{"id":"https://openalex.org/W4412888614","doi":"https://doi.org/10.18653/v1/2025.findings-acl.341","title":"RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models","display_name":"RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888614","doi":"https://doi.org/10.18653/v1/2025.findings-acl.341"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.341","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.341","pdf_url":"https://aclanthology.org/2025.findings-acl.341.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.341.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100367667","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0003-0142-8634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641132","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0001-9620-5665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625354","display_name":"Kai L\u00fc","orcid":"https://orcid.org/0000-0002-6378-7002"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009868061","display_name":"Guokuan Li","orcid":"https://orcid.org/0009-0005-7998-5520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guokuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044866795","display_name":"Jiguang Wan","orcid":"https://orcid.org/0000-0003-3440-4460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiguang Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2409,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94420691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6564","last_page":"6574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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":0.9973000288009644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9959999918937683,"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/shot","display_name":"Shot (pellet)","score":0.6982681751251221},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6915419101715088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6469206213951111},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6315685510635376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5912944078445435},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5887141227722168},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4430687427520752},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4145858883857727},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10543191432952881}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6982681751251221},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6915419101715088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469206213951111},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6315685510635376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5912944078445435},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5887141227722168},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4430687427520752},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4145858883857727},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10543191432952881},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"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:10.18653/v1/2025.findings-acl.341","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.341","pdf_url":"https://aclanthology.org/2025.findings-acl.341.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.341","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.341","pdf_url":"https://aclanthology.org/2025.findings-acl.341.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3451530047","display_name":null,"funder_award_id":"2021B0101400003","funder_id":"https://openalex.org/F4320336405","funder_display_name":"Special Project for Research and Development in Key areas of Guangdong Province"},{"id":"https://openalex.org/G8489799302","display_name":null,"funder_award_id":"2023YFB4502701","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336405","display_name":"Special Project for Research and Development in Key areas of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888614.pdf","grobid_xml":"https://content.openalex.org/works/W4412888614.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Object":[0],"Navigation":[1],"(ObjectNav)":[2],"is":[3,38],"a":[4,49,71,76,109],"fundamental":[5],"task":[6],"in":[7,16,24],"embodied":[8],"artificial":[9],"intelligence.Although":[10],"significant":[11],"progress":[12],"has":[13],"been":[14],"made":[15],"semantic":[17],"map":[18],"construction":[19],"and":[20,29,56,59,82,102,114],"target":[21],"direction":[22,37],"prediction":[23],"current":[25],"research,":[26],"redundant":[27],"exploration":[28,30,43,54,57,84,88,103],"failures":[31],"remain":[32],"inevitable.A":[33],"critical":[34],"but":[35],"underexplored":[36],"the":[39,61,92,120,124],"timely":[40],"termination":[41],"of":[42,64,97,112,117],"to":[44],"overcome":[45],"these":[46],"challenges.We":[47],"observe":[48],"diminishing":[50],"marginal":[51],"effect":[52],"between":[53],"steps":[55],"rates":[58,104],"analyze":[60],"costbenefit":[62],"relationship":[63],"exploration.Inspired":[65],"by":[66],"this,":[67],"we":[68],"propose":[69],"RATE-Nav,":[70],"Region-Aware":[72],"Termination-Enhanced":[73],"method.It":[74],"includes":[75],"geometric":[77],"predictive":[78],"region":[79],"segmentation":[80],"algorithm":[81,86],"region-Based":[83],"estimation":[85],"for":[87],"rate":[89,111],"calculation.By":[90],"leveraging":[91],"visual":[93,98],"question":[94],"answering":[95],"capabilities":[96],"language":[99],"models":[100],"(VLMs)":[101],"enables":[105],"efficient":[106],"termination.RATE-Nav":[107],"achieves":[108],"success":[110],"67.8%":[113],"an":[115],"SPL":[116],"31.3%":[118],"on":[119,123],"HM3D":[121],"dataset.And":[122],"more":[125],"challenging":[126],"MP3D":[127],"dataset,":[128],"RATE-Nav":[129],"shows":[130],"approximately":[131],"10%":[132],"improvement":[133],"over":[134],"previous":[135],"zero-shot":[136],"methods.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}