{"id":"https://openalex.org/W4416749980","doi":"https://doi.org/10.1109/iros60139.2025.11247664","title":"Towards Efficient Image-goal Navigation: A Self-supervised Transformer-based Reinforcement Learning Approach","display_name":"Towards Efficient Image-goal Navigation: A Self-supervised Transformer-based Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749980","doi":"https://doi.org/10.1109/iros60139.2025.11247664"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5014935116","display_name":"Qizhen Weng","orcid":"https://orcid.org/0009-0004-6135-6227"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhen Weng","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105354654","display_name":"Jiaocheng Hu","orcid":"https://orcid.org/0009-0001-3062-3765"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaocheng Hu","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032593051","display_name":"Zhijie Wu","orcid":"https://orcid.org/0000-0003-2425-5836"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Wu","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100667117","display_name":"Xiangwei Zhu","orcid":"https://orcid.org/0000-0002-8956-0711"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangwei Zhu","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42615142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18482","last_page":"18488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8284000158309937,"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":0.8284000158309937,"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":0.0430000014603138,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.027899999171495438,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8101000189781189},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.605400025844574},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5622000098228455},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5320000052452087},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5130000114440918},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4544000029563904},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.37540000677108765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8101000189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261999845504761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607000231742859},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5622000098228455},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5170999765396118},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28299999237060547}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/F4320321160","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2898306786","https://openalex.org/W2951360122","https://openalex.org/W2962887844","https://openalex.org/W3001075632","https://openalex.org/W3034728521","https://openalex.org/W3046768359","https://openalex.org/W3120006980","https://openalex.org/W3203187896","https://openalex.org/W4312929500","https://openalex.org/W4313156423","https://openalex.org/W4383108519","https://openalex.org/W4386824909","https://openalex.org/W4390874813","https://openalex.org/W4401326209"],"related_works":[],"abstract_inverted_index":{"Image-goal":[0],"navigation":[1],"is":[2,119],"a":[3,15,99,115],"crucial":[4],"yet":[5],"challenging":[6],"task":[7],"that":[8],"requires":[9],"an":[10,20],"agent":[11],"to":[12,14,77,102,138],"navigate":[13],"goal":[16,71],"location":[17],"specified":[18],"by":[19,97],"image.":[21,72],"Modular":[22],"methods":[23,50],"decompose":[24],"the":[25,66,70,80,86,107,143],"problem":[26],"into":[27],"distinct":[28],"subtasks":[29],"and":[30,69,126,134,146,150],"often":[31],"involve":[32],"explicit":[33],"map":[34],"construction,":[35],"which":[36],"can":[37],"struggle":[38],"in":[39,85],"complex,":[40],"unstructured":[41],"environments.":[42],"In":[43,90],"contrast,":[44],"end-to-end":[45],"deep":[46],"reinforcement":[47],"learning":[48,125],"(DRL)-based":[49],"directly":[51],"output":[52],"actions":[53],"from":[54],"visual":[55],"input,":[56],"with":[57],"recent":[58],"improvements":[59],"focusing":[60],"on":[61],"enhancing":[62],"embedding":[63],"fusion":[64],"between":[65],"current":[67],"observation":[68],"However,":[73],"both":[74,122],"approaches":[75],"fail":[76],"fully":[78],"leverage":[79],"rich":[81],"temporal":[82],"relationships":[83],"present":[84],"agent\u2019s":[87,108],"visual-action":[88,109],"history.":[89],"this":[91,95],"paper,":[92],"we":[93],"address":[94],"limitation":[96],"employing":[98],"self-supervised":[100],"transformer":[101,118],"predict":[103],"masked":[104,123],"portions":[105],"of":[106],"embeddings.":[110],"To":[111],"promote":[112],"spatio-temporal":[113],"reasoning,":[114],"dual-attention":[116],"shared":[117],"utilized":[120],"for":[121],"representation":[124],"policy":[127],"generation.":[128],"Our":[129],"method":[130],"demonstrates":[131],"superior":[132],"performance":[133],"generalization":[135],"ability":[136],"compared":[137],"12":[139],"existing":[140],"baselines":[141],"across":[142],"Gibson,":[144],"MP3D,":[145],"HM3D":[147],"datasets.":[148],"Code":[149],"trained":[151],"models":[152],"are":[153],"available":[154],"at":[155],"https://github.com/hujch23/DaMVA.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}