{"id":"https://openalex.org/W4406523182","doi":"https://doi.org/10.1109/tpami.2025.3531452","title":"<i>RelationLMM</i>: Large Multimodal Model as Open and Versatile Visual Relationship Generalist","display_name":"<i>RelationLMM</i>: Large Multimodal Model as Open and Versatile Visual Relationship Generalist","publication_year":2025,"publication_date":"2025-01-17","ids":{"openalex":"https://openalex.org/W4406523182","doi":"https://doi.org/10.1109/tpami.2025.3531452","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031220"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3531452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3531452","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103221862","display_name":"Chi Xie","orcid":"https://orcid.org/0000-0002-5808-1742"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Xie","raw_affiliation_strings":["School of Software Engineering, Tongji University, Shanghai, China","School of Software EngineeringTongji University"],"raw_orcid":"https://orcid.org/0000-0002-5808-1742","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Software EngineeringTongji University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043630267","display_name":"Shuang Liang","orcid":"https://orcid.org/0000-0003-0457-6093"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Liang","raw_affiliation_strings":["School of Software Engineering, Tongji University, Shanghai, China","School of Software EngineeringTongji University"],"raw_orcid":"https://orcid.org/0000-0003-0457-6093","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Software EngineeringTongji University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119268664","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-9059-330X"},"institutions":[{"id":"https://openalex.org/I4210092218","display_name":"Sensimetrics Corporation","ror":"https://ror.org/00h7y2d26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092218"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Sensetime Research, Hong Kong","Sensetime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sensetime Research, Hong Kong","institution_ids":["https://openalex.org/I4210092218"]},{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205468","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0002-1521-8163"},"institutions":[{"id":"https://openalex.org/I4210092218","display_name":"Sensimetrics Corporation","ror":"https://ror.org/00h7y2d26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092218"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Sensetime Research, Hong Kong","Sensetime Research"],"raw_orcid":"https://orcid.org/0000-0002-1521-8163","affiliations":[{"raw_affiliation_string":"Sensetime Research, Hong Kong","institution_ids":["https://openalex.org/I4210092218"]},{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860742","display_name":"Feng Zhu","orcid":"https://orcid.org/0009-0002-5759-9176"},"institutions":[{"id":"https://openalex.org/I4210092218","display_name":"Sensimetrics Corporation","ror":"https://ror.org/00h7y2d26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092218"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Zhu","raw_affiliation_strings":["Sensetime Research, Hong Kong","Sensetime Research"],"raw_orcid":"https://orcid.org/0009-0002-5759-9176","affiliations":[{"raw_affiliation_string":"Sensetime Research, Hong Kong","institution_ids":["https://openalex.org/I4210092218"]},{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024522346","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0001-5874-131X"},"institutions":[{"id":"https://openalex.org/I4210092218","display_name":"Sensimetrics Corporation","ror":"https://ror.org/00h7y2d26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092218"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Sensetime Research, Hong Kong","Sensetime Research"],"raw_orcid":"https://orcid.org/0000-0001-5874-131X","affiliations":[{"raw_affiliation_string":"Sensetime Research, Hong Kong","institution_ids":["https://openalex.org/I4210092218"]},{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Yichen Wei","orcid":"https://orcid.org/0000-0001-5473-4112"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Yichen Wei","raw_affiliation_strings":["Shukun Technology, Vienna, Austria","Shukun Technology"],"raw_orcid":"https://orcid.org/0000-0001-5473-4112","affiliations":[{"raw_affiliation_string":"Shukun Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Shukun Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2358,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.94288055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"47","issue":"5","first_page":"3515","last_page":"3529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8410000205039978,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8410000205039978,"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/T10799","display_name":"Data Visualization and Analytics","score":0.8048999905586243,"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/computer-science","display_name":"Computer science","score":0.664339542388916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5835452079772949},{"id":"https://openalex.org/keywords/generalist-and-specialist-species","display_name":"Generalist and specialist species","score":0.44036561250686646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43903791904449463},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3715948164463043},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34434202313423157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.664339542388916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835452079772949},{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.44036561250686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43903791904449463},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3715948164463043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34434202313423157},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C185933670","wikidata":"https://www.wikidata.org/wiki/Q52105","display_name":"Habitat","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3531452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3531452","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40031220","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031220","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4882422340","display_name":null,"funder_award_id":"62076183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7745458035","display_name":null,"funder_award_id":"23511103100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":104,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1891689858","https://openalex.org/W2169393274","https://openalex.org/W2214124602","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2561715562","https://openalex.org/W2579549467","https://openalex.org/W2795378892","https://openalex.org/W2799263800","https://openalex.org/W2883170015","https://openalex.org/W2886970679","https://openalex.org/W2888096830","https://openalex.org/W2896457183","https://openalex.org/W2962202279","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2964225075","https://openalex.org/W2967870022","https://openalex.org/W2983943451","https://openalex.org/W2997150218","https://openalex.org/W3034538190","https://openalex.org/W3036686441","https://openalex.org/W3096609285","https://openalex.org/W3108864070","https://openalex.org/W3151099711","https://openalex.org/W3153149165","https://openalex.org/W3160447289","https://openalex.org/W3168279596","https://openalex.org/W3174012740","https://openalex.org/W3174164794","https://openalex.org/W3174293538","https://openalex.org/W3181556077","https://openalex.org/W3201861986","https://openalex.org/W4288083516","https://openalex.org/W4312241193","https://openalex.org/W4312502942","https://openalex.org/W4312563197","https://openalex.org/W4312596525","https://openalex.org/W4312613394","https://openalex.org/W4312770707","https://openalex.org/W4312848112","https://openalex.org/W4312873085","https://openalex.org/W4312960102","https://openalex.org/W4313176000","https://openalex.org/W4313406113","https://openalex.org/W4319783489","https://openalex.org/W4366352717","https://openalex.org/W4379382409","https://openalex.org/W4380303580","https://openalex.org/W4381611105","https://openalex.org/W4382240040","https://openalex.org/W4386057783","https://openalex.org/W4386065350","https://openalex.org/W4386065815","https://openalex.org/W4386071767","https://openalex.org/W4386071869","https://openalex.org/W4386075638","https://openalex.org/W4386075828","https://openalex.org/W4386076270","https://openalex.org/W4386076271","https://openalex.org/W4388145690","https://openalex.org/W4388579765","https://openalex.org/W4389519620","https://openalex.org/W4390872009","https://openalex.org/W4390872408","https://openalex.org/W4390872535","https://openalex.org/W4390873003","https://openalex.org/W4390873619","https://openalex.org/W4390873633","https://openalex.org/W4390873637","https://openalex.org/W4390873645","https://openalex.org/W4390874575","https://openalex.org/W4390874582","https://openalex.org/W4394597131","https://openalex.org/W4402727764","https://openalex.org/W6632922691","https://openalex.org/W6778883912","https://openalex.org/W6784094891","https://openalex.org/W6791353385","https://openalex.org/W6799822930","https://openalex.org/W6801512601","https://openalex.org/W6809646742","https://openalex.org/W6839034341","https://openalex.org/W6839220867","https://openalex.org/W6843484045","https://openalex.org/W6845723861","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6852874933","https://openalex.org/W6852999659","https://openalex.org/W6853450284","https://openalex.org/W6854262950","https://openalex.org/W6854308264","https://openalex.org/W6854915240","https://openalex.org/W6856224812","https://openalex.org/W6857109777","https://openalex.org/W6857487352","https://openalex.org/W6858380932","https://openalex.org/W6858602045"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Visual":[0],"relationships":[1],"are":[2],"crucial":[3],"for":[4,33,69,121],"visual":[5,95,160],"perception":[6],"and":[7,9,18,42,49,54,86,109,139,146,175,183],"reasoning,":[8],"cover":[10],"tasks":[11,97,108,136],"like":[12],"Scene":[13],"Graph":[14],"Generation,":[15],"Human-Object":[16],"Interaction,":[17],"object":[19],"affordance.":[20],"Despite":[21],"significant":[22],"efforts,":[23],"this":[24],"field":[25],"still":[26],"suffers":[27],"from":[28],"the":[29,79,101,104,119],"following":[30],"limitations:":[31],"specialists":[32],"a":[34,64,159,165],"specific":[35],"task":[36,44],"without":[37,151],"considering":[38,126],"similar":[39],"ones,":[40],"strict":[41],"complex":[43],"formulations":[45],"with":[46,52,88,164,180],"limited":[47],"flexibility,":[48],"underexploited":[50],"reasoning":[51,87],"language":[53],"knowledge.":[55],"To":[56],"solve":[57,114],"these":[58,115],"limitations,":[59],"we":[60],"seek":[61],"to":[62,93,134,177],"build":[63,158],"new":[65],"framework,":[66],"one":[67,181,184],"model":[68,182],"all":[70,150],"tasks,":[71,83,179],"over":[72],"Large":[73],"Multimodal":[74],"Models":[75],"(LMMs).":[76],"LMMs":[77],"offer":[78],"potential":[80],"of":[81,186],"unifying":[82],"flexible":[84,176],"forms,":[85],"language.":[89],"However,":[90],"they":[91],"fail":[92],"handle":[94],"relationship":[96,161],"well.":[98],"We":[99,113,132],"find":[100],"obstacles":[102],"include":[103],"conflicts":[105],"between":[106],"different":[107,178],"insufficient":[110],"instance-level":[111],"information.":[112],"problems":[116],"by":[117],"reforming":[118],"data":[120],"LMMs,":[122],"rather":[123],"than":[124],"architectures,":[125],"their":[127],"strong":[128],"language-in":[129],"language-out":[130],"capability.":[131],"propose":[133],"disassemble":[135],"into":[137],"simple":[138,166],"common":[140],"sub-tasks,":[141],"verbally":[142],"estimate":[143],"instance":[144,148],"confidence,":[145],"augment":[147],"diversity,":[149],"additional":[152],"modules.":[153],"These":[154],"strategies":[155],"help":[156],"us":[157],"generalist,":[162],"RelationLMM,":[163],"architecture.":[167],"Exhaustive":[168],"experiments":[169],"demonstrate":[170],"RelationLMM":[171],"is":[172],"strong,":[173],"generalizable":[174],"suite":[185],"weight.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-01-18T00:00:00"}
