{"id":"https://openalex.org/W7164855155","doi":"https://doi.org/10.1145/3805622.3810871","title":"Decision-Invariant Sim-to-Real Vision-and-Language Navigation with Pseudo-Panoramic Observations","display_name":"Decision-Invariant Sim-to-Real Vision-and-Language Navigation with Pseudo-Panoramic Observations","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164855155","doi":"https://doi.org/10.1145/3805622.3810871"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810871","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810871","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810871","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061738429","display_name":"Yuexiao Zheng","orcid":"https://orcid.org/0009-0007-1208-4220"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyu Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-1208-4220","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138681953","display_name":"Xumin Shen","orcid":"https://orcid.org/0009-0005-6731-8552"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xumin Shen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-6731-8552","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100526684","display_name":"Yunda Sun","orcid":"https://orcid.org/0009-0000-3926-540X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunda Sun","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-3926-540X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021739501","display_name":"Ying Shen","orcid":"https://orcid.org/0000-0002-2966-7955"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2966-7955","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351849","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0002-4360-5523"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China and IEIT SYSTEMS (Beijing) Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4360-5523","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China and IEIT SYSTEMS (Beijing) Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93967882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"902","last_page":"910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7764000296592712,"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":0.7764000296592712,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.10520000010728836,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.03629999980330467,"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/semantics","display_name":"Semantics (computer science)","score":0.6237000226974487},{"id":"https://openalex.org/keywords/waypoint","display_name":"Waypoint","score":0.5666000247001648},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.4575999975204468},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.3955000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995999813079834},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42980000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36579999327659607},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810871","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810871","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810871","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810871","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5966210961341858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2926977875","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W3009928773","https://openalex.org/W3109085430","https://openalex.org/W4226052928","https://openalex.org/W4312253995","https://openalex.org/W4312544224","https://openalex.org/W4312996039","https://openalex.org/W4390871755","https://openalex.org/W4393154152","https://openalex.org/W4394627367","https://openalex.org/W4402353981","https://openalex.org/W4402703032","https://openalex.org/W4402754062","https://openalex.org/W4408841099","https://openalex.org/W4414050442","https://openalex.org/W4414050622","https://openalex.org/W7133235210"],"related_works":[],"abstract_inverted_index":{"Following":[0],"natural":[1],"language":[2],"instructions":[3],"to":[4,24,53,105,110,126,168],"complete":[5,44],"navigation":[6,18,189],"tasks":[7],"is":[8],"a":[9,66,81,100,113,133,158],"crucial":[10],"capability":[11],"for":[12,33],"real-world":[13,91,122],"embodied":[14],"robots.":[15],"In":[16,60],"vision-and-language":[17],"(VLN),":[19],"agents":[20,164],"typically":[21],"assume":[22],"access":[23],"complete,":[25],"on-the-fly":[26],"environmental":[27],"observations":[28,78,96,154],"and":[29,57,76,84,90,151,180],"rely":[30],"on":[31],"them":[32],"decision":[34,129],"making.":[35],"However,":[36],"most":[37],"sim-to-real":[38,67,128,188],"VLN":[39,68],"approaches":[40],"approximate":[41],"the":[42,72,173],"privileged":[43],"panoramic":[45],"sensing":[46,83],"in":[47,145,166,172,178],"simulation":[48,167],"with":[49,121],"monocular":[50],"sensors,":[51],"leading":[52],"significant":[54],"semantic":[55,153],"loss":[56],"incomplete":[58],"perception.":[59],"this":[61],"work,":[62],"we":[63],"present":[64],"DIP2,":[65],"framework":[69],"that":[70,184],"reduces":[71],"discrepancy":[73],"between":[74],"assumed":[75],"realizable":[77],"by":[79],"introducing":[80],"unified":[82],"mapping":[85],"representation":[86],"shared":[87],"across":[88],"simulated":[89,118,179],"domains.":[92,147],"Specifically,":[93],"dense":[94,152],"pseudo-panoramic":[95],"are":[97,155],"synthesized":[98],"from":[99],"self-assembled":[101],"surround-view":[102],"camera":[103],"system":[104],"recover":[106],"rich":[107],"semantics":[108],"comparable":[109],"simulation,":[111],"while":[112],"structure-only":[114],"metric":[115],"map":[116],"unifies":[117],"RGB-D":[119],"inputs":[120],"LiDAR":[123],"observations.":[124],"Furthermore,":[125],"promote":[127],"invariance,":[130],"DIP2":[131,185],"employs":[132],"learning-free":[134],"local":[135],"navigable":[136],"waypoint":[137],"prediction":[138],"strategy":[139],"via":[140],"radial":[141],"expansion,":[142],"applied":[143],"consistently":[144],"both":[146],"The":[148],"predicted":[149],"waypoints":[150],"integrated":[156],"into":[157],"global":[159],"topological":[160],"map,":[161],"allowing":[162],"existing":[163],"trained":[165],"be":[169,194],"directly":[170],"deployed":[171],"real":[174,181],"world.":[175],"Extensive":[176],"experiments":[177],"environments":[182],"demonstrate":[183],"substantially":[186],"improves":[187],"performance.":[190],"Source":[191],"code":[192],"will":[193],"published":[195],"at":[196],"https://github.com/zheng19845/DIP2.":[197]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}