{"id":"https://openalex.org/W7123345751","doi":"https://doi.org/10.1109/tcsvt.2026.3651752","title":"SceneReasoner: Sufficient Embodied Scene Understanding From Limited Perception by Explicit Functional Association","display_name":"SceneReasoner: Sufficient Embodied Scene Understanding From Limited Perception by Explicit Functional Association","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123345751","doi":"https://doi.org/10.1109/tcsvt.2026.3651752"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3651752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3651752","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","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/A5009400940","display_name":"Xiukun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiukun Liu","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0002-0229-4543","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102803916","display_name":"Ning Lan","orcid":"https://orcid.org/0009-0005-3584-8540"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Lan","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0005-3584-8540","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingjie Wei","orcid":"https://orcid.org/0009-0008-5301-3274"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Wei","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0008-5301-3274","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuemei Xie","orcid":"https://orcid.org/0000-0001-7857-0845"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemei Xie","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-7857-0845","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guangming Shi","orcid":"https://orcid.org/0000-0003-2179-3292"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Shi","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0003-2179-3292","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009400940"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05990735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6456","last_page":"6471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.820900022983551,"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":0.820900022983551,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.042899999767541885,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02669999934732914,"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/interpretability","display_name":"Interpretability","score":0.7814000248908997},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7027999758720398},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.6840999722480774},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6606000065803528},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5674999952316284},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.5637000203132629},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.5156999826431274},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43950000405311584}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7814000248908997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253999710083008},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7027999758720398},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6606000065803528},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.5637000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321000218391418},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C13655849","wikidata":"https://www.wikidata.org/wiki/Q25294","display_name":"Hammer","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3651752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3651752","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G777008584","display_name":null,"funder_award_id":"2024ZD1300700","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sufficient":[0],"embodied":[1,9],"scene":[2,47,94,110,208,232,252,274,286],"understanding":[3,22,111,253,275],"serves":[4],"as":[5],"the":[6,43,90,93,105,148,161,164,174,204,207,211,217,231,245],"foundation":[7],"for":[8,187],"agents":[10],"to":[11,56,60,88,107,126,214,240],"perceive,":[12],"interpret,":[13],"and":[14,68,153,171,185,221,224,254,285],"solve":[15,256],"scene-related":[16,257],"questions":[17],"in":[18,42,115,138,143,166,194,199,206,230],"a":[19,116,139,144,151,183,195,200,227,236,250],"scene.":[20,140,196],"Such":[21],"is":[23,49,209],"often":[24],"constrained":[25],"by":[26,71,283,289],"limited":[27,113,277],"perception,":[28],"which":[29,80],"can":[30,158,247,270],"be":[31],"summarized":[32],"into":[33],"two":[34,131],"aspects:":[35],"(1)":[36,133],"The":[37,46],"lack":[38],"of":[39,92,136,163,176,192],"perceptual":[40,281],"abilities":[41],"agent.":[44],"(2)":[45,190],"itself":[48],"incomplete.":[50],"Existing":[51],"large":[52],"models-based":[53],"methods":[54],"attempt":[55],"leverage":[57],"implicit":[58],"knowledge":[59,124],"overcome":[61],"these":[62],"limitations,":[63],"but":[64],"this":[65,167],"lacks":[66],"interpretability":[67],"controllability.":[69],"Inspired":[70],"human":[72],"explainable":[73],"associative":[74,84,123],"thinking,":[75],"we":[76],"propose":[77],"SceneReasoner":[78,120],"framework,":[79],"imposes":[81],"explicit":[82,242,264],"functional":[83,100,243,268],"rules":[85,129],"on":[86],"LLMs":[87],"guide":[89],"process":[91],"understanding.":[95],"This":[96],"framework":[97],"mines":[98],"deeper":[99],"relationships":[101],"between":[102],"objects,":[103,156],"enabling":[104],"agent":[106,149,212,246],"gain":[108],"sufficient":[109,251],"from":[112,130],"perception":[114],"controllable":[117],"manner.":[118],"Specifically,":[119],"employs":[121],"an":[122],"base":[125],"provide":[127],"such":[128,241,263],"aspects.":[132],"Functional":[134],"complementarity":[135],"objects":[137,179,193],"For":[141,197],"instance,":[142],"computer":[145],"workspace,":[146],"if":[147],"perceives":[150],"monitor":[152,165],"other":[154,177,293],"unclear":[155],"it":[157],"first":[159,215],"analyze":[160],"function":[162],"area":[168],"(content":[169],"display),":[170],"then":[172,225],"infer":[173],"presence":[175],"related":[178],"(<italic":[180,233],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[181,234],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g.</i>,":[182,235],"mouse":[184],"keyboard":[186],"content":[188],"input).":[189],"Commonality":[191],"example,":[198],"picture-hanging":[201],"task,":[202],"when":[203],"hammer":[205],"missing,":[210],"needs":[213],"identify":[216],"hammer\u2019s":[218],"attributes":[219],"(hard":[220],"applying":[222],"force),":[223],"associate":[226],"suitable":[228],"substitute":[229],"hard":[237],"wrench).":[238],"Due":[239],"association,":[244],"rapidly":[248],"form":[249],"effectively":[255],"questions.":[258],"Experimental":[259],"results":[260],"demonstrate":[261],"that":[262],"association":[265],"augmented":[266],"with":[267,292],"reasoning":[269,287],"significantly":[271],"enhance":[272],"agents\u2019":[273],"under":[276],"perception.":[278],"It":[279],"improves":[280],"quality":[282],"9.75%":[284],"ability":[288],"21.42%":[290],"compared":[291],"methods.":[294]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-01-14T00:00:00"}