{"id":"https://openalex.org/W4387968661","doi":"https://doi.org/10.1145/3581783.3611736","title":"Mind the Gap: Improving Success Rate of Vision-and-Language Navigation by Revisiting Oracle Success Routes","display_name":"Mind the Gap: Improving Success Rate of Vision-and-Language Navigation by Revisiting Oracle Success Routes","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968661","doi":"https://doi.org/10.1145/3581783.3611736"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5057733392","display_name":"Chongyang Zhao","orcid":"https://orcid.org/0000-0002-2942-1218"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chongyang Zhao","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2942-1218","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4312-5682","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4349","last_page":"4358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9975000023841858,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9789000153541565,"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/oracle","display_name":"Oracle","score":0.7975823879241943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7136878967285156},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6126030087471008},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5993468165397644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5608723759651184},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5289646983146667},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4938088357448578},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47321099042892456},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44185715913772583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38701295852661133},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15003198385238647}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7975823879241943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136878967285156},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6126030087471008},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5993468165397644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608723759651184},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5289646983146667},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4938088357448578},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47321099042892456},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44185715913772583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38701295852661133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15003198385238647},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2890502146","https://openalex.org/W2894280539","https://openalex.org/W2926977875","https://openalex.org/W2952132648","https://openalex.org/W2962869524","https://openalex.org/W2962914239","https://openalex.org/W2963095467","https://openalex.org/W2963351448","https://openalex.org/W2963393391","https://openalex.org/W2963843782","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2964339842","https://openalex.org/W3034500398","https://openalex.org/W3035339529","https://openalex.org/W3087365719","https://openalex.org/W3096609285","https://openalex.org/W3112077297","https://openalex.org/W3165915253","https://openalex.org/W3166712493","https://openalex.org/W3174887918","https://openalex.org/W3204090293","https://openalex.org/W3208883793","https://openalex.org/W3214642103","https://openalex.org/W4200630135","https://openalex.org/W4214490042","https://openalex.org/W4221167472","https://openalex.org/W4226052928","https://openalex.org/W4293329554","https://openalex.org/W4304097971","https://openalex.org/W4307929959","https://openalex.org/W4312434279","https://openalex.org/W4312581490","https://openalex.org/W4313591672","https://openalex.org/W4386065870","https://openalex.org/W6600213211","https://openalex.org/W6600548291","https://openalex.org/W6600553734","https://openalex.org/W6601048702","https://openalex.org/W6601250092","https://openalex.org/W6605584388","https://openalex.org/W6845827088"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2378211422","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"aims":[3],"to":[4,6,38,64,98,113,143],"navigate":[5],"the":[7,35,46,82,86,90,94,101,115,145,155,175],"target":[8,87,102,116,150],"location":[9,103,117,151],"by":[10,122],"following":[11],"a":[12,21,40,59,119,129,149],"given":[13,121],"instruction.":[14,156],"Unlike":[15],"existing":[16],"methods":[17,70],"focused":[18],"on":[19,66,162],"predicting":[20,108],"more":[22,178],"accurate":[23],"action":[24],"at":[25,100,104],"each":[26],"step":[27],"in":[28,30,43,154],"navigation,":[29],"this":[31],"paper,":[32],"we":[33,111,127],"make":[34],"first":[36],"attempt":[37],"tackle":[39],"long-ignored":[41],"problem":[42],"VLN:":[44],"narrowing":[45],"gap":[47,62],"between":[48],"Success":[49,54],"Rate":[50,55],"(SR)":[51],"and":[52,76,168,170],"Oracle":[53],"(OSR).":[56],"We":[57],"observe":[58],"consistently":[60],"large":[61],"(up":[63],"9%)":[65],"four":[67],"state-of-the-art":[68],"VLN":[69,124],"across":[71],"two":[72],"benchmark":[73],"datasets:":[74,165],"R2R":[75],"REVERIE.":[77],"The":[78,157],"high":[79],"OSR":[80],"indicates":[81],"robot":[83],"agent":[84,95],"passes":[85],"location,":[88],"while":[89],"low":[91],"SR":[92],"suggests":[93],"actually":[96],"fails":[97],"stop":[99],"last.":[105],"Instead":[106],"of":[107,147],"actions":[109],"directly,":[110],"propose":[112],"mine":[114],"from":[118],"trajectory":[120,137],"off-the-shelf":[123],"models.":[125],"Specially,":[126],"design":[128],"multi-module":[130],"transformer-based":[131],"model":[132],"for":[133,177],"learning":[134],"compact":[135],"discriminative":[136],"viewpoint":[138],"representation,":[139],"which":[140],"is":[141,160],"used":[142],"predict":[144],"confidence":[146],"being":[148],"as":[152],"described":[153],"proposed":[158],"method":[159],"evaluated":[161],"three":[163],"widely-adopted":[164],"R2R,":[166],"REVERIE":[167],"NDH,":[169],"shows":[171],"promising":[172],"results,":[173],"demonstrating":[174],"potential":[176],"future":[179],"research.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}