{"id":"https://openalex.org/W4414271340","doi":"https://doi.org/10.1109/tmm.2025.3607747","title":"Detailed Object Description With Controllable Dimensions","display_name":"Detailed Object Description With Controllable Dimensions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414271340","doi":"https://doi.org/10.1109/tmm.2025.3607747"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3607747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607747","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5082142463","display_name":"Xinran Wang","orcid":"https://orcid.org/0000-0001-8793-2174"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinran Wang","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8793-2174","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiwen Zhang","orcid":"https://orcid.org/0009-0003-0522-2083"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwen Zhang","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0522-2083","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081025967","display_name":"Bin Li","orcid":"https://orcid.org/0000-0001-9341-4672"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoteng Li","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077313814","display_name":"Kongming Liang","orcid":"https://orcid.org/0000-0002-4726-093X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongming Liang","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4726-093X","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063142903","display_name":"Hao Sun","orcid":"https://orcid.org/0009-0007-7917-1628"},"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"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["China Telecom Artificial Intelligence Technology Company Ltd., Beijing, China","China Telecom Artificial Intelligence Technology Co. Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Artificial Intelligence Technology Company Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"China Telecom Artificial Intelligence Technology Co. Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722779","display_name":"Zhongjiang He","orcid":"https://orcid.org/0009-0000-1835-9271"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Guo","orcid":"https://orcid.org/0000-0001-9045-1339"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Guo","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9045-1339","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.11638865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"8474","last_page":"8485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9456999897956848,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9456999897956848,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9326000213623047,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9264000058174133,"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/dimension","display_name":"Dimension (graph theory)","score":0.7662000060081482},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7508000135421753},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6879000067710876},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6262000203132629},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49129998683929443},{"id":"https://openalex.org/keywords/method","display_name":"Method","score":0.45660001039505005},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44780001044273376},{"id":"https://openalex.org/keywords/object-oriented-design","display_name":"Object-oriented design","score":0.4271000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734999895095825},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7662000060081482},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7508000135421753},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6879000067710876},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6262000203132629},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49129998683929443},{"id":"https://openalex.org/C512554520","wikidata":"https://www.wikidata.org/wiki/Q815844","display_name":"Method","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4544999897480011},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C53073257","wikidata":"https://www.wikidata.org/wiki/Q7075021","display_name":"Object-oriented design","level":3,"score":0.4271000027656555},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.41190001368522644},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C154526789","wikidata":"https://www.wikidata.org/wiki/Q157965","display_name":"Object code","level":4,"score":0.2994999885559082},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3607747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607747","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G172479822","display_name":null,"funder_award_id":"62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5612663533","display_name":null,"funder_award_id":"62476029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8677236040","display_name":null,"funder_award_id":"U23B2052","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"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2098411764","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2520762063","https://openalex.org/W2806457960","https://openalex.org/W2886641317","https://openalex.org/W2890718122","https://openalex.org/W2901988662","https://openalex.org/W2952122856","https://openalex.org/W2954841306","https://openalex.org/W2963062932","https://openalex.org/W2963758027","https://openalex.org/W2984138079","https://openalex.org/W3005983418","https://openalex.org/W3034984754","https://openalex.org/W3045147787","https://openalex.org/W3094502228","https://openalex.org/W3153469116","https://openalex.org/W3170494780","https://openalex.org/W3172112830","https://openalex.org/W3183226462","https://openalex.org/W4210606756","https://openalex.org/W4213019668","https://openalex.org/W4386065383","https://openalex.org/W4386076683","https://openalex.org/W4387385612","https://openalex.org/W4387969704","https://openalex.org/W4388430331","https://openalex.org/W4389523832","https://openalex.org/W4390874566","https://openalex.org/W4394841935","https://openalex.org/W4399180739","https://openalex.org/W4399343407","https://openalex.org/W4402446139","https://openalex.org/W4402704565","https://openalex.org/W4402716381","https://openalex.org/W4402727007","https://openalex.org/W4402727558","https://openalex.org/W4402727764","https://openalex.org/W4402753899","https://openalex.org/W4402917081","https://openalex.org/W4402996499","https://openalex.org/W4404199570","https://openalex.org/W4404690131","https://openalex.org/W4404781340","https://openalex.org/W4404783175","https://openalex.org/W4405510969","https://openalex.org/W4405596328","https://openalex.org/W4410706693","https://openalex.org/W4415537998"],"related_works":[],"abstract_inverted_index":{"Object":[0],"description":[1,89,117],"plays":[2],"an":[3,79],"important":[4,62],"role":[5],"for":[6,32],"visually":[7],"impaired":[8],"individuals":[9],"to":[10,55,97,150],"understand":[11],"and":[12,28,112],"compare":[13],"the":[14,37,56,73,116,127,152,162,168,171],"differences":[15],"between":[16],"objects.":[17],"Recent":[18],"multimodal":[19],"large":[20],"language":[21],"models":[22,42],"(MLLMs)":[23],"exhibit":[24],"powerful":[25],"perceptual":[26],"abilities":[27],"demonstrate":[29,151],"impressive":[30],"potential":[31],"generating":[33],"object-centric":[34],"descriptions.":[35,103,160],"However,":[36],"descriptions":[38],"generated":[39],"by":[40],"such":[41],"may":[43,70],"still":[44],"usually":[45],"contain":[46],"a":[47,86],"lot":[48],"of":[49,75,78,129,154,170],"content":[50],"that":[51],"is":[52,176],"not":[53,124],"relevant":[54],"user":[57,144],"intent":[58],"or":[59,138],"miss":[60],"some":[61],"object":[63,88,102,130,159],"dimension":[64,109],"details.":[65],"Under":[66],"special":[67],"scenarios,":[68],"users":[69],"only":[71,125],"need":[72],"details":[74,100,131],"certain":[76],"dimensions":[77,141],"object.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"propose":[85],"training-free":[87],"refinement":[90],"pipeline,":[91],"<bold":[92],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[93,181],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Dimension":[94],"Tailor</b>,":[95],"designed":[96],"enhance":[98],"user-specified":[99,119],"in":[101,136],"This":[104],"pipeline":[105,164],"includes":[106],"three":[107],"steps:":[108],"extracting,":[110],"erasing,":[111],"supplementing,":[113],"which":[114],"decompose":[115],"into":[118],"dimensions.":[120],"Dimension":[121,155],"Tailor":[122,156],"can":[123,165],"improve":[126,167],"quality":[128],"but":[132],"also":[133],"offer":[134],"flexibility":[135],"including":[137],"excluding":[139],"specific":[140],"based":[142],"on":[143,157],"preferences.":[145],"We":[146],"conducted":[147],"extensive":[148],"experiments":[149],"effectiveness":[153],"controllable":[158],"Notably,":[161],"proposed":[163],"consistently":[166],"performance":[169],"recent":[172],"MLLMs.":[173],"The":[174],"code":[175],"currently":[177],"accessible":[178],"at":[179],"<uri":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/PRIS-CV/ControllableObjectDescription</uri>.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}