{"id":"https://openalex.org/W4416750034","doi":"https://doi.org/10.1109/iros60139.2025.11246600","title":"VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models","display_name":"VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750034","doi":"https://doi.org/10.1109/iros60139.2025.11246600"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5100641551","display_name":"Kui Wu","orcid":"https://orcid.org/0000-0003-3326-7943"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kui Wu","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033137793","display_name":"Shuxiang Xu","orcid":"https://orcid.org/0000-0003-0597-7040"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhang Xu","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353673","display_name":"Hao Chen","orcid":"https://orcid.org/0009-0001-6480-7976"},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["City University of Macau,China"],"affiliations":[{"raw_affiliation_string":"City University of Macau,China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011041316","display_name":"Churan Wang","orcid":"https://orcid.org/0000-0002-7699-0894"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Churan Wang","raw_affiliation_strings":["Peking University,School of Computer Science, Inst. for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Computer Science, Inst. for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036786337","display_name":"Zhoujun Li","orcid":"https://orcid.org/0000-0002-9603-9713"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoujun Li","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602394","display_name":"Yizhou Wang","orcid":"https://orcid.org/0000-0001-9692-6235"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Wang","raw_affiliation_strings":["Peking University,School of Computer Science, Inst. for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Computer Science, Inst. for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081893016","display_name":"Fangwei Zhong","orcid":"https://orcid.org/0000-0002-0428-4552"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangwei Zhong","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100641551"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91256437,"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":"13154","last_page":"13161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.531499981880188,"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":0.531499981880188,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.21330000460147858,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.0272000003606081,"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/active-vision","display_name":"Active vision","score":0.6266999840736389},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6176000237464905},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5778999924659729},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5317999720573425},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5174000263214111},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5085999965667725},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43209999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610999703407288},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021999716758728},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4593999981880188},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.4115000069141388},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2046715600","https://openalex.org/W2049046732","https://openalex.org/W2123762917","https://openalex.org/W2152669093","https://openalex.org/W2158827467","https://openalex.org/W2767011576","https://openalex.org/W2795166961","https://openalex.org/W2891670750","https://openalex.org/W2985275943","https://openalex.org/W3159890488","https://openalex.org/W4285216306","https://openalex.org/W4315815580","https://openalex.org/W4379409345","https://openalex.org/W4382240014","https://openalex.org/W4390874670","https://openalex.org/W4392172801","https://openalex.org/W4393972750","https://openalex.org/W4401417061","https://openalex.org/W4402353981","https://openalex.org/W4402716288","https://openalex.org/W4402944034","https://openalex.org/W4404970496"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,44,62],"novel":[3],"self-improving":[4],"framework":[5,60,94],"that":[6,66,136],"enhances":[7],"Embodied":[8],"Visual":[9],"Tracking":[10],"(EVT)":[11],"with":[12,39,92,100,106],"Vision-Language":[13],"Models":[14],"(VLMs)":[15],"to":[16,70,121],"address":[17],"the":[18,34,68,115],"limitations":[19,81],"of":[20,118],"current":[21],"active":[22,36],"visual":[23,46],"tracking":[24,29,37,50],"systems":[25],"in":[26,82,109,125,141],"recovering":[27],"from":[28,75],"failure.":[30],"Our":[31],"approach":[32],"combines":[33],"off-the-shelf":[35],"methods":[38,108],"VLMs\u2019":[40,80],"reasoning":[41,54,120],"capabilities,":[42],"deploying":[43],"fast":[45],"policy":[47],"for":[48,132],"normal":[49],"and":[51,104],"activating":[52],"VLM":[53,69],"only":[55],"upon":[56],"failure":[57,127],"detection.":[58],"The":[59],"features":[61],"memory-augmented":[63],"self-reflection":[64],"mechanism":[65],"enables":[67],"progressively":[71],"improve":[72],"by":[73,98],"learning":[74],"past":[76],"experiences,":[77],"effectively":[78],"addressing":[79],"3D":[83],"spatial":[84],"reasoning.":[85],"Experimental":[86],"results":[87],"demonstrate":[88],"significant":[89],"performance":[90],"improvements,":[91],"our":[93],"boosting":[95],"success":[96],"rates":[97],"72%":[99],"state-of-the-art":[101],"RL-based":[102],"approaches":[103],"220%":[105],"PID-based":[107],"challenging":[110],"environments.":[111,144],"This":[112],"work":[113],"represents":[114],"first":[116],"integration":[117],"VLM-based":[119],"assist":[122],"EVT":[123],"agents":[124],"proactive":[126],"recovery,":[128],"offering":[129],"substantial":[130],"advances":[131],"real-world":[133],"robotic":[134],"applications":[135],"require":[137],"continuous":[138],"target":[139],"monitoring":[140],"dynamic,":[142],"unstructured":[143],"Project":[145],"website:":[146],"https://sites.google.com/view/evt-recovery-assistant.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}