{"id":"https://openalex.org/W7128437391","doi":"https://doi.org/10.1109/lra.2026.3662560","title":"Agent as Student: Learning From Informative Cues for Active Open-Vocabulary Recognition","display_name":"Agent as Student: Learning From Informative Cues for Active Open-Vocabulary Recognition","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128437391","doi":"https://doi.org/10.1109/lra.2026.3662560"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3662560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3662560","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5104281019","display_name":"Ruizhe Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhe Zeng","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3513-2297","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125450578","display_name":"Lu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6240-5300","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125456192","display_name":"Xu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0553-4581","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125456512","display_name":"Zhiyong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2148-1846","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"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":0.15756995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"3","first_page":"3708","last_page":"3715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.40549999475479126,"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":0.40549999475479126,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.34689998626708984,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05009999871253967,"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/adaptation","display_name":"Adaptation (eye)","score":0.510699987411499},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4763999879360199},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4620000123977661},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.41200000047683716},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.40779998898506165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392999887466431},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27000001072883606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3662560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3662560","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5886667966842651}],"awards":[{"id":"https://openalex.org/G297044484","display_name":null,"funder_award_id":"62206288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2018629239","https://openalex.org/W2064675550","https://openalex.org/W2141559645","https://openalex.org/W2194775991","https://openalex.org/W2593769898","https://openalex.org/W2948672349","https://openalex.org/W2963306405","https://openalex.org/W2981900248","https://openalex.org/W3107575247","https://openalex.org/W3174156594","https://openalex.org/W4243970992","https://openalex.org/W4312291425","https://openalex.org/W4383108417","https://openalex.org/W4383108839","https://openalex.org/W4389665758","https://openalex.org/W4390873343","https://openalex.org/W4391547487","https://openalex.org/W4393158298","https://openalex.org/W4402715959","https://openalex.org/W4402727189","https://openalex.org/W4406142301","https://openalex.org/W4415797909","https://openalex.org/W4416748923"],"related_works":[],"abstract_inverted_index":{"Active":[0],"recognition,":[1],"a":[2,72,94,100,153],"fundamental":[3],"task":[4],"in":[5,51,71,125],"embodied":[6],"vision,":[7],"aims":[8],"to":[9,19,69,162],"improve":[10],"recognition":[11,32,53,64,180],"performance":[12,40,172],"by":[13,43,75],"dynamically":[14],"adjusting":[15],"viewpoints":[16],"and":[17,26,104,141,158],"poses":[18],"mitigate":[20],"the":[21,44,111,115],"negative":[22],"impacts":[23],"of":[24,47,79,114,173],"occlusion":[25],"blind":[27],"spots.":[28],"Although":[29],"existing":[30],"active":[31,52,62,165,178],"methods":[33],"possess":[34],"basic":[35],"viewpoint":[36],"adaptation":[37,145],"capabilities,":[38],"their":[39],"is":[41,120],"constrained":[42],"insufficient":[45],"exploitation":[46],"informative":[48,80],"cues":[49],"inherent":[50],"scenarios.":[54],"To":[55],"address":[56],"this":[57],"limitation,":[58],"we":[59,151],"propose":[60],"an":[61,130,143],"open-vocabulary":[63,166,179],"method":[65,175],"that":[66,98,135],"enables":[67],"agent":[68],"learn":[70],"student-like":[73],"manner":[74],"leveraging":[76],"two":[77],"types":[78],"cues.":[81],"The":[82,117],"first":[83],"type":[84,119],"involves":[85],"failure":[86,101,107],"experiences":[87],"from":[88,122],"previously":[89],"encountered":[90],"samples.":[91],"We":[92,128],"introduce":[93],"failure-driven":[95],"learning":[96],"mechanism":[97,146],"maintains":[99],"replay":[102],"buffer":[103],"strategically":[105],"replays":[106],"cases":[108],"based":[109],"on":[110],"current":[112,126],"competency":[113],"agent.":[116],"second":[118],"derived":[121],"high-quality":[123],"frames":[124,138],"tasks.":[127],"develop":[129],"adaptive":[131],"feature":[132],"fusion":[133],"module":[134],"treats":[136],"these":[137],"as":[139],"templates":[140],"incorporates":[142],"entropy-guided":[144],"for":[147],"online":[148],"finetuning.":[149],"Furthermore,":[150],"construct":[152],"benchmark":[154],"dataset":[155],"with":[156],"diverse":[157],"fine-grained":[159],"object":[160],"categories":[161],"comprehensively":[163],"evaluate":[164],"recognition.":[167],"Extensive":[168],"experiments":[169],"demonstrate":[170],"superior":[171],"our":[174],"across":[176],"multiple":[177],"benchmarks.":[181]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-10T00:00:00"}