{"id":"https://openalex.org/W4403791917","doi":"https://doi.org/10.1145/3664647.3681518","title":"Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigation","display_name":"Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791917","doi":"https://doi.org/10.1145/3664647.3681518"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5114112388","display_name":"Huilin Tian","orcid":null},"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":"Huilin Tian","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2154-4829","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112193133","display_name":"Jingke Meng","orcid":"https://orcid.org/0009-0003-9131-5808"},"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":"Jingke Meng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9131-5808","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050904","display_name":"Wei\u2010Shi Zheng","orcid":"https://orcid.org/0000-0001-8327-0003"},"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":"Wei-Shi Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University &amp; Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, &amp; Guangdong Provincial Key Laboratory of Information Security Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8327-0003","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University &amp; Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, &amp; Guangdong Provincial Key Laboratory of Information Security Technology, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049799619","display_name":"Yuan-Ming Li","orcid":null},"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":"Yuan-Ming Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-5914-5605","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102249848","display_name":"Junkai Yan","orcid":"https://orcid.org/0009-0009-6531-0070"},"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":"Junkai Yan","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-6531-0070","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053064477","display_name":"Yunong Zhang","orcid":"https://orcid.org/0000-0002-2228-0395"},"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":"Yunong Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2228-0395","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4073","last_page":"4081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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":0.983299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693630039691925},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5511155724525452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4611321985721588},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.382174551486969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693630039691925},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5511155724525452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611321985721588},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.382174551486969}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1566256432","https://openalex.org/W2117539524","https://openalex.org/W2146241755","https://openalex.org/W2558333741","https://openalex.org/W2636355936","https://openalex.org/W2926977875","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964343989","https://openalex.org/W2964935470","https://openalex.org/W2979727876","https://openalex.org/W3003391301","https://openalex.org/W3034500398","https://openalex.org/W3091588028","https://openalex.org/W3105521436","https://openalex.org/W3109097593","https://openalex.org/W3155707959","https://openalex.org/W3175443984","https://openalex.org/W3176974620","https://openalex.org/W4212980052","https://openalex.org/W4224329474","https://openalex.org/W4226052928","https://openalex.org/W4319299816","https://openalex.org/W4386075539","https://openalex.org/W4390873597","https://openalex.org/W4390874160","https://openalex.org/W4393147080","https://openalex.org/W4393154152","https://openalex.org/W4402904106"],"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":[0],"and":[1,15,184,263,275],"Language":[2],"Navigation":[3],"(VLN)":[4],"is":[5,32,161,216,226],"a":[6,21,105,137,169,178,185,207],"challenging":[7],"task":[8],"that":[9,210,279],"requires":[10],"agents":[11],"to":[12,17,56,107,113,145,162,192,205,241,254,258],"understand":[13],"instructions":[14],"navigate":[16],"the":[18,26,39,53,57,62,66,72,81,89,108,122,129,164,194,201,214,218,229,238,246,251,260,265,273,280,284],"destination":[19],"in":[20,29,71,128,152,200],"visual":[22,58,243],"environment.":[23],"One":[24],"of":[25,35,38,65,84,91,125,267],"key":[27],"challenges":[28],"outdoor":[30,92,153],"VLN":[31,154],"keeping":[33],"track":[34],"which":[36,176,225],"part":[37],"instruction":[40],"was":[41],"completed.":[42],"To":[43],"alleviate":[44],"this":[45,76,133,233],"problem,":[46],"previous":[47],"works":[48],"mainly":[49],"focus":[50],"on":[51,88,173,272],"grounding":[52,73,90],"natural":[54],"language":[55],"input,":[59],"but":[60],"neglecting":[61],"crucial":[63],"role":[64,124],"agent's":[67],"spatial":[68,85,126,147,165,180,198,256],"position":[69,86,208],"information":[70,257],"process.":[74,131],"In":[75,99,132],"work,":[77,134],"we":[78,135,203,236,249],"first":[79],"explore":[80],"substantial":[82],"effect":[83],"locating":[87,181,234,247],"VLN,":[93],"drawing":[94],"inspiration":[95],"from":[96,217],"human":[97],"navigation.":[98],"real-world":[100],"navigation":[101,130],"scenarios,":[102],"before":[103,141,167],"planning":[104,151,168,188],"path":[106],"destination,":[109],"humans":[110],"typically":[111],"need":[112],"figure":[114],"out":[115],"their":[116],"current":[117],"location.":[118],"This":[119],"observation":[120],"underscores":[121],"pivotal":[123],"localization":[127,166],"introduce":[136],"novel":[138],"framework,":[139],"Locating":[140],"Planning":[142],"(Loc4Plan),":[143],"designed":[144],"incorporate":[146,255],"perception":[148],"for":[149,221],"action":[150,171,187,268],"tasks.":[155],"The":[156],"main":[157],"idea":[158],"behind":[159],"Loc4Plan":[160,282],"perform":[163],"decision":[170],"based":[172],"corresponding":[174,261],"guidance,":[175],"comprises":[177],"block-aware":[179],"(BAL)":[182],"module":[183,240,253],"spatial-aware":[186],"(SAP)":[189],"module.":[190,231],"Specifically,":[191],"help":[193],"agent":[195,215],"perceive":[196],"its":[197,223],"location":[199],"environment,":[202],"propose":[204,237,250],"learn":[206],"predictor":[209],"measures":[211],"how":[212],"far":[213],"next":[219],"intersection":[220],"reflecting":[222],"position,":[224],"achieved":[227],"by":[228],"BAL":[230],"After":[232,245],"process,":[235,248],"PSA":[239],"associate":[242],"observations":[244],"SAP":[252],"ground":[259],"guidance":[262],"enhance":[264],"precision":[266],"planning.":[269],"Extensive":[270],"experiments":[271],"Touchdown":[274],"map2seq":[276],"datasets":[277],"show":[278],"proposed":[281],"outperforms":[283],"SOTA":[285],"methods.":[286]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
