{"id":"https://openalex.org/W4413157068","doi":"https://doi.org/10.1109/cvpr52734.2025.00753","title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","display_name":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413157068","doi":"https://doi.org/10.1109/cvpr52734.2025.00753"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5018417380","display_name":"SeungJu Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"SeungJu Cha","raw_affiliation_strings":["Hanyang University,South Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110525949","display_name":"Kwan-Young Lee","orcid":"https://orcid.org/0000-0001-9251-5877"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanyoung Lee","raw_affiliation_strings":["Hanyang University,South Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025866986","display_name":"Ye\u2010Chan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ye-Chan Kim","raw_affiliation_strings":["Hanyang University,South Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051407073","display_name":"Hyunwoo Oh","orcid":"https://orcid.org/0000-0003-4224-8808"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo Oh","raw_affiliation_strings":["Hanyang University,South Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dong-Jin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Jin Kim","raw_affiliation_strings":["Hanyang University,South Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018417380"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10133365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8041","last_page":"8050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9839000105857849,"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/T10028","display_name":"Topic Modeling","score":0.9839000105857849,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9830999970436096,"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/T12031","display_name":"Speech and dialogue systems","score":0.9376999735832214,"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/diffusion","display_name":"Diffusion","score":0.6331520080566406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5882239937782288},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15095114707946777},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.07334581017494202}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6331520080566406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5882239937782288},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15095114707946777},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.07334581017494202}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2963691377","https://openalex.org/W2963775347","https://openalex.org/W2964225075","https://openalex.org/W2970641574","https://openalex.org/W3138516171","https://openalex.org/W4312933868","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4390872387","https://openalex.org/W4390873054","https://openalex.org/W4390873732","https://openalex.org/W4393148852","https://openalex.org/W4402618831","https://openalex.org/W4402715994","https://openalex.org/W4402753551","https://openalex.org/W4402775818","https://openalex.org/W4403601051","https://openalex.org/W4404984122","https://openalex.org/W4409263010"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"large-scale":[1],"text-to-image":[2,44,51],"diffusion":[3,45],"models":[4],"generate":[5],"photorealistic":[6],"images":[7,85,116],"but":[8],"often":[9],"struggle":[10],"to":[11,20,24,35,86,104,137],"accurately":[12,105],"depict":[13],"interactions":[14,42,119],"between":[15,58,110],"humans":[16,111],"and":[17,61,78,112],"objects":[18],"due":[19],"their":[21],"limited":[22],"ability":[23],"differentiate":[25],"various":[26,71],"interaction":[27,59,72,81,109],"words.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,69],"propose":[33],"VerbDiff":[34,47],"address":[36],"the":[37,56,64,88,102,107,127,131],"challenge":[38],"of":[39,66,133],"capturing":[40],"nuanced":[41],"within":[43],"models.":[46],"is":[48],"a":[49],"novel":[50],"generation":[52],"model":[53,89,103],"that":[54],"weakens":[55],"bias":[57],"words":[60,73,77,95],"objects,":[62,113],"enhancing":[63],"understanding":[65],"interactions.":[67],"Specifically,":[68],"disentangle":[70],"from":[74,83],"frequency-based":[75],"anchor":[76],"leverage":[79],"localized":[80],"regions":[82],"generated":[84],"help":[87],"better":[90],"capture":[91],"semantics":[92],"in":[93],"distinctive":[94],"without":[96],"extra":[97],"conditions.":[98],"Our":[99],"approach":[100],"enables":[101],"understand":[106],"intended":[108],"producing":[114],"high-quality":[115],"with":[117,121],"accurate":[118],"aligned":[120],"specified":[122],"verbs.":[123],"Extensive":[124],"experiments":[125],"on":[126],"HICO-DET":[128],"dataset":[129],"demonstrate":[130],"effectiveness":[132],"our":[134],"method":[135],"compared":[136],"previous":[138],"approaches.":[139]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}