{"id":"https://openalex.org/W4407246966","doi":"https://doi.org/10.1109/tcsvt.2025.3538860","title":"Visual Environment-Interactive Planning for Embodied Complex-Question Answering","display_name":"Visual Environment-Interactive Planning for Embodied Complex-Question Answering","publication_year":2025,"publication_date":"2025-02-07","ids":{"openalex":"https://openalex.org/W4407246966","doi":"https://doi.org/10.1109/tcsvt.2025.3538860"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3538860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3538860","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.00775","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"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":"https://openalex.org/A5116188638","display_name":"Baoshan Ou","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":false,"raw_author_name":"Baoshan Ou","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"],"raw_orcid":null,"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/A5100458706","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":"https://openalex.org/A5101549504","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":4,"corresponding_author_ids":["https://openalex.org/A5102803916"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":3.0311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86785784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"35","issue":"7","first_page":"6481","last_page":"6493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10636","display_name":"Innovative Teaching and Learning Methods","score":0.8454999923706055,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10636","display_name":"Innovative Teaching and Learning Methods","score":0.8454999923706055,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T14236","display_name":"Educational Tools and Methods","score":0.7850000262260437,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7652999758720398,"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/question-answering","display_name":"Question answering","score":0.7492298483848572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7298275232315063},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7029961943626404},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4513671398162842},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4295569658279419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34903639554977417},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33079203963279724}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7492298483848572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7298275232315063},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7029961943626404},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4513671398162842},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4295569658279419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34903639554977417},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33079203963279724}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3538860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3538860","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"},{"id":"pmh:oai:arXiv.org:2504.00775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00775","pdf_url":"https://arxiv.org/pdf/2504.00775","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.00775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00775","pdf_url":"https://arxiv.org/pdf/2504.00775","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2930283066","https://openalex.org/W2950697717","https://openalex.org/W2962684798","https://openalex.org/W2995933538","https://openalex.org/W3039925688","https://openalex.org/W3108503467","https://openalex.org/W3122490299","https://openalex.org/W3192660112","https://openalex.org/W4207072548","https://openalex.org/W4221143046","https://openalex.org/W4297903107","https://openalex.org/W4313427326","https://openalex.org/W4322704425","https://openalex.org/W4382657797","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4387624022","https://openalex.org/W4388720459","https://openalex.org/W4390707165","https://openalex.org/W4396941553","https://openalex.org/W4399177289","https://openalex.org/W4401414087","https://openalex.org/W4402353987","https://openalex.org/W4402354038","https://openalex.org/W4402776116","https://openalex.org/W4403307161","https://openalex.org/W4405785004","https://openalex.org/W4411119815","https://openalex.org/W6756121852","https://openalex.org/W6800673378","https://openalex.org/W6809509765","https://openalex.org/W6839928859","https://openalex.org/W6846254642","https://openalex.org/W6850886341","https://openalex.org/W6852136651","https://openalex.org/W6854164357","https://openalex.org/W6855965637","https://openalex.org/W6857220666","https://openalex.org/W6859757029","https://openalex.org/W6860199513","https://openalex.org/W6863120303","https://openalex.org/W6869701673"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W1570928019"],"abstract_inverted_index":{"This":[0,120,189],"study":[1],"focuses":[2],"on":[3,35,62,137,166,174,227],"Embodied":[4],"Complex-Question":[5],"Answering":[6],"task,":[7],"which":[8,143],"means":[9],"the":[10,36,39,69,74,90,113,128,146,149,164,197,232],"embodied":[11],"robot":[12,198],"need":[13],"to":[14,95,156,199],"understand":[15],"human":[16,133],"questions":[17],"with":[18,179,213],"intricate":[19],"structures":[20],"and":[21,109,194,225],"abstract":[22],"semantics.":[23],"The":[24],"core":[25],"of":[26,38,68,92,112,148,182,234],"this":[27,86],"task":[28,124],"lies":[29],"in":[30,47,79,85,237],"making":[31],"appropriate":[32],"plans":[33,46,78],"based":[34,136,173],"perception":[37,108],"visual":[40,107,139,177],"environment.":[41,70],"Existing":[42],"methods":[43],"often":[44],"generate":[45],"a":[48,80,101,138,158,210],"once-for-all":[49],"manner,":[50],"<inline-formula":[51],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[52],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[53],"<tex-math":[54],"notation=\"LaTeX\">$i.e$":[55],"</tex-math></inline-formula>.,":[56],"one-step":[57],"planning.":[58],"Such":[59],"approach":[60,190,222,236],"rely":[61],"large":[63,167],"models,":[64],"without":[65],"sufficient":[66],"understanding":[67],"Considering":[71],"multi-step":[72],"planning,":[73],"framework":[75,94],"for":[76,160],"formulating":[77],"sequential":[81,123],"manner":[82],"is":[83,171,187],"proposed":[84],"paper.":[87],"To":[88,204],"ensure":[89],"ability":[91],"our":[93,206,221,235],"tackle":[96],"complex":[97,215,228],"questions,":[98],"we":[99,130,152,208],"create":[100],"structured":[102],"semantic":[103],"space,":[104],"where":[105],"hierarchical":[106,140],"chain":[110],"expression":[111],"question":[114],"essence":[115],"can":[116,144],"achieve":[117],"iterative":[118],"interaction.":[119],"space":[121],"makes":[122],"planning":[125],"possible.":[126],"Within":[127],"framework,":[129,207],"first":[131],"parse":[132],"natural":[134],"language":[135],"scene":[141],"graph,":[142],"clarify":[145],"intention":[147],"question.":[150],"Then,":[151],"incorporate":[153],"external":[154],"rules":[155],"make":[157],"plan":[159,170],"current":[161],"step,":[162],"weakening":[163],"reliance":[165],"models.":[168],"Every":[169],"generated":[172],"feedback":[175,193],"from":[176],"perception,":[178],"multiple":[180],"rounds":[181],"interaction":[183],"until":[184],"an":[185],"answer":[186],"obtained.":[188],"enables":[191],"continuous":[192],"adjustment,":[195],"allowing":[196],"optimize":[200],"its":[201,244],"action":[202],"strategy.":[203],"test":[205],"contribute":[209],"new":[211],"dataset":[212],"more":[214],"questions.":[216],"Experimental":[217],"results":[218],"demonstrate":[219],"that":[220],"performs":[223],"excellently":[224],"stably":[226],"tasks.":[229],"And":[230],"also,":[231],"feasibility":[233],"real-world":[238],"scenarios":[239],"has":[240],"been":[241],"established,":[242],"indicating":[243],"practical":[245],"applicability.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}