{"id":"https://openalex.org/W4405785171","doi":"https://doi.org/10.1109/iros58592.2024.10802709","title":"HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation","display_name":"HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785171","doi":"https://doi.org/10.1109/iros58592.2024.10802709"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5103004161","display_name":"Naoki Yokoyama","orcid":"https://orcid.org/0009-0002-2919-936X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoki Yokoyama","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065926101","display_name":"Ram Ramrakhya","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ram Ramrakhya","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102972112","display_name":"Abhishek Das","orcid":"https://orcid.org/0000-0002-4718-4316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhishek Das","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":"https://orcid.org/0000-0002-1358-0011"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064581452","display_name":"Sehoon Ha","orcid":"https://orcid.org/0000-0002-1972-328X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sehoon Ha","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5543","last_page":"5550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9901999831199646,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9901999831199646,"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/T10028","display_name":"Topic Modeling","score":0.9057000279426575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7996964454650879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7839984893798828},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5582947731018066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5441052913665771},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5120394825935364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39586949348449707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34922146797180176},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06647956371307373},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06028103828430176},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05798840522766113}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7996964454650879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839984893798828},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5582947731018066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5441052913665771},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5120394825935364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39586949348449707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34922146797180176},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06647956371307373},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06028103828430176},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05798840522766113},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2107667896","https://openalex.org/W2962887844","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2970641574","https://openalex.org/W3009928773","https://openalex.org/W3034201026","https://openalex.org/W3034578524","https://openalex.org/W3034728521","https://openalex.org/W3049043369","https://openalex.org/W3199020598","https://openalex.org/W3201759799","https://openalex.org/W3210395242","https://openalex.org/W3211462570","https://openalex.org/W4282981845","https://openalex.org/W4312707839","https://openalex.org/W4313180266","https://openalex.org/W4386075729","https://openalex.org/W4386075839","https://openalex.org/W4389422344","https://openalex.org/W4390873312","https://openalex.org/W4390874813","https://openalex.org/W4401417061","https://openalex.org/W4402753977","https://openalex.org/W4404612908","https://openalex.org/W6640174482","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6753516098","https://openalex.org/W6764655487","https://openalex.org/W6773029903","https://openalex.org/W6780167394","https://openalex.org/W6780443396","https://openalex.org/W6785121346","https://openalex.org/W6845716266","https://openalex.org/W6850481810","https://openalex.org/W6853781193"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"We":[0,130,162],"present":[1],"the":[2,17,30,73,158],"Habitat-Matterport":[3],"3D":[4,49],"Open":[5],"Vocabulary":[6],"Object":[7,24],"Goal":[8,25],"Navigation":[9,26],"dataset":[10],"(HM3D-OVON),":[11],"a":[12,65,191],"large-scale":[13],"benchmark":[14,166],"that":[15,102,132,143,164,177],"broadens":[16],"scope":[18],"and":[19,75,121,148,154,167,196,202],"semantic":[20,198],"range":[21],"of":[22,39,51,68,77,82,105,126],"prior":[23],"(ObjectNav)":[27],"benchmarks.":[28],"Leveraging":[29],"HM3DSem":[31],"dataset,":[32],"HM3D-OVON":[33,71,94,133],"incorporates":[34],"over":[35],"15k":[36],"annotated":[37],"instances":[38],"household":[40,184],"objects":[41,63,185],"across":[42],"379":[43],"distinct":[44],"categories,":[45,70],"derived":[46],"from":[47],"photo-realistic":[48],"scans":[50],"real-world":[52,180],"environments.":[53],"In":[54],"contrast":[55],"to":[56,64,137,152,182],"earlier":[57],"ObjectNav":[58,141,160],"datasets,":[59],"which":[60],"limit":[61],"goal":[62],"predefined":[66],"set":[67],"6-21":[69],"facilitates":[72],"training":[74],"evaluation":[76],"models":[78],"with":[79],"an":[80,114,139],"open-set":[81],"goals":[83],"defined":[84],"through":[85,187],"free-form":[86,188],"language":[87],"at":[88],"test-time.":[89],"Through":[90],"this":[91],"open-vocabulary":[92,115,140],"formulation,":[93],"encourages":[95],"progress":[96],"towards":[97,193],"learning":[98],"visuo-semantic":[99],"navigation":[100],"behaviors":[101],"are":[103],"capable":[104],"searching":[106],"for":[107],"any":[108],"object":[109],"specified":[110,186],"by":[111],"text":[112],"in":[113,173],"manner.":[116],"Additionally,":[117],"we":[118],"systematically":[119],"evaluate":[120],"compare":[122],"several":[123],"different":[124],"types":[125],"approaches":[127],"on":[128],"HM3D-OVON.":[129],"find":[131,183],"can":[134,178],"be":[135],"used":[136],"train":[138],"agent":[142],"achieves":[144],"both":[145],"higher":[146],"performance":[147],"is":[149],"more":[150,194],"robust":[151],"localization":[153],"actuation":[155],"noise":[156],"than":[157],"state-of-the-art":[159],"approach.":[161],"hope":[163],"our":[165],"baseline":[168],"results":[169],"will":[170],"drive":[171],"interest":[172],"developing":[174],"embodied":[175],"agents":[176],"navigate":[179],"spaces":[181],"language,":[189],"taking":[190],"step":[192],"flexible":[195],"human-like":[197],"visual":[199],"navigation.":[200],"Code":[201],"videos":[203],"available":[204],"at:":[205],"naoki.io/ovon.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}