{"id":"https://openalex.org/W4416213879","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228883","title":"Seeing is Believing? Enhancing Vision-Language Navigation using Visual Perturbations","display_name":"Seeing is Believing? Enhancing Vision-Language Navigation using Visual Perturbations","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416213879","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228883"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5027777954","display_name":"Xuesong Zhang","orcid":"https://orcid.org/0000-0001-6256-9997"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuesong Zhang","raw_affiliation_strings":["Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019391894","display_name":"Jia Li","orcid":"https://orcid.org/0000-0001-9446-249X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385467","display_name":"Yunbo Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Xu","raw_affiliation_strings":["Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040235604","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-1042-8361"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029727770","display_name":"Richang Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,The School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027777954"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34039874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9768000245094299,"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":0.9768000245094299,"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":0.0019000000320374966,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00139999995008111,"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/visualization","display_name":"Visualization","score":0.6151000261306763},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5471000075340271},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4830999970436096},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40459999442100525},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3917999863624573},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.38199999928474426},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009999752044678},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6151000261306763},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5444999933242798},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4645000100135803},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40459999442100525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2950697717","https://openalex.org/W2962735233","https://openalex.org/W2963800628","https://openalex.org/W2964343989","https://openalex.org/W2970231061","https://openalex.org/W3034578524","https://openalex.org/W3034758614","https://openalex.org/W3034984114","https://openalex.org/W3035561630","https://openalex.org/W3094502228","https://openalex.org/W3152079230","https://openalex.org/W3174887918","https://openalex.org/W3176974620","https://openalex.org/W3192009892","https://openalex.org/W4226052928","https://openalex.org/W4312544224","https://openalex.org/W4312938887","https://openalex.org/W4313591672","https://openalex.org/W4382240593","https://openalex.org/W4382466814","https://openalex.org/W4385768138","https://openalex.org/W4386065508","https://openalex.org/W4389009553","https://openalex.org/W4389523832","https://openalex.org/W4390871755","https://openalex.org/W4390872665","https://openalex.org/W4399198074","https://openalex.org/W4402727020","https://openalex.org/W4402733575","https://openalex.org/W4402754062","https://openalex.org/W4404523505"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"navigation":[1,15],"guided":[2],"by":[3,69,106],"natural":[4],"language":[5],"instructions":[6],"in":[7,21,47],"embodied":[8],"environments":[9,68],"remains":[10],"a":[11,112,135,139,146],"challenge":[12],"for":[13],"vision-language":[14,49],"(VLN)":[16],"agents.":[17,160],"Although":[18],"recent":[19],"advancements":[20],"learning":[22],"diverse":[23],"and":[24,84,128],"fine-grained":[25],"visual":[26,42,64,74,98,129,148,176],"environmental":[27],"representations":[28],"have":[29],"shown":[30],"promise,":[31],"the":[32,63,102,121,125],"fragile":[33],"performance":[34],"improvements":[35],"may":[36],"not":[37],"conclusively":[38],"attribute":[39],"to":[40,118,157],"enhanced":[41],"grounding\u2014a":[43],"limitation":[44],"also":[45],"observed":[46],"related":[48],"tasks.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,88,109],"preliminarily":[55],"investigate":[56],"whether":[57],"advanced":[58],"VLN":[59,159,165],"models":[60],"genuinely":[61],"comprehend":[62],"content":[65],"of":[66,73,123],"their":[67],"introducing":[70],"varying":[71],"levels":[72],"perturbations.":[75],"These":[76],"perturbations":[77],"include":[78],"ground-truth":[79],"depth":[80],"images,":[81],"perturbed":[82],"views":[83],"random":[85],"noise.":[86],"Surprisingly,":[87],"experimentally":[89],"find":[90],"that":[91,171],"simple":[92,154],"branch":[93,126,144],"expansion,":[94],"even":[95,180],"with":[96,174],"noisy":[97],"inputs,":[99],"paradoxically":[100],"improves":[101],"navigational":[103],"efficacy.":[104],"Inspired":[105],"these":[107],"insights,":[108],"further":[110],"present":[111],"versatile":[113],"Multi-Branch":[114],"Architecture":[115],"(MBA)":[116],"designed":[117],"delve":[119],"into":[120,138],"impact":[122],"both":[124],"quantity":[127],"quality.":[130],"The":[131,184],"proposed":[132],"MBA":[133],"extends":[134],"base":[136],"agent":[137],"multi-branch":[140],"variant,":[141],"where":[142],"each":[143],"processes":[145],"different":[147],"input.":[149],"This":[150],"approach":[151],"is":[152,187],"embarrassingly":[153],"yet":[155],"agnostic":[156],"topology-based":[158],"Extensive":[161],"experiments":[162],"on":[163],"three":[164],"benchmarks":[166],"(R2R,":[167],"REVERIE,":[168],"SOON)":[169],"demonstrate":[170],"our":[172],"method":[173],"optimal":[175],"permutations":[177],"matches":[178],"or":[179],"surpasses":[181],"state-of-the-art":[182],"results.":[183],"source":[185],"code":[186],"available":[188],"at":[189],"here.":[190]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}