{"id":"https://openalex.org/W4415317215","doi":"https://doi.org/10.1109/iccv51701.2025.00797","title":"DialNav: Multi-Turn Dialog Navigation with a Remote Guide","display_name":"DialNav: Multi-Turn Dialog Navigation with a Remote Guide","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415317215","doi":"https://doi.org/10.1109/iccv51701.2025.00797"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101853484","display_name":"Li Han","orcid":"https://orcid.org/0000-0002-1294-4581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leekyeung Han","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyunji Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunji Min","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120050067","display_name":"Gyeom Hwangbo","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyeom Hwangbo","raw_affiliation_strings":["University of Seoul"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112425448","display_name":"Jonghyun Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonghyun Choi","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051808590","display_name":"Paul Hongsuck Seo","orcid":"https://orcid.org/0000-0002-6747-1101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Hongsuck Seo","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.25164075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8514","last_page":"8523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9693999886512756,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/dialog-box","display_name":"Dialog box","score":0.9197999835014343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6668000221252441},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6527000069618225},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5756999850273132},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5625},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4424999952316284}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9197999835014343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400000095367432},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6604999899864197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5756999850273132},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26429998874664307}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.12894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12894","pdf_url":"https://arxiv.org/pdf/2509.12894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.12894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12894","pdf_url":"https://arxiv.org/pdf/2509.12894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8102855944","display_name":null,"funder_award_id":"IITP-2025-RS-2020-II201819,IITP-2025-RS-2024-00436857,RS-202400398115,IITP-2025-RS-2025-02263754,IITP-2025-RS-2025-02304828,RS-2021-II212068","funder_id":"https://openalex.org/F4320319144","funder_display_name":"Indian Institute of Technology, Patna"}],"funders":[{"id":"https://openalex.org/F4320319144","display_name":"Indian Institute of Technology, Patna","ror":"https://ror.org/01ft5vz71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,75,99],"introduce":[1],"DialNav,":[2],"a":[3,10,15,25,77],"novel":[4],"collaborative":[5],"embodied":[6,117],"dialog":[7,22,67],"task,":[8,54],"where":[9],"navigation":[11,70,83],"agent":[12],"(Navigator)":[13],"and":[14,36,57,84,86,96,103,109],"remote":[16],"guide":[17],"(Guide)":[18],"engage":[19],"in":[20,62,72,116],"multi-turn":[21],"to":[23,40,80,112],"reach":[24],"goal":[26],"location.":[27],"Unlike":[28],"prior":[29],"work,":[30],"DialNav":[31],"aims":[32],"for":[33,48],"holistic":[34],"evaluation":[35,110],"requires":[37],"the":[38,42,59,91,106],"Guide":[39,97],"infer":[41],"Navigator's":[43],"location,":[44],"making":[45],"communication":[46],"essential":[47],"task":[49],"success.":[50],"To":[51],"support":[52],"this":[53],"we":[55],"collect":[56],"release":[58,105],"Remote":[60],"Assistance":[61],"Navigation":[63],"(RAIN)":[64],"dataset,":[65,107],"human-human":[66],"paired":[68],"with":[69],"trajectories":[71],"photorealistic":[73],"environments.":[74],"design":[76],"comprehensive":[78],"benchmark":[79],"evaluate":[81],"both":[82],"dialog,":[85],"conduct":[87],"extensive":[88],"experiments":[89],"analyzing":[90],"impact":[92],"of":[93],"different":[94],"Navigator":[95],"models.":[98],"highlight":[100],"key":[101],"challenges":[102],"publicly":[104],"code,":[108],"framework":[111],"foster":[113],"future":[114],"research":[115],"dialog.":[118]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-18T00:00:00"}
