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.42697012424468994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16515541076660156},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08887025713920593},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10803061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10803061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330487","display_name":"State Key Laboratory of Reliability and Intelligence of Electrical Equipment","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2926977875","https://openalex.org/W2951973805","https://openalex.org/W2962946204","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2970231061","https://openalex.org/W2981836239","https://openalex.org/W3009928773","https://openalex.org/W3034728521","https://openalex.org/W3100923070","https://openalex.org/W3109085430","https://openalex.org/W3109097593","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3176974620","https://openalex.org/W3195026654","https://openalex.org/W3203338521","https://openalex.org/W3206064582","https://openalex.org/W3206064780","https://openalex.org/W4226052928","https://openalex.org/W4304097971","https://openalex.org/W4312253995","https://openalex.org/W4312434279","https://openalex.org/W4312501707","https://openalex.org/W4312544224","https://openalex.org/W4312729859","https://openalex.org/W4312996039","https://openalex.org/W4313591672","https://openalex.org/W4385245566","https://openalex.org/W4386065347","https://openalex.org/W4390872665","https://openalex.org/W4390872901","https://openalex.org/W4390873167","https://openalex.org/W4394627367","https://openalex.org/W6748848655","https://openalex.org/W6751885507","https://openalex.org/W6753516098","https://openalex.org/W6755207826","https://openalex.org/W6757724268","https://openalex.org/W6766978945","https://openalex.org/W6773029903","https://openalex.org/W6780443396","https://openalex.org/W6785803027","https://openalex.org/W6791353385","https://openalex.org/W6798225807","https://openalex.org/W6798350552","https://openalex.org/W6810940169","https://openalex.org/W6846113813"],"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":{"Vision-and-Language":[0],"Navigation":[1,158],"(VLN)":[2],"in":[3,11,78,95,106,154],"continuous":[4,72],"environments":[5,13],"aims":[6],"to":[7,31,88,111,123],"navigate":[8],"robot":[9],"agents":[10],"unseen":[12],"following":[14],"natural":[15],"language":[16],"instructions.":[17],"The":[18],"majority":[19],"of":[20,41,133,156,166,175],"existing":[21],"approaches":[22],"rely":[23],"on":[24,140],"constructing":[25],"semantic":[26,35,176],"maps":[27,30,36,52],"or":[28],"topological":[29,51,99],"record":[32],"information.":[33],"However,":[34],"overlook":[37],"the":[38,44,54,96,107,121,125,131,141,150,157,164,172],"detailed":[39],"information":[40],"objects":[42],"and":[43,136],"correspondence":[45],"among":[46],"views":[47],"during":[48],"navigation,":[49],"while":[50],"lack":[53],"spatial":[55],"representation":[56,69],"between":[57],"entities.":[58],"To":[59],"address":[60],"these":[61],"limitations,":[62],"we":[63],"propose":[64],"a":[65,113,117],"novel":[66],"visual":[67,86,90,168],"feature":[68],"method":[70,148],"for":[71],"VLN,":[73],"called":[74],"Multiple":[75],"Visual":[76],"Features":[77],"Topological":[79],"Map":[80],"(MV-Topo).":[81],"MV-Topo":[82],"utilizes":[83],"three":[84],"distinct":[85],"encoders":[87],"extract":[89],"features,":[91],"which":[92],"are":[93],"integrated":[94],"dynamically":[97],"generated":[98],"map.":[100],"These":[101],"fused":[102],"features":[103,169],"actively":[104],"participate":[105],"subsequent":[108],"cross-modal":[109],"planning":[110],"derive":[112],"long-term":[114],"path":[115],"towards":[116],"subgoal,":[118],"effectively":[119],"guiding":[120],"agent":[122],"reach":[124],"final":[126],"location.":[127],"We":[128],"experimentally":[129],"demonstrate":[130],"effectiveness":[132],"our":[134,147],"approach":[135],"achieve":[137],"competitive":[138],"results":[139],"full":[142],"VLN-CE":[143],"test":[144],"splits.":[145],"Notably,":[146],"outperforms":[149],"state-of-the-art":[151],"by":[152],"3.5%":[153],"terms":[155],"Error":[159],"(NE)":[160],"metric,":[161],"indicating":[162],"that":[163],"utilization":[165],"multiple":[167],"significantly":[170],"enhances":[171],"agent\u2019s":[173],"perception":[174],"targets.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}