{"id":"https://openalex.org/W4412404211","doi":"https://doi.org/10.1109/tcsvt.2025.3588357","title":"Generalized Visual Relation Detection With Diffusion Models","display_name":"Generalized Visual Relation Detection With Diffusion Models","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412404211","doi":"https://doi.org/10.1109/tcsvt.2025.3588357"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3588357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3588357","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/A5103043311","display_name":"Kaifeng Gao","orcid":"https://orcid.org/0000-0003-2450-6551"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaifeng Gao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460974","display_name":"Siqi Chen","orcid":"https://orcid.org/0000-0002-0800-0713"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759885","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-7361-3084"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633158","display_name":"Qianru Sun","orcid":"https://orcid.org/0000-0003-2689-317X"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianru Sun","raw_affiliation_strings":["School of Information Systems, Singapore Management University, Bras Basah, Singapore","School of Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Information Systems, Singapore Management University, Bras Basah, Singapore","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103043311"],"corresponding_institution_ids":["https://openalex.org/I168879160","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14559064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"1","first_page":"1203","last_page":"1215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9301999807357788,"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":0.9301999807357788,"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/relation","display_name":"Relation (database)","score":0.577835738658905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5628310441970825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39595869183540344},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35582059621810913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35410451889038086},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2478232979774475}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.577835738658905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5628310441970825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39595869183540344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35582059621810913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35410451889038086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2478232979774475}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3588357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3588357","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:ink.library.smu.edu.sg:sis_research-11922","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10920","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TCSVT.2025.3588357","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2655623952","display_name":null,"funder_award_id":"226-2024-00058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G381587919","display_name":null,"funder_award_id":"LD25F020001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5540768979","display_name":null,"funder_award_id":"62337001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6689777572","display_name":null,"funder_award_id":"226-2025-00057","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2141461755","https://openalex.org/W2250378130","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2579549467","https://openalex.org/W2962739339","https://openalex.org/W2963486920","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2964225075","https://openalex.org/W2997150218","https://openalex.org/W3023511145","https://openalex.org/W3035017890","https://openalex.org/W3049440217","https://openalex.org/W3081642947","https://openalex.org/W3096609285","https://openalex.org/W3151099711","https://openalex.org/W3173859428","https://openalex.org/W3191092153","https://openalex.org/W3209102402","https://openalex.org/W3217030260","https://openalex.org/W4250643848","https://openalex.org/W4311415873","https://openalex.org/W4312377805","https://openalex.org/W4312446811","https://openalex.org/W4312538795","https://openalex.org/W4312563197","https://openalex.org/W4312574495","https://openalex.org/W4312695182","https://openalex.org/W4312747482","https://openalex.org/W4312873085","https://openalex.org/W4312933868","https://openalex.org/W4312960102","https://openalex.org/W4313037583","https://openalex.org/W4366352717","https://openalex.org/W4379108576","https://openalex.org/W4382240040","https://openalex.org/W4385245566","https://openalex.org/W4386071767","https://openalex.org/W4386072307","https://openalex.org/W4386076396","https://openalex.org/W4386076501","https://openalex.org/W4387092463","https://openalex.org/W4390872297","https://openalex.org/W4391248741","https://openalex.org/W4394698791","https://openalex.org/W4397026441","https://openalex.org/W4401212733","https://openalex.org/W4401567860","https://openalex.org/W4402727824","https://openalex.org/W4402968873","https://openalex.org/W4405126049"],"related_works":["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","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Visual":[0],"relation":[1,30,164],"detection":[2,225],"(VRD)":[3],"aims":[4],"to":[5,28,34,89,100,161,166,184,233],"identify":[6],"relationships":[7],"(or":[8],"interactions)":[9],"between":[10],"object":[11],"pairs":[12,142,168],"in":[13,104,116,125,220],"an":[14,129],"image.":[15],"Although":[16],"recent":[17],"VRD":[18,103,200],"models":[19,99],"have":[20],"achieved":[21],"impressive":[22],"performance,":[23],"they":[24],"are":[25,148],"all":[26,122],"restricted":[27],"pre-defined":[29,190],"categories,":[31],"while":[32],"failing":[33],"consider":[35],"the":[36,47,77,113,126,133,135,153,163,176,189,234],"<italic":[37],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[38],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">semantic":[39],"ambiguity</i>":[40],"characteristic":[41],"of":[42,49,140,193,238],"visual":[43,50,91,136,186],"relations.":[44],"Unlike":[45],"objects,":[46],"appearance":[48],"relations":[51,92,124,187],"is":[52,182],"always":[53],"subtle":[54],"and":[55,73,79,96,120,137,147,210,226,236],"can":[56,68],"be":[57,69],"described":[58],"by":[59,169,215],"multiple":[60],"predicate":[61],"words":[62,165],"from":[63,76,175],"different":[64],"perspectives,":[65],"e.g.,":[66],"\u201cride\u201d":[67],"depicted":[70],"as":[71,93,128,144],"\u201crace\u201d":[72],"\u201csit":[74],"on\u201d,":[75],"sports":[78],"spatial":[80],"position":[81],"views,":[82],"respectively.":[83],"To":[84,195],"this":[85,198],"end,":[86],"we":[87,155,202],"propose":[88],"model":[90,112],"continuous":[94],"embeddings,":[95],"design":[97,156],"diffusion":[98,114],"achieve":[101],"generalized":[102,199],"a":[105,117,157],"conditional":[106,145],"generative":[107,178],"manner,":[108],"termed":[109],"Diff-VRD.":[110,239],"We":[111],"process":[115],"latent":[118],"space":[119],"generate":[121,185],"possible":[123],"image":[127,216],"embedding":[130],"sequence.":[131],"During":[132],"generation,":[134,154],"text":[138],"embeddings":[139],"subject-object":[141,167],"serve":[143],"signals":[146],"injected":[149],"via":[150],"cross-attention.":[151],"After":[152],"subsequent":[158],"matching":[159],"stage":[160],"assign":[162],"considering":[170],"their":[171],"semantic":[172],"similarities.":[173],"Benefiting":[174],"diffusion-based":[177],"process,":[179],"our":[180],"Diff-VRD":[181],"able":[183],"beyond":[188],"category":[191],"labels":[192],"datasets.":[194],"properly":[196],"evaluate":[197],"task,":[201],"introduce":[203],"two":[204],"evaluation":[205],"metrics,":[206],"i.e.,":[207],"text-to-image":[208],"retrieval":[209],"SPICE":[211],"PR":[212],"Curve":[213],"inspired":[214],"captioning.":[217],"Extensive":[218],"experiments":[219],"both":[221],"human-object":[222],"interaction":[223],"(HOI)":[224],"scene":[227],"graph":[228],"generation":[229],"(SGG)":[230],"benchmarks":[231],"attest":[232],"superiority":[235],"effectiveness":[237]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}